Mova0.5 pre-release⌕
☰
home / docs / papers / Machine translation / The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages

The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages

What it is about

The paper describes the framework behind the PMB. English text gets seven annotation layers (segmentation, symbolisation, semantic tagging, word sense disambiguation, syntax, thematic roles and coreference), and the result is projected to translations. Projection breaks where word order, multiword expressions, definiteness, articles and compounds differ between languages. The authors therefore retrain the tagging and parsing models for each non-English language, starting from the translations whose projection is already correct, then reprocess the rest with the new models and correct the output by hand. A fine-grained matching of meaning representations checks whether a projected annotation gives the same meaning as the English. The paper also explains how new documents and new languages are added, and where its assumptions fail: CCG as a common syntax and English-based categories do not suit every language.

Ideas

For Mova

The code is tools/hbo, tools/macula and tools/translate/hebrew.rs. I1 is a concrete plan for open problem 7 (better Hebrew alignment), and I2 with I3 address open problem 2, since a merge should be kept only when the readings still match.

Topics: Word sense disambiguation · Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. arXiv 2012.14854

@misc{abzianidze2020parallel,
  title = {{The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages}},
  author = {Abzianidze, Lasha and Noord, Rik van and Wang, Chunliu and Bos, Johan},
  year = {2020},
  eprint = {2012.14854},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2012.14854}
}

References

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

  1. 1. Abdou, M., Kulmizev, A., Ravishankar, V., Abzianidze, L., Bos, J.: What can we learn from semantic tagging? In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. pp. 4881–4889 (2018) 2. Abzianidze, L., Bjerva, J., Evang, K., Haagsma, H., van Noord, R., Ludmann, P., Nguyen, D.D., Bos, J.: 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. pp. 242–247. Association for Computational Linguistics, Valencia, Spain (April 2017), http://www.aclweb.org/anthology/E17-2039 3. Abzianidze, L., Bos, J.: Towards universal semantic tagging. In: Proceedings of the 12th International Conference on Computational Semantics (IWCS 2017) – Short Papers. Association for Computational Linguistics, Montpellier, France (September 2017), http://aclweb.org/anthology/W17-6901 4. Abzianidze, L., van Noord, R., Haagsma, H., Bos, J.: The first shared task on discourse representation structure parsing. In: Proceedings of the IWCS Shared Task on Semantic Parsing. Association for Computational Linguistics, Gothenburg, Sweden (May 2019), https://www.aclweb.org/anthology/W19-1201 5. Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K., Hermjakob, U., Knight, K., Koehn, P., Palmer, M., Schneider, N.: Abstract Meaning Representation for sembanking. In: Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse. pp. 178–186. ↗ our card
  2. Sofia, Bulgaria (2013), http://www.aclweb.org/anthology/W13-2322 6. Basile, V., Bos, J., Evang, K., Venhuizen, N.: Developing a large semantically annotated corpus. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC 2012). pp. 3196–3200. ↗ our card
  3. Istanbul, Turkey (2012) 7. Basile, V., Bos, J., Evang, K., Venhuizen, N.: A platform for collaborative semantic annotation. In: Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2012). pp. 92–96. find
  4. Avignon, France (2012) 8. Belinkov, Y., Màrquez, L., Sajjad, H., Durrani, N., Dalvi, F., Glass, J.: Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). pp. 1–10 (2017) 9. Bjerva, J.: Will my auxiliary tagging task help? estimating auxiliary tasks effectivity in multi-task learning. In: Proceedings of the 21st Nordic Conference on Computational Linguistics. pp. 216–220 (2017) 10. Bjerva, J., Plank, B., Bos, J.: Semantic tagging with deep residual networks. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. pp. 3531–3541. find
  5. Osaka, Japan (2016) 11. Bonial, C., Corvey, W.J., Palmer, M., Petukhova, V., Bunt, H.: A hierarchical unification of LIRICS and VerbNet semantic roles. In: Proceedings of the 5th IEEE International Conference on Semantic Computing (ICSC 2011). pp. 483–489 (2011) 12. Bos, J.: Wide-Coverage Semantic Analysis with Boxer. In: Bos, J., Delmonte, R. (eds.) Semantics in Text Processing. STEP 2008 Conference Proceedings, Research in Computational Semantics, vol. 1, pp. 277–286. find
  6. College Publications (2008), http://www.aclweb.org/anthology/W08-2222 13. Bos, J.: Open-domain semantic parsing with Boxer. In: Megyesi, B. (ed.) Proceedings of the 20th Nordic Conference of Computational Linguistics (NODALIDA 2015). pp. 301–304 (2015) 14. Bos, J., Basile, V., Evang, K., Venhuizen, N., Bjerva, J.: The Groningen Meaning Bank. In: Ide, N., Pustejovsky, J. (eds.) Handbook of Linguistic Annotation. ↗
  7. Springer Netherlands (2017), http://www.springer.com/la/book/9789402408799 15. Brants, T.: Tnt: A statistical part-of-speech tagger. In: Proceedings of the Sixth Conference on Applied Natural Language Processing. pp. 224–231. ANLC ’00, Association for Computational Linguistics, Stroudsburg, PA, USA (2000) 16. Dalvi, F., Sajjad, H., Durrani, N., Belinkov, Y.: Exploiting redundancy in pre-trained language models for efficient transfer learning. arXiv preprint arXiv:2004.04010 (2020) 17. Durrani, N., Dalvi, F., Sajjad, H., Belinkov, Y., Nakov, P.: One size does not fit all: Comparing NMT representations of different granularities. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 1504–1516. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019), https://www.aclweb.org/anthology/N19-1154 18. Ek, A., Bernardy, J.P., Lappin, S.: Language modeling with syntactic and semantic representation for sentence acceptability predictions. In: NEAL Proceedings of the 22nd Nordic Conference on Computional Linguistics (NoDaLiDa), September 30-October 2, Turku, Finland. pp. 76–85. No. 167, Linköping University Electronic Press (2019) 19. Evang, K.: Cross-lingual Semantic Parsing with Categorial Grammars. Ph.D. thesis, University of Groningen (2016) 20. Evang, K.: Transition-based DRS parsing using stack-LSTMs. In: Proceedings of the IWCS 2019 Shared Task on Semantic Parsing (2019) 21. Evang, K., Basile, V., Chrupa la, G., Bos, J.: Elephant: Sequence labeling for word and sentence segmentation. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 1422–1426. ↗ our card
  8. Seattle, Washington, USA (2013), http://www.aclweb.org/anthology/D13-1146 22. Fancellu, F., Gilroy, S., Lopez, A., Lapata, M.: Semantic graph parsing with recurrent neural network DAG grammars. 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). pp. 2769– 2778. Association for Computational Linguistics, Hong Kong, China (Nov 2019), https://www.aclweb.org/anthology/D19-1278 23. Fellbaum, C. (ed.): WordNet. An Electronic Lexical Database. ↗
  9. The MIT Press, Cambridge, Ma., USA (1998) 24. Johnson, M., Klein, E.: Discourse, anaphora and parsing. In: 11th International Conference on Computational Linguistics. Proceedings of Coling ’86. pp. 669–675. find
  10. Bonn, Germany (1986) 25. Kamp, H., Reyle, U.: From Discourse to Logic; An Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and DRT. find
  11. Kluwer, Dordrecht (1993) 26. Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning. p. 282–289. ICML ’01, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001) 27. Le, P., Zuidema, W.: Learning compositional semantics for open domain semantic parsing. In: Proceedings of COLING 2012. pp. 1535–1552. find
  12. The COLING 2012 Organizing Committee, Mumbai, India (2012) 28. Lewis, M., Steedman, M.: A* CCG parsing with a supertag-factored model. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 990–1000. find our card
  13. Doha, Qatar (2014), http://www.aclweb.org/anthology/D14-1107 29. Liu, J., Cohen, S., Lapata, M.: Discourse representation structure parsing with recurrent neural networks and the transformer model. In: Proceedings of the IWCS 2019 Shared Task on Semantic Parsing (2019) 30. Liu, J., Cohen, S.B., Lapata, M.: Discourse representation structure parsing. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). vol. 1, pp. 429–439. ↗ our card
  14. Melbourne, Australia (2018) 31. Liu, J., Cohen, S.B., Lapata, M.: Discourse representation parsing for sentences and documents. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 6248–6262. Association for Computational Linguistics, Florence, Italy (Jul 2019), https://www.aclweb.org/anthology/P19-1629 32. Liu, N.F., Gardner, M., Belinkov, Y., Peters, M.E., Smith, N.A.: Linguistic knowledge and transferability of contextual representations. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 1073–1094. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019), https://www.aclweb.org/anthology/N19-1112 33. Minnen, G., Carroll, J., Pearce, D.: Applied morphological processing of English. Natural Language Engineering 7(3), 207–223 (2001) 34. van Noord, R.: Neural Boxer at the IWCS shared task on DRS parsing. In: Proceedings of the IWCS 2019 Shared Task on Semantic Parsing (2019) 35. van Noord, R., Abzianidze, L., Haagsma, H., Bos, J.: Evaluating scoped meaning representations. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). ↗
  15. Miyazaki, Japan (2018) 36. van Noord, R., Abzianidze, L., Toral, A., Bos, J.: Exploring neural methods for parsing discourse representation structures. Transactions of the Association for Computational Linguistics 6, 619–633 (2018), https://www.aclweb.org/ anthology/Q18-1043 37. van Noord, R., Toral, A., Bos, J.: Linguistic information in neural semantic parsing with multiple encoders. In: IWCS 2019-13th International Conference on Computational Semantics-Short papers (2019) 38. Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29(1), 19–51 (2003) 39. Pkhakadze, K., Chikvinidze, M., Chichua, G., Maskharashvili, A., Beriashvili, I.: An overview of the trial version of the georgian self-developing intellectual corpus necessary for creating georgian text analyzer, speech processing, and automatic translation systems. In: Reports of Enlarged Session of the Seminar of I. Vekua Institute of Applied Mathematics. vol. 28. I. Vekua Institute of Applied Mathematics (2014) 40. Steedman, M.: The Syntactic Process. ↗
  16. The MIT Press, Cambridge, Ma., USA (2001) 41. Straka, M., Hajič, J., Straková, J.: UDPipe: Trainable pipeline for processing CoNLL-u files performing tokenization, morphological analysis, POS tagging and parsing. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16). pp. 4290–4297. European Language Resources Association (ELRA), Portorož, Slovenia (May 2016), https://www.aclweb.org/ anthology/L16-1680 42. Tse, D., Curran, J.R.: Chinese CCGbank: extracting CCG derivations from the Penn Chinese treebank. In: Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010). pp. 1083–1091. Coling 2010 Organizing Committee, Beijing, China (Aug 2010), https://www.aclweb.org/anthology/ C10-1122 43. Wada, H., Asher, N.: BUILDRS: An implementation of DR theory and LFG. In: 11th International Conference on Computational Linguistics. Proceedings of Coling ’86. pp. 540–545. ↗ our card
  17. Bonn, Germany (1986) 44. Xue, N., Zhang, X., Jiang, Z., Palmer, M., Xia, F., Chiou, F.D., Chang, M.: Chinese treebank 9.0 ldc2016t13 (2016), https://catalog.ldc.upenn.edu/LDC2016T13 45. Yanaka, H., Mineshima, K., Bekki, D., Inui, K., Sekine, S., Abzianidze, L., Bos, J.: Can neural networks understand monotonicity reasoning? In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. pp. 31–40 (2019) 46. Yanaka, H., Mineshima, K., Yamada, A., Yamaguchi, Y., Kubota, Y., Abzianidze, L., Bos, J.: Building a japanese version of parallel meaning bank. In: 26th Annual Meeting of the Association for Natural Language Processing. pp. 1145–1158 (2020) 47. Yoshikawa, M., Noji, H., Matsumoto, Y.: A* CCG parsing with a supertag and dependency factored model. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 277–287. Association for Computational Linguistics, Vancouver, Canada (Jul 2017), https://www.aclweb.org/anthology/P17-1026 48. Yu, K., Miyao, Y., Matsuzaki, T., Wang, X., Tsujii, J.: Analysis of the difficulties in Chinese deep parsing. In: Proceedings of the 12th International Conference on Parsing Technologies. pp. 48–57. Association for Computational Linguistics, Dublin, Ireland (Oct 2011), https://www.aclweb.org/anthology/W11-2907 ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/abzianidze-2020-parallel-meaning-bank-framework-semantically/