diff --git a/content/publication/aksu-etal-2021-velocidapter/index.md b/content/publication/aksu-etal-2021-velocidapter/index.md index 82f7444..f1cbd94 100644 --- a/content/publication/aksu-etal-2021-velocidapter/index.md +++ b/content/publication/aksu-etal-2021-velocidapter/index.md @@ -4,7 +4,7 @@ title: 'Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synt authors: - Ibrahim Taha Aksu - Zhengyuan Liu -- Min-Yen Kan +- min - Nancy Chen date: '2021-07-01' publishDate: '2024-07-05T17:09:42.645613Z' diff --git a/content/publication/dou-etal-2022-towards/index.md b/content/publication/dou-etal-2022-towards/index.md index 80ab2b5..7a92e1d 100644 --- a/content/publication/dou-etal-2022-towards/index.md +++ b/content/publication/dou-etal-2022-towards/index.md @@ -8,7 +8,7 @@ authors: - Dingzirui Wang - Wanxiang Che - Dechen Zhan -- Min-Yen Kan +- min - Jian-Guang Lou date: '2022-12-01' publishDate: '2024-07-05T17:09:42.603419Z' diff --git a/content/publication/han-etal-2022-mm/index.md b/content/publication/han-etal-2022-mm/index.md index 4f41024..9cb0ca8 100644 --- a/content/publication/han-etal-2022-mm/index.md +++ b/content/publication/han-etal-2022-mm/index.md @@ -4,7 +4,7 @@ title: 'MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast a authors: - Wei Han - Hui Chen -- Min-Yen Kan +- min - Soujanya Poria date: '2022-12-01' publishDate: '2024-07-05T17:09:42.610472Z' diff --git a/content/publication/han-etal-2024-self/index.md b/content/publication/han-etal-2024-self/index.md index fbf6297..0688a16 100644 --- a/content/publication/han-etal-2024-self/index.md +++ b/content/publication/han-etal-2024-self/index.md @@ -4,7 +4,7 @@ title: Self-Adaptive Sampling for Accurate Video Question Answering on Image Tex authors: - Wei Han - Hui Chen -- Min-Yen Kan +- min - Soujanya Poria date: '2024-06-01' publishDate: '2024-07-05T17:09:42.578623Z' diff --git a/content/publication/huang-etal-2022-lightweight/index.md b/content/publication/huang-etal-2022-lightweight/index.md index d0efc15..a456c54 100644 --- a/content/publication/huang-etal-2022-lightweight/index.md +++ b/content/publication/huang-etal-2022-lightweight/index.md @@ -5,7 +5,7 @@ authors: - Abhinav Ramesh Kashyap - Yanxia Qin - Yajing Yang -- Min-Yen Kan +- min date: '2022-10-01' publishDate: '2024-07-05T10:15:26.841390Z' publication_types: diff --git a/content/publication/jain-etal-2022-comparative/index.md b/content/publication/jain-etal-2022-comparative/index.md index b4df4e5..cb6c493 100644 --- a/content/publication/jain-etal-2022-comparative/index.md +++ b/content/publication/jain-etal-2022-comparative/index.md @@ -3,7 +3,7 @@ title: Comparative Snippet Generation authors: - Saurabh Jain - Yisong Miao -- Min-Yen Kan +- min date: '2022-05-01' publishDate: '2024-07-05T17:09:42.617512Z' publication_types: diff --git a/publications.bib b/publications.bib index f1de23a..5081b98 100644 --- a/publications.bib +++ b/publications.bib @@ -17,111 +17,417 @@ @inproceedings{han-etal-2024-self abstract = "Image{--}text models (ITMs) is the prevalent architecture to solve video question{--}answering tasks, which requires only a few input frames to save huge computational cost compared to video{--}language models.However, we find existent ITM video question{--}answering solutions either 1) adopt simplistic and unintentional sampling strategies, which may miss key frames to offer the answer clues; or 2) sample a large number of frames into divided groups, which the computational sources can not accommodate. In this work, we aim at an efficient sampling method towards the few-frame situations.We first summarize a family of prior sampling methods based on question{--}frame correlation into a unified one, dubbed *Most Implied Frames* (MIF). Through some primary results and analysis, Through analysis, we form a hypothesis that question-aware sampling is not necessary, from which we further propose the other method *Most Dominant Frames* (MDF).Experimental results on four public datasets and three advanced ITMs demonstrate that our proposed strategies can boost the performance for image{--}text pretrained models, and have a wide application scenario in terms of model architectures and dataset types. Our code is available at https://github.com/declare-lab/Sealing\url{https://github.com/declare-lab/Sealing}.", } -@inproceedings{aksu-etal-2022-n, - title = "N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking", - author = "Aksu, Ibrahim and - Liu, Zhengyuan and +@inproceedings{li-etal-2024-uno, + title = "{UNO}-{DST}: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking", + author = "Li, Chuang and + Zhang, Yan and Kan, Min-Yen and - Chen, Nancy", - editor = "Muresan, Smaranda and - Nakov, Preslav and - Villavicencio, Aline", - booktitle = "Findings of the Association for Computational Linguistics: ACL 2022", - month = may, - year = "2022", - address = "Dublin, Ireland", + Li, Haizhou", + editor = "Duh, Kevin and + Gomez, Helena and + Bethard, Steven", + booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024", + month = jun, + year = "2024", + address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.findings-acl.131", - doi = "10.18653/v1/2022.findings-acl.131", - pages = "1659--1671", - abstract = "Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.", + url = "https://aclanthology.org/2024.findings-naacl.187", + pages = "2972--2983", + abstract = "Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, but ignore unlabelled data in the target domain.We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training methods. Our method incorporates auxiliary tasks that generate slot types as inverse prompts for main tasks, creating slot values during joint training. Cycle consistency between these two tasks enables the generation and selection of quality samples in unknown target domains for subsequent fine-tuning. This approach also facilitates automatic label creation, thereby optimizing the training and fine-tuning of DST models. We demonstrate this method{'}s effectiveness on general language models in zero-shot scenarios, improving average joint goal accuracy by 8{\%} across all domains in MultiWOZ.", } -@inproceedings{zhang-etal-2022-interpreting, - title = "Interpreting the Robustness of Neural {NLP} Models to Textual Perturbations", - author = "Zhang, Yunxiang and +@inproceedings{zhang-etal-2024-nnose, + title = "{NNOSE}: Nearest Neighbor Occupational Skill Extraction", + author = "Zhang, Mike and + van der Goot, Rob and + Kan, Min-Yen and + Plank, Barbara", + editor = "Graham, Yvette and + Purver, Matthew", + booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = mar, + year = "2024", + address = "St. Julian{'}s, Malta", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2024.eacl-long.35", + pages = "589--608", + abstract = "The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text. With the advent of English benchmark job description datasets, there is a need for systems that handle their diversity well. We tackle the complexity in occupational skill datasets tasks{---}combining and leveraging multiple datasets for skill extraction, to identify rarely observed skills within a dataset, and overcoming the scarcity of skills across datasets. In particular, we investigate the retrieval-augmentation of language models, employing an external datastore for retrieving similar skills in a dataset-unifying manner. Our proposed method, \textbf{N}earest \textbf{N}eighbor \textbf{O}ccupational \textbf{S}kill \textbf{E}xtraction (NNOSE) effectively leverages multiple datasets by retrieving neighboring skills from other datasets in the datastore. This improves skill extraction \textit{without} additional fine-tuning. Crucially, we observe a performance gain in predicting infrequent patterns, with substantial gains of up to 30{\%} span-F1 in cross-dataset settings.", +} + +@inproceedings{meng-etal-2023-followupqg, + title = "{F}ollowup{QG}: Towards information-seeking follow-up question generation", + author = "Meng, Yan and Pan, Liangming and - Tan, Samson and + Cao, Yixin and Kan, Min-Yen", - editor = "Muresan, Smaranda and + editor = "Park, Jong C. and + Arase, Yuki and + Hu, Baotian and + Lu, Wei and + Wijaya, Derry and + Purwarianti, Ayu and + Krisnadhi, Adila Alfa", + booktitle = "Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = nov, + year = "2023", + address = "Nusa Dua, Bali", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.ijcnlp-main.17", + doi = "10.18653/v1/2023.ijcnlp-main.17", + pages = "252--271", +} + +@inproceedings{pan-etal-2023-investigating, + title = "Investigating Zero- and Few-shot Generalization in Fact Verification", + author = "Pan, Liangming and + Zhang, Yunxiang and + Kan, Min-Yen", + editor = "Park, Jong C. and + Arase, Yuki and + Hu, Baotian and + Lu, Wei and + Wijaya, Derry and + Purwarianti, Ayu and + Krisnadhi, Adila Alfa", + booktitle = "Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = nov, + year = "2023", + address = "Nusa Dua, Bali", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.ijcnlp-main.34", + doi = "10.18653/v1/2023.ijcnlp-main.34", + pages = "511--524", +} +@inproceedings{pan-etal-2023-attacking, + title = "Attacking Open-domain Question Answering by Injecting Misinformation", + author = "Pan, Liangming and + Chen, Wenhu and + Kan, Min-Yen and + Wang, William Yang", + editor = "Park, Jong C. and + Arase, Yuki and + Hu, Baotian and + Lu, Wei and + Wijaya, Derry and + Purwarianti, Ayu and + Krisnadhi, Adila Alfa", + booktitle = "Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = nov, + year = "2023", + address = "Nusa Dua, Bali", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.ijcnlp-main.35", + doi = "10.18653/v1/2023.ijcnlp-main.35", + pages = "525--539", +} + +@inproceedings{pan-etal-2023-risk, + title = "On the Risk of Misinformation Pollution with Large Language Models", + author = "Pan, Yikang and + Pan, Liangming and + Chen, Wenhu and Nakov, Preslav and - Villavicencio, Aline", - booktitle = "Findings of the Association for Computational Linguistics: ACL 2022", - month = may, - year = "2022", - address = "Dublin, Ireland", + Kan, Min-Yen and + Wang, William", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", + month = dec, + year = "2023", + address = "Singapore", publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.findings-acl.315", - doi = "10.18653/v1/2022.findings-acl.315", - pages = "3993--4007", - abstract = "Modern Natural Language Processing (NLP) models are known to be sensitive to input perturbations and their performance can decrease when applied to real-world, noisy data. However, it is still unclear why models are less robust to some perturbations than others. In this work, we test the hypothesis that the extent to which a model is affected by an unseen textual perturbation (robustness) can be explained by the learnability of the perturbation (defined as how well the model learns to identify the perturbation with a small amount of evidence). We further give a causal justification for the learnability metric. We conduct extensive experiments with four prominent NLP models {---} TextRNN, BERT, RoBERTa and XLNet {---} over eight types of textual perturbations on three datasets. We show that a model which is better at identifying a perturbation (higher learnability) becomes worse at ignoring such a perturbation at test time (lower robustness), providing empirical support for our hypothesis.", + url = "https://aclanthology.org/2023.findings-emnlp.97", + doi = "10.18653/v1/2023.findings-emnlp.97", + pages = "1389--1403", + abstract = "We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems. We establish a threat model and simulate potential misuse scenarios, both unintentional and intentional, to assess the extent to which LLMs can be utilized to produce misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation (up to 87{\%}) in the performance of ODQA systems. Moreover, we uncover disparities in the attributes associated with persuading humans and machines, presenting an obstacle to current human-centric approaches to combat misinformation. To mitigate the harm caused by LLM-generated misinformation, we propose three defense strategies: misinformation detection, vigilant prompting, and reader ensemble. These approaches have demonstrated promising results, albeit with certain associated costs. Lastly, we discuss the practicality of utilizing LLMs as automatic misinformation generators and provide relevant resources and code to facilitate future research in this area.", +} + +@inproceedings{xie-etal-2023-echo, + title = "{ECH}o: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning", + author = "Xie, Yuxi and + Li, Guanzhen and + Kan, Min-Yen", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", + month = dec, + year = "2023", + address = "Singapore", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.findings-emnlp.268", + doi = "10.18653/v1/2023.findings-emnlp.268", + pages = "4064--4085", + abstract = "We introduce ECHo (Event Causality Inference via Human-Centric Reasoning), a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios. ECHo employs real-world human-centric deductive information building on a television crime drama. ECHo requires the Theory-of-Mind (ToM) ability to understand and reason about social interactions based on multimodal information. Using ECHo, we propose a unified Chain-of-Thought (CoT) framework to assess the reasoning capability of current AI systems. Our ToM-enhanced CoT pipeline accommodates various large foundation models in both zero-shot and few-shot visio-linguistic reasoning. We use this framework to scrutinize recent large foundation models such as InstructGPT and MiniGPT-4 on three diagnostic human-centric tasks. Further analysis demonstrates ECHo as a challenging dataset to expose imperfections and inconsistencies in reasoning. Our data and code are publicly available at [https://github.com/YuxiXie/ECHo](https://github.com/YuxiXie/ECHo).", } -@inproceedings{dou-etal-2022-towards, - title = "Towards Knowledge-Intensive Text-to-{SQL} Semantic Parsing with Formulaic Knowledge", - author = "Dou, Longxu and - Gao, Yan and - Liu, Xuqi and - Pan, Mingyang and - Wang, Dingzirui and - Che, Wanxiang and - Zhan, Dechen and +@inproceedings{li-etal-2023-coannotating, + title = "{C}o{A}nnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation", + author = "Li, Minzhi and + Shi, Taiwei and + Ziems, Caleb and Kan, Min-Yen and - Lou, Jian-Guang", - editor = "Goldberg, Yoav and - Kozareva, Zornitsa and - Zhang, Yue", - booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", + Chen, Nancy and + Liu, Zhengyuan and + Yang, Diyi", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", month = dec, - year = "2022", - address = "Abu Dhabi, United Arab Emirates", + year = "2023", + address = "Singapore", publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.emnlp-main.350", - doi = "10.18653/v1/2022.emnlp-main.350", - pages = "5240--5253", - abstract = "In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by representing formulaic knowledge rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2{\%} improvement overall on KnowSQL.", + url = "https://aclanthology.org/2023.emnlp-main.92", + doi = "10.18653/v1/2023.emnlp-main.92", + pages = "1487--1505", + abstract = "Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance. Given recent developments in Large Language Models (LLMs), models such as ChatGPT demonstrate zero-shot capability on many text-annotation tasks, comparable with or even exceeding human annotators. Such LLMs can serve as alternatives for manual annotation, due to lower costs and higher scalability. However, limited work has leveraged LLMs as complementary annotators, nor explored how annotation work is best allocated among humans and LLMs to achieve both quality and cost objectives. We propose CoAnnotating, a novel paradigm for Human-LLM co-annotation of unstructured texts at scale. Under this framework, we utilize uncertainty to estimate LLMs{'} annotation capability. Our empirical study shows CoAnnotating to be an effective means to allocate work from results on different datasets, with up to 21{\%} performance improvement over random baseline. For code implementation, see https://github.com/SALT-NLP/CoAnnotating.", } -@inproceedings{han-etal-2022-mm, - title = "{MM}-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences", - author = "Han, Wei and - Chen, Hui and +@inproceedings{lu-etal-2023-scitab, + title = "{SCITAB}: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables", + author = "Lu, Xinyuan and + Pan, Liangming and + Liu, Qian and + Nakov, Preslav and + Kan, Min-Yen", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", + month = dec, + year = "2023", + address = "Singapore", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.emnlp-main.483", + doi = "10.18653/v1/2023.emnlp-main.483", + pages = "7787--7813", + abstract = "Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence. We present SCITAB, a challenging evaluation dataset consisting of 1.2K expert-verified scientific claims that 1) originate from authentic scientific publications and 2) require compositional reasoning for verification. The claims are paired with evidence-containing scientific tables annotated with labels. Through extensive evaluations, we demonstrate that SCITAB poses a significant challenge to state-of-the-art models, including table-based pretraining models and large language models. All models except GPT-4 achieved performance barely above random guessing. Popular prompting techniques, such as Chain-of-Thought, do not achieve much performance gains on SCITAB. Our analysis uncovers several unique challenges posed by SCITAB, including table grounding, claim ambiguity, and compositional reasoning. Our codes and data are publicly available at https://github.com/XinyuanLu00/SciTab.", +} + +@inproceedings{rohatgi-etal-2023-acl, + title = "The {ACL} {OCL} Corpus: Advancing Open Science in Computational Linguistics", + author = "Rohatgi, Shaurya and + Qin, Yanxia and + Aw, Benjamin and + Unnithan, Niranjana and + Kan, Min-Yen", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", + month = dec, + year = "2023", + address = "Singapore", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.emnlp-main.640", + doi = "10.18653/v1/2023.emnlp-main.640", + pages = "10348--10361", + abstract = "We present ACL OCL, a scholarly corpus derived from the ACL Anthology to assist Open scientific research in the Computational Linguistics domain. Integrating and enhancing the previous versions of the ACL Anthology, the ACL OCL contributes metadata, PDF files, citation graphs and additional structured full texts with sections, figures, and links to a large knowledge resource (Semantic Scholar). The ACL OCL spans seven decades, containing 73K papers, alongside 210K figures. We spotlight how ACL OCL applies to observe trends in computational linguistics. By detecting paper topics with a supervised neural model, we note that interest in {``}Syntax: Tagging, Chunking and Parsing{''} is waning and {``}Natural Language Generation{''} is resurging. Our dataset is available from HuggingFace (https://huggingface.co/datasets/WINGNUS/ACL-OCL).", +} + + +@inproceedings{diao-etal-2023-doolittle, + title = "Doolittle: Benchmarks and Corpora for Academic Writing Formalization", + author = "Diao, Shizhe and + Lei, Yongyu and + Pan, Liangming and + Fang, Tianqing and + Zhou, Wangchunshu and + Keh, Sedrick and Kan, Min-Yen and - Poria, Soujanya", - editor = "Goldberg, Yoav and - Kozareva, Zornitsa and - Zhang, Yue", - booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", + Zhang, Tong", + editor = "Bouamor, Houda and + Pino, Juan and + Bali, Kalika", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", month = dec, - year = "2022", - address = "Abu Dhabi, United Arab Emirates", + year = "2023", + address = "Singapore", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.emnlp-main.809", + doi = "10.18653/v1/2023.emnlp-main.809", + pages = "13093--13111", + abstract = "Improving the quality of academic writing is a meaningful but challenging task. Conventional methods of language refinement focus on narrow, specific linguistic features within isolated sentences, such as grammatical errors and improper word use. We propose a more general task, Academic Writing Formalization (AWF), to improve the overall quality of formal academic writing at the paragraph level. We formulate this language refinement task as a formal text style transfer task which transfers informal-academic text to formal-academic and contribute a large-scale non-parallel dataset, Doolittle, for this purpose. Concurrently, we apply a method named metric-oriented reinforcement learning (MORL) to two large language models (LLM) where we incorporate different levels of automatic feedback into the training process. Our experiments reveal that existing text transfer models and grammatical error correction models address certain aspects of AWF but still have a significant performance gap compared to human performance. Meanwhile, language models fine-tuned with our MORL method exhibit considerably improved performance, rivaling the latest chatbot ChatGPT, but still have a non-negligible gap compared to the ground truth formal-academic texts in Doolittle.", +} + + +@inproceedings{pan-etal-2023-qacheck, + title = "{QAC}heck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking", + author = "Pan, Liangming and + Lu, Xinyuan and + Kan, Min-Yen and + Nakov, Preslav", + editor = "Feng, Yansong and + Lefever, Els", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", + month = dec, + year = "2023", + address = "Singapore", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.emnlp-demo.23", + doi = "10.18653/v1/2023.emnlp-demo.23", + pages = "264--273", + abstract = "Fact-checking real-world claims often requires intricate, multi-step reasoning due to the absence of direct evidence to support or refute them. However, existing fact-checking systems often lack transparency in their decision-making, making it challenging for users to comprehend their reasoning process. To address this, we propose the Question-guided Multi-hop Fact-Checking (QACheck) system, which guides the model{'}s reasoning process by asking a series of questions critical for verifying a claim. QACheck has five key modules: a claim verifier, a question generator, a question-answering module, a QA validator, and a reasoner. Users can input a claim into QACheck, which then predicts its veracity and provides a comprehensive report detailing its reasoning process, guided by a sequence of (question, answer) pairs. QACheck also provides the source of evidence supporting each question, fostering a transparent, explainable, and user-friendly fact-checking process.", +} + +@inproceedings{ding-etal-2023-cocoscisum, + title = "{C}oco{S}ci{S}um: A Scientific Summarization Toolkit with Compositional Controllability", + author = "Ding, Yixi and + Qin, Yanxia and + Liu, Qian and + Kan, Min-Yen", + editor = "Feng, Yansong and + Lefever, Els", + booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", + month = dec, + year = "2023", + address = "Singapore", publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.emnlp-main.717", - doi = "10.18653/v1/2022.emnlp-main.717", - pages = "10498--10511", - abstract = "Existing multimodal tasks mostly target at the complete input modality setting, i.e., each modality is either complete or completely missing in both training and test sets. However, the randomly missing situations have still been underexplored. In this paper, we present a novel approach named MM-Align to address the missing-modality inference problem. Concretely, we propose 1) an alignment dynamics learning module based on the theory of optimal transport (OT) for missing data imputation; 2) a denoising training algorithm to enhance the quality of imputation as well as the accuracy of model predictions. Compared with previous generative methods which devote to restoring the missing inputs, MM-Align learns to capture and imitate the alignment dynamics between modality sequences. Results of comprehensive experiments on two multimodal tasks empirically demonstrate that our method can perform more accurate and faster inference and alleviate the overfitting issue under different missing conditions.", + url = "https://aclanthology.org/2023.emnlp-demo.47", + doi = "10.18653/v1/2023.emnlp-demo.47", + pages = "518--526", + abstract = "We present a novel toolkit for controlled summarization of scientific documents, designed for the specific needs of the scientific community. Our system generates summaries based on user preferences, adjusting key attributes specifically of length and keyword inclusion. A distinguishing feature is its ability to manage multiple attributes concurrently, demonstrating Compositional Controllability for Scientific Summarization (CocoSciSum). Benchmarked against the strong Flan-T5 baseline, CocoSciSum exhibits superior performance on both the quality of summaries generated and the control over single and multiple attributes. Moreover, CocoSciSum is a user-centric toolkit, supporting user preferences expressed in natural language instructions, and accommodating diverse input document formats. CocoSciSum is available on GitHub (https://github.com/WING-NUS/SciAssist/tree/CocoSciSum) with an introduction video (https://youtu.be/YC1YDeEjAbQ).", } -@inproceedings{jain-etal-2022-comparative, - title = "Comparative Snippet Generation", - author = "Jain, Saurabh and - Miao, Yisong and +@inproceedings{benotti-etal-2023-understanding, + title = "Understanding Ethics in {NLP} Authoring and Reviewing", + author = {Benotti, Luciana and + Fort, Kar{\"e}n and + Kan, Min-Yen and + Tsvetkov, Yulia}, + editor = "Zanzotto, Fabio Massimo and + Pradhan, Sameer", + booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts", + month = may, + year = "2023", + address = "Dubrovnik, Croatia", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.eacl-tutorials.4", + doi = "10.18653/v1/2023.eacl-tutorials.4", + pages = "19--24", + abstract = "With NLP research now quickly being transferred into real-world applications, it is important to be aware of and think through the consequences of our scientific investigation. Such ethical considerations are important in both authoring and reviewing. This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues and review common considerations that recur in NLP research. The methodology is interactive and participatory, including case studies and working in groups. Importantly, the participants will be co-building the tutorial outcomes and will be working to create further tutorial materials to share as public outcomes.", +} + +@inproceedings{malik-etal-2023-udapter, + title = "{UDAPTER} - Efficient Domain Adaptation Using Adapters", + author = "Malik, Bhavitvya and + Ramesh Kashyap, Abhinav and + Kan, Min-Yen and + Poria, Soujanya", + editor = "Vlachos, Andreas and + Augenstein, Isabelle", + booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics", + month = may, + year = "2023", + address = "Dubrovnik, Croatia", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.eacl-main.165", + doi = "10.18653/v1/2023.eacl-main.165", + pages = "2249--2263", + abstract = "We propose two methods to make unsupervised domain adaptation (UDA) more parameter efficient using adapters {--} small bottleneck layers interspersed with every layer of the large-scale pre-trained language model (PLM). The first method deconstructs UDA into a two-step process: first by adding a domain adapter to learn domain-invariant information and then by adding a task adapter that uses domain-invariant information to learn task representations in the source domain. The second method jointly learns a supervised classifier while reducing the divergence measure. Compared to strong baselines, our simple methods perform well in natural language inference (MNLI) and the cross-domain sentiment classification task. We even outperform unsupervised domain adaptation methods such as DANN and DSN in sentiment classification, and we are within 0.85{\%} F1 for natural language inference task, by fine-tuning only a fraction of the full model parameters. We release our code at this URL.", +} + + +@inproceedings{chow-etal-2023-travlr, + title = "{T}ra{VLR}: Now You See It, Now You Don{'}t! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning", + author = "Chow, Keng Ji and + Tan, Samson and Kan, Min-Yen", - editor = "Malmasi, Shervin and - Rokhlenko, Oleg and - Ueffing, Nicola and - Guy, Ido and - Agichtein, Eugene and - Kallumadi, Surya", - booktitle = "Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)", + editor = "Vlachos, Andreas and + Augenstein, Isabelle", + booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics", + month = may, + year = "2023", + address = "Dubrovnik, Croatia", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.eacl-main.242", + doi = "10.18653/v1/2023.eacl-main.242", + pages = "3322--3347", + abstract = "Numerous visio-linguistic (V+L) representation learning methods have been developed, yet existing datasets do not adequately evaluate the extent to which they represent visual and linguistic concepts in a unified space. We propose several novel evaluation settings for V+L models, including cross-modal transfer. Furthermore, existing V+L benchmarks often report global accuracy scores on the entire dataset, making it difficult to pinpoint the specific reasoning tasks that models fail and succeed at. We present TraVLR, a synthetic dataset comprising four V+L reasoning tasks. TraVLR{'}s synthetic nature allows us to constrain its training and testing distributions along task-relevant dimensions, enabling the evaluation of out-of-distribution generalisation. Each example in TraVLR redundantly encodes the scene in two modalities, allowing either to be dropped or added during training or testing without losing relevant information. We compare the performance of four state-of-the-art V+L models, finding that while they perform well on test examples from the same modality, they all fail at cross-modal transfer and have limited success accommodating the addition or deletion of one modality. We release TraVLR as an open challenge for the research community.", +} + +@inproceedings{ou-etal-2023-songs, + title = "Songs Across Borders: Singable and Controllable Neural Lyric Translation", + author = "Ou, Longshen and + Ma, Xichu and + Kan, Min-Yen and + Wang, Ye", + editor = "Rogers, Anna and + Boyd-Graber, Jordan and + Okazaki, Naoaki", + booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = jul, + year = "2023", + address = "Toronto, Canada", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.acl-long.27", + doi = "10.18653/v1/2023.acl-long.27", + pages = "447--467", + abstract = "The development of general-domain neural machine translation (NMT) methods has advanced significantly in recent years, but the lack of naturalness and musical constraints in the outputs makes them unable to produce singable lyric translations. This paper bridges the singability quality gap by formalizing lyric translation into a constrained translation problem, converting theoretical guidance and practical techniques from translatology literature to prompt-driven NMT approaches, exploring better adaptation methods, and instantiating them to an English-Chinese lyric translation system. Our model achieves 99.85{\%}, 99.00{\%}, and 95.52{\%} on length accuracy, rhyme accuracy, and word boundary recall. In our subjective evaluation, our model shows a 75{\%} relative enhancement on overall quality, compared against naive fine-tuning (Code available at \url{https://github.com/Sonata165/ControllableLyricTranslation}).", +} + +@inproceedings{aksu-etal-2023-prompter, + title = "Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation", + author = "Aksu, Ibrahim Taha and + Kan, Min-Yen and + Chen, Nancy", + editor = "Rogers, Anna and + Boyd-Graber, Jordan and + Okazaki, Naoaki", + booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = jul, + year = "2023", + address = "Toronto, Canada", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.acl-long.252", + doi = "10.18653/v1/2023.acl-long.252", + pages = "4588--4603", + abstract = "A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data {---} zero-shot domain adaptation. Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem due to its robustness. However, it has yet to be applied to the zero-shot scenarios, as it is not clear how to apply it unsupervisedly. Our method, Prompter, uses descriptions of target domain slots to generate dynamic prefixes that are concatenated to the key and values at each layer{'}s self-attention mechanism. This allows for the use of prefix-tuning in zero-shot. Prompter outperforms previous methods on both the MultiWOZ and SGD benchmarks. In generating prefixes, our analyses find that Prompter not only utilizes the semantics of slot descriptions but also how often the slots appear together in conversation. Moreover, Prompter{'}s gains are due to its improved ability to distinguish {''}none{''}-valued dialogue slots, compared against baselines.", +} + +@inproceedings{pan-etal-2023-fact, + title = "Fact-Checking Complex Claims with Program-Guided Reasoning", + author = "Pan, Liangming and + Wu, Xiaobao and + Lu, Xinyuan and + Luu, Anh Tuan and + Wang, William Yang and + Kan, Min-Yen and + Nakov, Preslav", + editor = "Rogers, Anna and + Boyd-Graber, Jordan and + Okazaki, Naoaki", + booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", + month = jul, + year = "2023", + address = "Toronto, Canada", + publisher = "Association for Computational Linguistics", + url = "https://aclanthology.org/2023.acl-long.386", + doi = "10.18653/v1/2023.acl-long.386", + pages = "6981--7004", + abstract = "Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Checking (ProgramFC), a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions. We first leverage the in-context learning ability of large language models to generate reasoning programs to guide the verification process. Afterward, we execute the program by delegating each sub-task to the corresponding sub-task handler. This process makes our model both explanatory and data-efficient, providing clear explanations of its reasoning process and requiring minimal training data. We evaluate ProgramFC on two challenging fact-checking datasets and show that it outperforms seven fact-checking baselines across different settings of evidence availability, with explicit output programs that benefit human debugging. Our codes and data are publicly available at \url{https://github.com/mbzuai-nlp/ProgramFC}.", +} + +@inproceedings{zhang-etal-2022-interpreting, + title = "Interpreting the Robustness of Neural {NLP} Models to Textual Perturbations", + author = "Zhang, Yunxiang and + Pan, Liangming and + Tan, Samson and + Kan, Min-Yen", + editor = "Muresan, Smaranda and + Nakov, Preslav and + Villavicencio, Aline", + booktitle = "Findings of the Association for Computational Linguistics: ACL 2022", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.ecnlp-1.7", - doi = "10.18653/v1/2022.ecnlp-1.7", - pages = "49--57", - abstract = "We model products{'} reviews to generate comparative responses consisting of positive and negative experiences regarding the product. Specifically, we generate a single-sentence, comparative response from a given positive and a negative opinion. We contribute the first dataset for this task of Comparative Snippet Generation from contrasting opinions regarding a product, and an analysis of performance of a pre-trained BERT model to generate such snippets.", + url = "https://aclanthology.org/2022.findings-acl.315", + doi = "10.18653/v1/2022.findings-acl.315", + pages = "3993--4007", + abstract = "Modern Natural Language Processing (NLP) models are known to be sensitive to input perturbations and their performance can decrease when applied to real-world, noisy data. However, it is still unclear why models are less robust to some perturbations than others. In this work, we test the hypothesis that the extent to which a model is affected by an unseen textual perturbation (robustness) can be explained by the learnability of the perturbation (defined as how well the model learns to identify the perturbation with a small amount of evidence). We further give a causal justification for the learnability metric. We conduct extensive experiments with four prominent NLP models {---} TextRNN, BERT, RoBERTa and XLNet {---} over eight types of textual perturbations on three datasets. We show that a model which is better at identifying a perturbation (higher learnability) becomes worse at ignoring such a perturbation at test time (lower robustness), providing empirical support for our hypothesis.", } @inproceedings{xu-etal-2022-corefdiffs, @@ -160,75 +466,3 @@ @inproceedings{xu-etal-2022-corefdiffs pages = "471--484", abstract = "Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally. For document-grounded dialog systems, the inter- and intra-document knowledge relations can be used to model such conversational flows. We develop a novel Multi-Document Co-Referential Graph (Coref-MDG) to effectively capture the inter-document relationships based on commonsense and similarity and the intra-document co-referential structures of knowledge segments within the grounding documents. We propose CorefDiffs, a Co-referential and Differential flow management method, to linearize the static Coref-MDG into conversational sequence logic. CorefDiffs performs knowledge selection by accounting for contextual graph structures and the knowledge difference sequences. CorefDiffs significantly outperforms the state-of-the-art by 9.5{\%}, 7.4{\%} and 8.2{\%} on three public benchmarks. This demonstrates that the effective modeling of co-reference and knowledge difference for dialog flows are critical for transitions in document-grounded conversation.", } - -@inproceedings{ramesh-kashyap-etal-2022-different, - title = "So Different Yet So Alike! Constrained Unsupervised Text Style Transfer", - author = "Ramesh Kashyap, Abhinav and - Hazarika, Devamanyu and - Kan, Min-Yen and - Zimmermann, Roger and - Poria, Soujanya", - editor = "Muresan, Smaranda and - Nakov, Preslav and - Villavicencio, Aline", - booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", - month = may, - year = "2022", - address = "Dublin, Ireland", - publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.acl-long.32", - doi = "10.18653/v1/2022.acl-long.32", - pages = "416--431", - abstract = "Automatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content while adapting to the target domain. However, it does not explicitly maintain other attributes between the source and translated text: e.g., text length and descriptiveness. Maintaining constraints in transfer has several downstream applications, including data augmentation and debiasing. We introduce a method for such constrained unsupervised text style transfer by introducing two complementary losses to the generative adversarial network (GAN) family of models. Unlike the competing losses used in GANs, we introduce cooperative losses where the discriminator and the generator cooperate and reduce the same loss. The first is a contrastive loss and the second is a classification loss {---} aiming to regularize the latent space further and bring similar sentences closer together. We demonstrate that such training retains lexical, syntactic and domain-specific constraints between domains for multiple benchmark datasets, including ones where more than one attribute change. We show that the complementary cooperative losses improve text quality, according to both automated and human evaluation measures.", -} - -@inproceedings{qin-etal-2022-gl, - title = "{GL}-{CL}e{F}: A Global{--}Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding", - author = "Qin, Libo and - Chen, Qiguang and - Xie, Tianbao and - Li, Qixin and - Lou, Jian-Guang and - Che, Wanxiang and - Kan, Min-Yen", - editor = "Muresan, Smaranda and - Nakov, Preslav and - Villavicencio, Aline", - booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", - month = may, - year = "2022", - address = "Dublin, Ireland", - publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2022.acl-long.191", - doi = "10.18653/v1/2022.acl-long.191", - pages = "2677--2686", - abstract = "Due to high data demands of current methods, attention to zero-shot cross-lingual spoken language understanding (SLU) has grown, as such approaches greatly reduce human annotation effort. However, existing models solely rely on shared parameters, which can only perform implicit alignment across languages. We present Global-Local Contrastive Learning Framework (GL-CLeF) to address this shortcoming. Specifically, we employ contrastive learning, leveraging bilingual dictionaries to construct multilingual views of the same utterance, then encourage their representations to be more similar than negative example pairs, which achieves to explicitly align representations of similar sentences across languages. In addition, a key step in GL-CLeF is a proposed Local and Global component, which achieves a fine-grained cross-lingual transfer (i.e., sentence-level Local intent transfer, token-level Local slot transfer, and semantic-level Global transfer across intent and slot). Experiments on MultiATIS++ show that GL-CLeF achieves the best performance and successfully pulls representations of similar sentences across languages closer.", -} - -@inproceedings{aksu-etal-2021-velocidapter, - title = "Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation", - author = "Aksu, Ibrahim Taha and - Liu, Zhengyuan and - Kan, Min-Yen and - Chen, Nancy", - editor = "Li, Haizhou and - Levow, Gina-Anne and - Yu, Zhou and - Gupta, Chitralekha and - Sisman, Berrak and - Cai, Siqi and - Vandyke, David and - Dethlefs, Nina and - Wu, Yan and - Li, Junyi Jessy", - booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue", - month = jul, - year = "2021", - address = "Singapore and Online", - publisher = "Association for Computational Linguistics", - url = "https://aclanthology.org/2021.sigdial-1.14", - doi = "10.18653/v1/2021.sigdial-1.14", - pages = "133--143", - abstract = "We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension. Velocidapter augments datasets by simulating synthetic conversations for a task-oriented dialogue domain, requiring a small amount of bootstrapping work for each new domain. We evaluate the efficacy of our framework on a task-oriented dialogue comprehension dataset, MRCWOZ, which we curate by annotating questions for slots in the restaurant, taxi, and hotel domains of the MultiWOZ 2.2 dataset (Zang et al., 2020). We run experiments within a low-resource setting, where we pretrain a model on SQuAD, fine-tuning it on either a small original data or on the synthetic data generated by our framework. Velocidapter shows significant improvements using both the transformer-based BERTBase and BiDAF as base models. We further show that the framework is easy to use by novice users and conclude that Velocidapter can greatly help training over task-oriented dialogues, especially for low-resourced emerging domains.", -} -