Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks (2310.02053v1)

Published 3 Oct 2023 in cs.CL

Abstract: A bare meaning representation can be expressed in various ways using natural language, depending on how the information is structured on the surface level. We are interested in finding ways to control topic-focus articulation when generating text from meaning. We focus on distinguishing active and passive voice for sentences with transitive verbs. The idea is to add pragmatic information such as topic to the meaning representation, thereby forcing either active or passive voice when given to a natural language generation system. We use graph neural models because there is no explicit information about word order in a meaning represented by a graph. We try three different methods for topic-focus articulation (TFA) employing graph neural models for a meaning-to-text generation task. We propose a novel encoding strategy about node aggregation in graph neural models, which instead of traditional encoding by aggregating adjacent node information, learns node representations by using depth-first search. The results show our approach can get competitive performance with state-of-art graph models on general text generation, and lead to significant improvements on the task of active-passive conversion compared to traditional adjacency-based aggregation strategies. Different types of TFA can have a huge impact on the performance of the graph models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. The Parallel Meaning Bank: Towards a multilingual corpus of translations annotated with compositional meaning representations. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 242–247, Valencia, Spain. Association for Computational Linguistics.
  2. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  3. Valerio Basile. 2015. From logic to language: Natural language generation from logical forms. Ph.D. thesis, University of Groningen.
  4. Graph-to-sequence learning using gated graph neural networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 273–283, Melbourne, Australia. Association for Computational Linguistics.
  5. Johan Bos. 2021. Variable-free discourse representation structures. Semantics Archive.
  6. Deng Cai and Wai Lam. 2020. Graph transformer for graph-to-sequence learning. In Proceedings of The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI).
  7. Marco Damonte and Shay B Cohen. 2019. Structural neural encoders for amr-to-text generation. In Proceedings of NAACL.
  8. Information structure in cross-linguistic corpora : annotation guidelines for phonology, morphology, syntax, semantics and information structure.
  9. Christiane Fellbaum. 1998. Wordnet: An electronic lexical database. The MIT Press, Cambridge, Ma., USA.
  10. Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1631–1640, Berlin, Germany. Association for Computational Linguistics.
  11. Pointing the unknown words. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 140–149, Berlin, Germany. Association for Computational Linguistics.
  12. Jeanette K Gundel and Thorstein Fretheim. 2004. Topic and focus. The handbook of pragmatics, 175(196):12.
  13. Densely connected graph convolutional networks for graph-to-sequence learning. Transactions of the Association for Computational Linguistics, 7:297–312.
  14. An introduction to functional grammar. Routledge.
  15. From discourse to logic: Introduction to model theoretic semantics of natural language, formal logic and discourse representation theory. Language, 71(4).
  16. Thomas Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR.
  17. A large-scale classification of english verbs. Language Resources and Evaluation, 42:21–40.
  18. OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations, pages 67–72, Vancouver, Canada. Association for Computational Linguistics.
  19. Neural AMR: Sequence-to-sequence models for parsing and generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 146–157, Vancouver, Canada. Association for Computational Linguistics.
  20. Knud Lambrecht. 1994. Information Structure and Sentence Form: Topic, Focus, and the Mental Representations of Discourse Referents. Cambridge University Press.
  21. Alon Lavie and Abhaya Agarwal. 2007. Meteor: An automatic metric for mt evaluation with high levels of correlation with human judgments. In Proceedings of the Second Workshop on Statistical Machine Translation, StatMT ’07, page 228–231, USA. Association for Computational Linguistics.
  22. C. N. Li and S. A. Thompson. 1984. Subject and topic: A new typology of language. Contemporary Linguistics.
  23. Deeper insights into graph convolutional networks for semi-supervised learning. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI Press.
  24. Gated graph sequence neural networks.
  25. Text generation from discourse representation structures. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 397–415. Association for Computational Linguistics. 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021 ; Conference date: 06-06-2021 Through 11-06-2021.
  26. Diego Marcheggiani and Ivan Titov. 2017. Encoding sentences with graph convolutional networks for semantic role labeling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1506–1515, Copenhagen, Denmark. Association for Computational Linguistics.
  27. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meetings of the ACL, pages 311–318.
  28. Enhancing AMR-to-text generation with dual graph representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3183–3194, Hong Kong, China. Association for Computational Linguistics.
  29. Modeling global and local node contexts for text generation from knowledge graphs. Transactions of the Association for Computational Linguistics, 8:589–604.
  30. Structural information preserving for graph-to-text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7987–7998, Online. Association for Computational Linguistics.
  31. Enric Vallduví and Elisabet Engdahl. 1996. The linguistic realization of information packaging. 34(3):459–520.
  32. Graph Attention Networks. International Conference on Learning Representations. Accepted as poster.
  33. Evaluating text generation from discourse representation structures. In Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), pages 73–83, Online. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Chunliu Wang (6 papers)
  2. Rik van Noord (17 papers)
  3. Johan Bos (27 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now