Mova0.5 pre-release⌕
☰
home / docs / papers / Machine translation / GenDR: A Generic Deep Realizer with Complex Lexicalization

GenDR: A Generic Deep Realizer with Complex Lexicalization

What it is about

GenDR is a generic deep realiser. Its input is a meaning description with lexical functions, a formalism for the typical word combinations of a language, and it builds the syntactic tree from that description. A salience-driven arborisation step decides which element becomes the head of the output tree, which gives the system a lot of syntactic flexibility. Its main strength, according to the authors, is the handling of collocations: lexical function entries say which word goes with which, and the system uses them in its grammar rules. The team reports about 37,000 described lexical functions, of which about 26,000 are implemented in grammar rules. The authors plan to link the system to verb frame resources and to map its output to UD structures.

Ideas

For Mova

The paper fits the lexicon of tools/translate (meta.rs, profile.rs) and the head choice of tools/roundtrip. The lexical-function formalism is not for Mova, but the collocation entries and the coverage report carry over. Note the licence: the paper is NC, so this card is a summary only and no text is taken into the build.

Topics: Machine translation

Cite

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

@inproceedings{lareau2018gendr,
  title = {{GenDR: A Generic Deep Realizer with Complex Lexicalization}},
  author = {Lareau, François and Lambrey, Florie and Dubinskaite, Ieva and Galarreta-Piquette, Daniel and Nejat, Maryam},
  booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year = {2018},
  url = {https://aclanthology.org/L18-1478/}
}

References

61 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Apresjan, J. D., Boguslavsky, I. M., Iomdin, L. L., and Tsinman, L. L. (2002). Lexical functions in actual NLP applications. In Computational Linguistics for the New Millennium: Divergence or Synergy? Festschrift in Honour of Peter Hellwig on the occasion of his 60th Birthday, pages 55–72. Peter Lang, Frankfurt. find
  2. Apresjan, J. (2000). Systematic lexicography. Oxford University Press, Oxford. find
  3. Basile, V. (2015). From Logic to Language: Natural Language Generation from Logical Forms. Ph.D. thesis, University of Groningen. find
  4. Bateman, J. A. (1996). KPML Development Environment. GMD/Institut für Integrierte Publikations- und Informationssysteme, Darmstadt. find
  5. Bohnet, B. and Wanner, L. (2010). Open source graph transducer interpreter and grammar development environment. In Proceedings of LREC’10, pages 211–218, Malta. find
  6. Bohnet, B., Langjahr, A., and Wanner, L. (2000). A development environment for an MTT-based sentence generator. In Proceedings of INLG’00, volume 14, pages 260–263, Mitzpe Ramon. find
  7. Bouayad-Agha, N., Casamayor, G., Wanner, L., Dı́ez, F., and López Hernández, S. (2011). FootbOWL: Using a generic ontology of football competition for planning match summaries. In Proceedings of ESWC’11, Heraklion. find
  8. Bouayad-Agha, N., Casamayor, G., Mille, S., and Wanner, L. (2012). Perspective-oriented generation of football match summaries: Old tasks, new challenges. ACM Transactions on Speech and Language Processing, 9(2):art. 3, 1–31. find
  9. Miriam Butt et al., editors. (2012). Proceedings of LFG’12, Denpasar, Indonesia. CSLI. find
  10. CoGenTex, (1998). RealPro: General English Grammar. User manual. find
  11. Daoust, N. and Lapalme, G. (2015). JSREAL: A text realizer for web programming. In Núria Gala, et al., editors, Language Production, Cognition, and the Lexicon, pages 361–376. Springer, Zürich. find
  12. Dras, M., Lareau, F., Börschinger, B., Dale, R., Motazedi, Y., Rambow, O., Turpin, M., and Ulinski, M. (2012). Complex predicates in Arrernte. In Butt and King (Butt and King, 2012), pages 177–197. find
  13. Dubinskaite, I. (2017). Développement de ressources litu-aniennes pour un générateur automatique de texte multilingue. Master’s thesis, Université Grenoble Alpes. find
  14. Elhadad, M. and Robin, J. (1996). An overview of SURGE: A reusable comprehensive syntactic realization component. In Proceedings of INLG’96, number 96-03, pages 1–4, Brighton. find our card
  15. Elhadad, M. (1993). FUF: the universal unifier. User manual version 5.2. Technical report, Computer Science, Ben Gurion University of the Negev, Beer Sheva, Israel. find
  16. Fonseca, A., Sadat, F., and Lareau, F. (2016a). Lexfom: a lexical functions ontology model. In Proceedings of CogALex’16 at COLING, Osaka. find
  17. Fonseca, A., Sadat, F., and Lareau, F. (2016b). A lexical ontology to represent lexical functions. In Proceedings of LangOnto’16 at LREC, Portorož. find
  18. Fonseca, A. (2018). Représentation des collocations dans un réseau lexical à l’aide des fonctions lexicales et des formalismes du web sémantique. Ph.D. thesis, Université du Québec à Montréal. find
  19. Gardent, C., Shimorina, A., Narayan, S., and Perez-Beltrachini, L. (2017). The WebNLG challenge: Generating text from RDF data. In Proceedings of INLG’17, pages 124–133, Santiago de Compostela. find our card
  20. Gatt, A. and Reiter, E. (2009). SimpleNLG: A realisation engine for practical applications. In Proceedings of ENLG’09, pages 90–93, Athens. find
  21. Jousse, A.-L. (2010). Modèle de structuration des relations lexicales basé sur le formalisme des fonctions lexicales. Ph.D. thesis, Université de Montréal/Université Paris 7. find
  22. Kahane, S. and Polguère, A. (2001). Formal foundation of lexical functions. In Proceedings of ACL 2001, Toulouse. find
  23. Kahane, S. (2003). The Meaning-Text Theory. In Vilmos Ágel, et al., editors, Dependenz und Valenz: Ein internationales Handbuch der zeitgenössischen Forshung/ Dependency and Valency: An International Handbook of Contemporary Research, volume 1, pages 546–570. Walter de Gruyter, Berlin/New York. find
  24. Kipper Schuler, K. (2006). VerbNet: A Broad-Coverage, Comprehensive Verb Lexicon. Ph.D. thesis, University of Pennsylvania, Philadelphia. find
  25. Lambrey, F. and Lareau, F. (2015). Le traitement des collocations en génération de texte multilingue. In Actes de TALN’15, pages 579–585, Caen. find
  26. Lambrey, F. (2016). Implémentation des collocations pour la réalisation de texte multilingue. Master’s thesis, Université de Montréal. find
  27. Lareau, F. and Wanner, L. (2007). Towards a generic multilingual dependency grammar for text generation. In Tracy Holloway King et al., editors, Proceedings of the GEAF07 Workshop, pages 203–223, Stanford. CSLI. find
  28. Lareau, F., Dras, M., Börschinger, B., and Dale, R. (2011). Collocations in multilingual natural language generation: Lexical functions meet lexical functional grammar. In Diego Mollá et al., editors, Proceedings of ALTA’11, pages 95–104, Canberra. find
  29. Lareau, F., Dras, M., Börschinger, B., and Turpin, M. (2012). Implementing lexical functions in XLE. In Butt and King (Butt and King, 2012), pages 362–382. find
  30. Lavoie, B. and Rambow, O. (1997). A fast and portable realizer for text generation systems. In Proceedings of ANLP 1997, pages 265–268, Washington. find our card
  31. Mel’čuk, I. A. (1973). Towards a linguistic ”Meaning-Text” model. In Ferenc Kiefer, editor, Trends in Soviet Theoretical Linguistics, pages 33–57. Reidel, Dordrecht. find
  32. Mel’čuk, I. A. (1988). Dependency syntax: theory and practice. SUNY series in linguistics. State University of New York Press, Albany. find
  33. Mel’čuk, I. (1995). The future of the lexicon in linguistic description and the explanatory combinatorial dictionary. In I.-H. Lee, editor, Linguistics in the morning calm, volume 3. Hanshin, Seoul. find
  34. Mel’čuk, I. A. (1996). Lexical functions: A tool for the description of lexical relations in a lexicon. In Wanner (Wanner, 1996), pages 37–102. find
  35. Mel’čuk, I. (1998). Collocations and lexical functions. In A. P. Cowie, editor, Phraseology. Theory, analysis, and applications, pages 23–53. Clarendon, Oxford. find
  36. Mel’čuk, I. A. (2001). Communicative organization in natural language: the semantic-communicative structure of sentences. Studies in language companion series. John Benjamins, Amsterdam/Philadelphia. find
  37. Mel’čuk, I. A., (2007). Phraseology: An international handbook of contemporary research, volume 1, chapter 11: Lexical functions. Walter de Gruyter, Berlin/New York. find
  38. Mel’čuk, I. A. (2012). Semantics: From Meaning to Text, volume 1. John Benjamins, Amsterdam/Philadelphia. find
  39. Mel’čuk, I. A. (2013). Semantics: From Meaning to Text, volume 2. John Benjamins, Amsterdam/Philadelphia. find
  40. Mel’čuk, I. A. (2014). Semantics: From Meaning to Text, volume 3. John Benjamins, Amsterdam/Philadelphia. find
  41. Milićević, J. (2006). A short guide to the Meaning-Text theory. Journal of Koralex, 8:187–233. find
  42. Mille, S. and Wanner, L. (2017). A demo of FORGe: the Pompeu Fabra open rule-based generator. In Proceedings of INLG’17, pages 245–246, Santiago de Compostela. find
  43. Mille, S., Carlini, R., Burga, A., and Wanner, L. (2017). FORGe at SemEval-2017 task 9: Deep sentence generation based on a sequence of graph transducers. In Proceedings of SemEval’17, pages 920–923, Vancouver. find
  44. Mille, S. (2014). Deep stochastic sentence generation: Resources and strategies. Ph.D. thesis, Universitat Pompeu Fabra, Barcelona. find
  45. Molins, P. and Lapalme, G. (2015). JSrealB: A bilingual text realizer for web programming. In Proceedings of ENGL’15, pages 109–111, Brighton. find
  46. Nivre, J., de Marneffe, M.-C., Ginter, F., Goldberg, Y., Hajič, J., Manning, C. D., McDonald, R., Petrov, S., Pyysalo, S., Silveira, N., Tsarfaty, R., and Zeman, D. (2016). Universal Dependencies v1: A multilingual treebank collection. In Proceedings of LREC’16, pages 1659–1666, Portorož. find our card
  47. Polguère, A. (2000). A “natural” lexicalization model for language generation. In Proceedings of SNLP 2000, pages 37–50, Chiangmai. find
  48. Polguère, A. (2007). Lexical function standardness. In Leo Wanner, editor, Selected lexical and grammatical issues in the Meaning-Text theory: in honour of Igor Mel’čuk, volume 84 of Language Companion Series. John Benjamins, Amsterdam/Philadelphia. find
  49. Pradet, Q., Danlos, L., and de Chalendar, G. (2014). Adapting VerbNet to French using existing resources. In Proceedings of LREC’14, Reykjavik. find
  50. Ramos-Soto, A., Janeiro-Gallardo, J., and Bugarı́n, A. (2017). Adapting SimpleNLG to Spanish. In Proceedings of INLG’17, pages 144–148, Santiago de Compostela. find
  51. Vaudry, P.-L. and Lapalme, G. (2013). Adapting SimpleNLG for bilingual English-French realisation. In Proceedings of ENLG’13, pages 183–187, Sofia. find
  52. Wanner, L. and Bateman, J. A. (1990). A Collocational Based Approach to Salience-Sensitive Lexical Selection. In Proceedings of INLG’90, Dawson, PA. find
  53. Wanner, L. and Lareau, F. (2009). Applying the Meaning-Text Theory model to text synthesis with low- and middle-density languages in mind. In Sergei Nirenburg, editor, Language Engineering for Lesser-Studied Languages, volume 21 of NATO Science for Peace and Security Series - D: Information and Communication Security. IOS Press, Amsterdam. find
  54. Wanner, L., Brügmann, S., Diallo, B., Giereth, M., Kompatsiaris, Y., Pianta, E., Rao, G., Schoester, P., and Zervaki, V. (2009). PATExpert: Semantic processing of patent documentation. find
  55. Wanner, L., Bohnet, B., Bouayad-Agha, N., Lareau, F., and Nicklaß, D. (2010). MARQUIS: Generation of user-tailored multilingual air quality bulletins. Applied Artificial Intelligence, 24(10):914–952. find
  56. Wanner, L., Bott, S., Bouayad-Agha, N., Casamayor, G., Ferraro, G., Graën, J., Joan Casademont, A., Lareau, F., Mille, S., and Vidal, V. (2011). Paraphrasing and multilingual summarization of patent claims. In Leo Wanner, et al., editors, PATExpert: A Next Generation Patent Processing Service. Technical documentation. find
  57. Wanner, L. (1992). Lexical Choice and the Organization of Lexical Resources in Text Generation. In Proceedings of the European Conference on Artificial Intelligence, Vienna, Austria. find
  58. Leo Wanner, editor. (1996). Lexical functions in lexicography and natural language processing. John Benjamins, Amsterdam/Philadelphia. find
  59. Weißgraeber, R. and Madsack, A. (2017). A working, non-trivial, topically indifferent NLG system for 17 languages. In Proceedings of INLG’17, pages 156–157, Santiago de Compostela. find
  60. White, M., (2008). OpenCCG Realizer Manual. find
  61. Žolkovskij, A. and Mel’čuk, I. (1967). O semantičeskom sinteze. Problemy kibernetiki, 19:177–238. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lareau-2018-gendr-generic-deep-realizer-complex/