Towards Generating Text from Discourse Representation Structures

What it is about

The paper argues that Discourse Representation Structures are a good language-neutral input for generation, since they hold the content that a macro planner would produce (rhetorical structure, presupposition, named entities, thematic roles and word senses). It describes SemBank, a corpus of English newswire text annotated with CCG syntax, DRT semantics and SDRT discourse relations, built semi-automatically with a parser and corrected by experts and a game with non-experts. The paper then lists three problems that a DRS-based generator must solve: referring expressions (a free variable can be a pronoun, a name or a description), lexicalisation (one WordNet synset can have several words, such as loon or diver, chosen by region and local context), and aggregation (coordinated noun phrases can be generated as one sentence or two, and a DRS must recognise the choice). The paper gives no generation results.

Ideas

• I1. Lexicalisation by local context: when a concept has several word forms, choose the one most frequent in its local context, keyed also by author or region. This is the encoder's context table; a regional or author key would carry the style deltas of open problem 8.
• I2. Coordination: keep "A and B did X" as one structure, and let the encoder choose conjoined or split output by counts from the Bible pairs. Measure both on dev.
• I3. Keep presupposition and definiteness as features on noun meta tokens (open problem 4). The paper argues that the DRT layer carries this information for generation.
• I4. Referring expressions: whether a pronoun or a name is used depends on the antecedent entity. Count pronoun choice against the antecedent across the aligned pairs, and report how often the choice is recoverable.

For Mova

The ideas fit tools/translate/profile.rs (context table and keys) and tools/translate/meta.rs (features on meta tokens). The paper has no measurements, so every idea above starts from a count on the Bible pairs that can be checked against the residual.

Topics: Discourse analysis · Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{basile2011generating,
  title = {{Towards Generating Text from Discourse Representation Structures}},
  author = {Basile, Valerio and Bos, Johan},
  booktitle = {Proceedings of the 13th European Workshop on Natural Language Generation},
  year = {2011},
  url = {https://aclanthology.org/W11-2819/}
}

References

25 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Guillaume Artignan, Mountaz Hascoët, and Mathieu Lafourcade. 2009. Multiscale visual analysis of lexical networks. Information Visualisation, International Conference on, 0:685–690. find
2. N. Asher and A. Lascarides. 2003. Logics of conversation. Studies in natural language processing. Cambridge University Press. find
3. Nicholas Asher. 1993. Reference to Abstract Objects in Discourse. Kluwer Academic Publishers. find
4. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics. Proceedings of the Conference, pages 86–90, Université de Montréal, Montreal, Quebec, Canada. find our card
5. John Bateman and Michael Zock. 2003. Natural Language Generation. In R. Mitkov, editor, Oxford Handbook of Computational Linguistics, chapter 15, pages 284–304. Oxford University Press, Oxford. find
6. Bernd Bohnet, Leo Wanner, Simon Mille, and Alicia Burga. 2010. Broad coverage multilingual deep sentence generation with a stochastic multi-level realizer. In Proceedings of the 23rd International Conference on Computational Linguistics, pages 98–106. find our card
7. Johan Bos. 2008. Wide-Coverage Semantic Analysis with Boxer. In J. Bos and R. Delmonte, editors, Semantics in Text Processing. STEP 2008 Conference Proceedings, volume 1 of Research in Computational Semantics, pages 277–286. College Publications. find
8. John Chamberlain, Massimo Poesio, and Udo Kruschwitz. 2008. Addressing the Resource Bottleneck to Create Large-Scale Annotated Texts. In Johan Bos and Rodolfo Delmonte, editors, Semantics in Text Processing. STEP 2008 Conference Proceedings, volume 1 of Research in Computational Semantics, pages 375–380. College Publications. find
9. Stephen Clark and James R. Curran. 2004. Parsing the WSJ using CCG and Log-Linear Models. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL ’04), pages 104–111, Barcelona, Spain. find
10. Michael Elhadad and Jacques Robin. 1996. An overview of SURGE: a reusable comprehensive syntactic realization component. Technical report. find our card
11. Christiane Fellbaum, editor. 1998. WordNet. An Electronic Lexical Database. The MIT Press. find
12. Claire Gardent, Hélène Manuélian, Kristina Striegnitz, and Marilisa Amoia. 2004. Generating definite descriptions: Non-incrementality, inference and data. In Thomas Pechmann and Christopher Habel, editors, Multidisciplinary approaches to language production, pages 53–85. Walter de Gruyter, Berlin. find
13. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: the 90% solution. In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, pages 57–60, Stroudsburg, PA, USA. find
14. Nancy Ide, Christiane Fellbaum, Collin Baker, and Rebecca Passonneau. 2010. The manually annotated sub-corpus: a community resource for and by the people. In Proceedings of the ACL 2010 Conference Short Papers, pages 68–73, Stroudsburg, PA, USA. find
15. Hans Kamp and Uwe Reyle. 1993. From Discourse to Logic; An Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and DRT. Kluwer, Dordrecht. find
16. Hans Kamp. 1984. A Theory of Truth and Semantic Representation. In Jeroen Groenendijk, Theo M.V. Janssen, and Martin Stokhof, editors, Truth, Interpretation and Information, pages 1–41. FORIS, Dordrecht – Holland/Cinnaminson – U.S.A. find
17. Karin Kipper, Anna Korhonen, Neville Ryant, and Martha Palmer. 2008. A large-scale classification of English verbs. Language Resources and Evaluation, 42(1):21–40. find
18. Reinhard Muskens. 1996. Combining Montague Semantics and Discourse Representation. Linguistics and Philosophy, 19:143–186. find
19. Martha Palmer, Paul Kingsbury, and Daniel Gildea. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71– 106. find our card
20. Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, and Bonnie Webber. 2005. The Penn Discourse TreeBank as a resource for natural language generation. In Proc. of the Corpus Linguistics Workshop on Using Corpora for Natural Language Generation, pages 25–32. find our card
21. Mark Steedman. 2001. The Syntactic Process. The MIT Press. find
22. Kees van Deemter. 2006. Generating referring expressions that involve gradable properties. Computational Linguistics, 32(2):195–222. find
23. Rob A. Van der Sandt. 1992. Presupposition Projection as Anaphora Resolution. Journal of Semantics, 9:333– 377. find
24. Michael White, Rajakrishnan Rajkumar, and Scott Martin. 2007. Towards broad coverage surface realization with CCG. In Proceedings of the Workshop on Using Corpora for NLG: Language Generation and Machine Translation (UCNLG+MT). find our card
25. Michael White. 2006. Efficient realization of coordinate structures in combinatory categorial grammar. Research on Language & Computation, 4:39–75. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/basile-2011-generating-text-discourse-representation-structures/