diff --git a/content/post/emnlp2023/index.md b/content/post/emnlp2023/index.md new file mode 100644 index 0000000..b4d1073 --- /dev/null +++ b/content/post/emnlp2023/index.md @@ -0,0 +1,33 @@ +--- +# Documentation: https://wowchemy.com/docs/managing-content/ + +title: "1 paper accepted to EMNLP Findings 2023" +subtitle: "" +summary: "" +authors: [] +tags: [] +categories: [] +date: 2023-10-14T09:24:01+02:00 +lastmod: 2023-10-14T09:24:01+02:00 +featured: false +draft: false + +# Featured image +# To use, add an image named `featured.jpg/png` to your page's folder. +# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight. +image: + caption: "" + focal_point: "" + preview_only: false + +# Projects (optional). +# Associate this post with one or more of your projects. +# Simply enter your project's folder or file name without extension. +# E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`. +# Otherwise, set `projects = []`. +projects: [] +--- + +One paper from DFKI-NLP authors has been accepted for publication as a Findings paper at [EMNLP 2023](https://2023.emnlp.org/), the 2023 Conference on Empirical Methods in Natural Language Processing. The conference is planned to be a hybrid meeting and will take place in Singapore, from Dec 6th to Dec 10th, 2023. The paper introduces the InterroLang framework for dialog-based explanations of NLP models and datasets. It adapts the conversational explanation framework TalkToModel to the NLP domain, and add new NLP-specific operations such as free-text rationalizations." + +{{< cite page="/publication/emnlp2023-feldhus-interrolang" view="4" >}} diff --git a/content/publication/emnlp2023-feldhus-interrolang/cite.bib b/content/publication/emnlp2023-feldhus-interrolang/cite.bib new file mode 100644 index 0000000..d691e53 --- /dev/null +++ b/content/publication/emnlp2023-feldhus-interrolang/cite.bib @@ -0,0 +1,9 @@ +@inproceedings{pub14060, + author = {Feldhus, Nils and Wang, Qianli and Anikina, Tatiana and Chopra, Sahil and Oguz, Cennet and Möller, Sebastian}, + editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika}, + title = {InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations}, + booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023. Conference on Empirical Methods in Natural Language Processing (EMNLP-2023), December 6-10, Singapore, Singapore}, + year = {2023}, + month = {12}, + publisher = {Association for Computational Linguistics} +} diff --git a/content/publication/emnlp2023-feldhus-interrolang/index.md b/content/publication/emnlp2023-feldhus-interrolang/index.md new file mode 100644 index 0000000..77f892a --- /dev/null +++ b/content/publication/emnlp2023-feldhus-interrolang/index.md @@ -0,0 +1,69 @@ +--- +# Documentation: https://wowchemy.com/docs/managing-content/ + +title: "InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations" +authors: ["Nils Feldhus", "Qianli Wang", "Tatiana Anikina", "Sahil Chopra", "Cennet Oguz", "Sebastian Möller"] +date: 2023-12-06 +doi: "10.48550/arXiv.2310.05592" + +# Schedule page publish date (NOT publication's date). +publishDate: 2023-10-15 + +# Publication type. +# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article; +# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section; +# 7 = Thesis; 8 = Patent +publication_types: ["1"] + +# Publication name and optional abbreviated publication name. +publication: "Findings of the Association for Computational Linguistics: EMNLP 2023" +publication_short: "Findings EMNLP 2023" + +abstract: "While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system can help users explore datasets and models with explanations in a contextualized manner, e.g. via clarification or follow-up questions, and through a natural language interface. We adapt the conversational explanation framework TalkToModel (Slack et al., 2022) to the NLP domain, add new NLP-specific operations such as free-text rationalization, and illustrate its generalizability on three NLP tasks (dialogue act classification, question answering, hate speech detection). To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models and implement a novel adapter-based approach. We then conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability, i.e. how objectively helpful dialogical explanations are for humans in figuring out the model's predicted label when it's not shown. We found rationalization and feature attribution were helpful in explaining the model behavior. Moreover, users could more reliably predict the model outcome based on an explanation dialogue rather than one-off explanations." + +# Summary. An optional shortened abstract. +summary: "" + +tags: ["Explainability"] +categories: [] +featured: false + +# Custom links (optional). +# Uncomment and edit lines below to show custom links. +# links: +# - name: Follow +# url: https://twitter.com +# icon_pack: fab +# icon: twitter + +url_pdf: "https://arxiv.org/pdf/2310.05592.pdf" +url_code: "https://github.com/DFKI-NLP/InterroLang" +url_dataset: +url_poster: +url_project: +url_slides: +url_source: +url_video: + +# Featured image +# To use, add an image named `featured.jpg/png` to your page's folder. +# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight. +image: + caption: "" + focal_point: "" + preview_only: false + +# Associated Projects (optional). +# Associate this publication with one or more of your projects. +# Simply enter your project's folder or file name without extension. +# E.g. `internal-project` references `content/project/internal-project/index.md`. +# Otherwise, set `projects: []`. +projects: [XAINES] + +# Slides (optional). +# Associate this publication with Markdown slides. +# Simply enter your slide deck's filename without extension. +# E.g. `slides: "example"` references `content/slides/example/index.md`. +# Otherwise, set `slides: ""`. +slides: "" +--- diff --git a/content/publication/vandeghinste-2023-ele-sign/cite.bib b/content/publication/vandeghinste-2023-ele-sign/cite.bib new file mode 100644 index 0000000..6685542 --- /dev/null +++ b/content/publication/vandeghinste-2023-ele-sign/cite.bib @@ -0,0 +1,10 @@ +@incollection{pub13411, + author = {Vandeghinste, Vincent and Sisto, Mirella De and Kopf, Maria and Picron, Davy Van Landuyt and Murtagh, Irene and Avramidis, Eleftherios and Coster, Mathieu De }, + editor = {Giagkou, Maria and Piperidis, Stelios and Rehm, Georg and Dunne, Jane}, + title = {European Language Equality, Report on Europe's Sign Languages}, + booktitle = {Project European Language Equality (ELE)}, + year = {2023}, + month = {5}, + pages = {1--31}, + publisher = {ELE Consortium} +} diff --git a/content/publication/vandeghinste-2023-ele-sign/index.md b/content/publication/vandeghinste-2023-ele-sign/index.md new file mode 100644 index 0000000..4403119 --- /dev/null +++ b/content/publication/vandeghinste-2023-ele-sign/index.md @@ -0,0 +1,69 @@ +--- +# Documentation: https://wowchemy.com/docs/managing-content/ + +title: "European Language Equality, Report on Europe's Sign Languages" +authors: ["Vincent Vandeghinste", "Mirella De Sisto", "Maria Kopf", "Davy Van Landuyt Picron", "Irene Murtagh", "Eleftherios Avramidis", "Mathieu De Coster"] +date: 2023-07-21 +doi: "10.5281/zenodo.8047005" + +# Schedule page publish date (NOT publication's date). +publishDate: 2023-07-21 + +# Publication type. +# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article; +# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section; +# 7 = Thesis; 8 = Patent +publication_types: ["6"] + +# Publication name and optional abbreviated publication name. +publication: "Project European Language Equality (ELE)" +publication_short: "ELE" + +abstract: "This report on Europe's Sign Languages is part of a series of language deliverables developed within the framework of the European Language Equality (ELE) project. The series seeks to not only delineate the current state of affairs for each European language, but to additionally identify the gaps and factors that hinder further development in research and technology. The survey presented here focuses on the condition of Language Technology (LT) with regard to Europe's Sign Languages, a set of languages often forgotten in the context of European Language Equality. With the rise of the deep learning paradigm in artificial intelligence, sign language technologies become technologically feasible, provided that enough data is available to feed this data-hungry paradigm. It is exactly the quality and quantity of data that is the main bottleneck in development of well performing and useful technologies. In the past, there have been several projects aimed at developing sign language technologies and methodologies that have been deemed of little value by the deaf communities. Co-creation and involvement of deaf communities throughout projects and development of technologies ensures that this does not happen again." + +# Summary. An optional shortened abstract. +summary: "" + +tags: ["Machine Translation"] +categories: [] +featured: false + +# Custom links (optional). +# Uncomment and edit lines below to show custom links. +# links: +# - name: Follow +# url: https://twitter.com +# icon_pack: fab +# icon: twitter + +url_pdf: "https://www.dfki.de/fileadmin/user_upload/import/13411_ELE_Report_on_Europe%27s_Sign_Languages.pdf" +url_code: "" +url_dataset: +url_poster: +url_project: +url_slides: +url_source: +url_video: + +# Featured image +# To use, add an image named `featured.jpg/png` to your page's folder. +# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight. +image: + caption: "" + focal_point: "" + preview_only: false + +# Associated Projects (optional). +# Associate this publication with one or more of your projects. +# Simply enter your project's folder or file name without extension. +# E.g. `internal-project` references `content/project/internal-project/index.md`. +# Otherwise, set `projects: []`. +projects: [] + +# Slides (optional). +# Associate this publication with Markdown slides. +# Simply enter your slide deck's filename without extension. +# E.g. `slides: "example"` references `content/slides/example/index.md`. +# Otherwise, set `slides: ""`. +slides: "" +---