Data-to-Text Papers

Some papers related to structured data summarization or description generation.

Thesis:

1. Joint Models for Concept-to-text Generation, Ioannis Konstas University of Edinburgh, 2014

Wikipedia Infobox/table/wikidata summarization

1. Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization http://aclweb.org/anthology/N18-1139

2. Table-to-text Generation by Structure-aware Seq2seq Learning https://tyliupku.github.io/papers/aaai2018_liu.pdf

3. Neural Text Generation from Structured Data with Application to the Biography Domain http://arxiv.org/abs/1603.07771

4. Table-to-Text: Describing Table Region with Natural Language https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16138

5. Learning to generate one-sentence biographies from Wikidata Chisholm, Andrew and Radford, Will and Hachey, Ben EACL, 2017

Data-To-Text

1. Unsupervised concept-to-text generation with hypergraphs Ioannis Konstas, Mirella Lapata , Journal Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Montréal, Canada

2. A Global Model for Concept-to-Text Generation I Konstas, M Lapata https://www.jair.org/index.php/jair/article/view/10841

3. Concept-to-text generation via discriminative reranking I Konstas, M Lapata ; ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics

4. Collective Content Selection for Concept-To-Text Generation Regina Barzilay Mirella Lapata ,Proceeding HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing Pages 331-338

5. Summarizing source code using a neural attention model Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Luke Zettlemoyer Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics

6. Neural amr: Sequence-to-sequence models for parsing and generation Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi, Luke Zettlemoyer , ACL 2017

7. A simple domain-independent probabilistic approach to generation. Angeli, G., Liang, P., and Klein, D. (2010). In Proceedings of the 2010 Conference on EmpiricalMethods in Natural Language Processing, pages 502–512, Cambridge, MA.

8. A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization Proceedings of NAACL-HLT 2018, pages 622–627 http://aclweb.org/anthology/N18-2098

9. Automatic Generation of Weather Forecast Texts Using Comprehensive Probabilistic Generation-space Models Nat. Lang. Eng. 2008

10. System Building Cost vs. Output Quality in Data-to-text Generation EN