1932

Abstract

Recent developments in language modeling have enabled large text encoders to derive a wealth of linguistic information from raw text corpora without supervision. Their success across natural language processing (NLP) tasks has called into question the role of man-made computational resources, such as verb lexicons, in supporting modern NLP. Still, probing analyses have concurrently exposed the limitations of the knowledge possessed by the large neural architectures, revealing them to be clever task solvers rather than self-taught linguists. Can human-designed lexical resources still help fill their knowledge gaps? Focusing on verb classification, we discuss approaches to generating verb classes multilingually and weigh the relative benefits of undertaking expensive lexicographic work and outsourcing the task to untrained native speakers. Then, we consider the evidence for the utility of augmenting pretrained language models with external verb knowledge and ponder the ways in which human expertise can continue to benefit multilingual NLP.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-linguistics-030521-043632
2023-01-17
2024-06-15
Loading full text...

Full text loading...

/deliver/fulltext/linguistics/9/1/annurev-linguistics-030521-043632.html?itemId=/content/journals/10.1146/annurev-linguistics-030521-043632&mimeType=html&fmt=ahah

Literature Cited

  1. Amigó E, Gonzalo J, Artiles J, Verdejo F. 2009. A comparison of extrinsic clustering evaluation metrics based on formal constraints. Inf. Retr. 12:4461–86
    [Google Scholar]
  2. Aparicio J, Taulé M, Martí MA. 2008. AnCora-Verb: a lexical resource for the semantic annotation of corpora. Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)797–802 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  3. Baker CF, Fillmore CJ, Lowe JB. 1998. The Berkeley FrameNet project. Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL ’98), Vol. 186–90 Montreal, Can: Univ. Montreal
    [Google Scholar]
  4. Baker M, Bobaljik J 2017. On inherent and dependent theories of ergative case. The Oxford Handbook of Ergativity J Coon, D Massam, LD Travis 111–34 Oxford, UK: Oxford Univ. Press
    [Google Scholar]
  5. Bick E. 2011. A FrameNet for Danish. Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011)34–41 n.p.: North. Eur. Assoc. Lang. Technol.
    [Google Scholar]
  6. Boas HC. 2002. Bilingual FrameNet dictionaries for machine translation. Proceedings of the Third International Conference on Language Resources and Evaluation (LREC'02)1364–71 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  7. Boons JP, Guillet A, Leclère C. 1976. La structure des phrases simples en français: constructions intransitives, Vol. 1 Geneva: Droz
    [Google Scholar]
  8. Brew C, Schulte im Walde S. 2002. Spectral clustering for German verbs. Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)117–24 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  9. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD et al. 2020. Language models are few-shot learners. Adv. Neural Inf. Proc. Syst. 33:1877–901
    [Google Scholar]
  10. Candito M, Amsili P, Barque L, Benamara F, de Chalendar G et al. 2014. Developing a French FrameNet: methodology and first results. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)1372–79 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  11. Chafe WL. 1970. Meaning and the Structure of Language Chicago: Univ. Chicago Press
    [Google Scholar]
  12. Chen C, Huang H, Shiue Y, Chen H. 2018. Numeral understanding in financial tweets for fine-grained crowd-based forecasting. 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI)136–43 New York: IEEE
    [Google Scholar]
  13. Chiu B, Majewska O, Pyysalo S, Wey L, Stenius U et al. 2019. A neural classification method for supporting the creation of BioVerbNet. J. Biomed. Semant. 10:12
    [Google Scholar]
  14. Cinková S, Fučíková E, Šindlerová J, Hajič J. 2014. EngVallex-English Valency Lexicon Prague: LINDAT-CLARIAH-CZ, Charles Univ http://hdl.handle.net/11234/1-3526
    [Google Scholar]
  15. Cook WA. 1979. Case Grammar: Development of the Matrix Model (1970–1978) Washington, DC: Georgetown Univ. Press
    [Google Scholar]
  16. Devlin J, Chang MW, Lee K, Toutanova K. 2019. BERT: pre-training of deep bidirectional Transformers for language understanding. 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)4171–86 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  17. Doddington GR, Mitchell A, Przybocki MA, Ramshaw LA, Strassel SM, Weischedel RM. 2004. The Automatic Content Extraction (ACE) program: tasks, data, and evaluation. Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC'04)837–40 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  18. Dryer MS, Haspelmath M, eds. 2013. WALS Online Leipzig, Ger.: Max Planck Inst. Evol. Anthropol. https://wals.info/
    [Google Scholar]
  19. Dubois J, Dubois-Charlier F 1997. Les verbes français Paris: Larousse
    [Google Scholar]
  20. Estarrona A, Aldezabal I, de Ilarraza AD 2020. How the corpus-based Basque Verb Index lexicon was built. Lang. Resour. Eval. 54:173–95
    [Google Scholar]
  21. Estarrona A, Aldezabal I, Díaz de Ilarraza A, Aranzabe MJ 2016. A methodology for the semiautomatic annotation of EPEC-RolSem, a Basque corpus labeled at predicate level following the PropBank-VerbNet model. Digit. Sch. Humanit. 31:3470–92
    [Google Scholar]
  22. Falk I, Gardent C, Lamirel JC. 2012. Classifying French verbs using French and English lexical resources. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)854–63 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  23. Faruqui M, Dodge J, Jauhar SK, Dyer C, Hovy E, Smith NA. 2015. Retrofitting word vectors to semantic lexicons. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies1606–15 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  24. Fillmore CJ. 1965. Indirect Object Constructions in English and the Ordering of Transformations. The Hague, Neth: Mouton
    [Google Scholar]
  25. Fillmore CJ. 1968. Lexical entries for verbs. Found. Lang. 4:373–93
    [Google Scholar]
  26. Fillmore CJ. 1976. Frame semantics and the nature of language. Ann. N.Y. Acad. Sci. 280:20–32
    [Google Scholar]
  27. Fillmore CJ 1977. The need for a frame semantics in linguistics. Statistical Methods in Linguistics, Vol. 12 H Karlgren 5–29 Stockholm: Scriptor
    [Google Scholar]
  28. Fillmore CJ. 1982. Frame semantics. Linguistics in the Morning Calm111–37 Seoul: Hanshin
    [Google Scholar]
  29. Fisher C, Gleitman H, Gleitman LR. 1991. On the semantic content of subcategorization frames. Cogn. Psychol. 23:3331–92
    [Google Scholar]
  30. Foley WA, Van Valin RD Jr 1984. Functional Syntax and Universal Grammar Cambridge, UK: Cambridge Univ. Press
    [Google Scholar]
  31. Gao T, Fisch A, Chen D. 2021. Making pre-trained language models better few-shot learners. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)3816–30 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  32. Gleitman L. 1990. The structural sources of verb meanings. Lang. Acquis. 1:13–55
    [Google Scholar]
  33. Goldberg AE. 1995. Constructions: A Construction Grammar Approach to Argument Structure Chicago: Univ. Chicago Press
    [Google Scholar]
  34. Gross M. 1975. Méthodes en syntaxe Paris: Hermann
    [Google Scholar]
  35. Gruber JS. 1965. Studies in lexical relations PhD Thesis, MIT, Cambridge, MA
    [Google Scholar]
  36. Guerssel M, Hale K, Laughren M, Levin B, Eagle JW 1985. A cross-linguistic study of transitivity alternations. Papers from the Parasession on Causatives and Agentivity at the Twenty-First Regional Meeting, Vol. 21 Part 2 48–63 Chicago: Chicago Linguist. Soc.
    [Google Scholar]
  37. Hajič J, Hajičová E, Panevová J, Sgall P, Cinková S et al. 2012. Prague Czech-English Dependency Treebank 2.0 Prague: Inst. Form. Appl. Linguist., Charles Univ https://ufal.mff.cuni.cz/pcedt2.0/
    [Google Scholar]
  38. Hale K, Keyser SJ. 1987. A view from the middle Lex. Project Work. Pap. 10, Cent. Cogn. Sci., MIT Cambridge, MA:
    [Google Scholar]
  39. Hartshorne JK, Bonial C, Palmer M. 2014. The VerbCorner Project: findings from Phase 1 of crowd-sourcing a semantic decomposition of verbs. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)397–402 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  40. Heppin KF, Gronostaj MT. 2012. The rocky road towards a Swedish FrameNet – creating SweFN. Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)256–61 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  41. Hewitt J, Manning CD. 2019. A structural probe for finding syntax in word representations. 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)4129–38 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  42. Huang Z, Wong K-F, Li W, Song D, Bruza P. 2003. Back to the future: a logical framework for temporal information representation and inferencing from financial news. Proceedings of the International Conference on Natural Language Processing and Knowledge Engineering, 200395–101 New York: IEEE
    [Google Scholar]
  43. Jackendoff R. 1983. Semantics and Cognition, Vol. 8 Cambridge, MA: MIT Press
    [Google Scholar]
  44. Jackendoff R. 2010. Meaning and the Lexicon: The Parallel Architecture 1975–2010 Oxford, UK: Oxford Univ. Press
    [Google Scholar]
  45. Jawahar G, Sagot B, Seddah D, Unicomb S, Iñiguez G et al. 2019. What does BERT learn about the structure of language?. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics3651–57 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  46. Joanis E, Stevenson S, James D 2008. A general feature space for automatic verb classification. Nat. Lang. Eng. 14:3337–67
    [Google Scholar]
  47. Jurgens D, Klapaftis I. 2013. SemEval-2013 task 13: word sense induction for graded and non-graded senses. Second Joint Conference on Lexical and Computational Semantics (*SEM), Vol. 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)290–99 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  48. Kamp JB. 2019. Statistical modeling at the syntax-semantics interface: exploiting automatically induced lexical classes evaluated through variational Bayesian inference MA Thesis, Utrecht Univ. Utrecht, Neth:.
    [Google Scholar]
  49. Kawahara D, Palmer M. 2014. Single classifier approach for verb sense disambiguation based on generalized features. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)4210–13 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  50. Kawahara D, Peterson D, Palmer M. 2014. A step-wise usage-based method for inducing polysemy-aware verb classes. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)1030–40 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  51. Kim J-u, Hahm Y, Choi KS. 2016. Korean FrameNet expansion based on projection of Japanese FrameNet. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations175–79 Osaka, Japan: COLING 2016 Organ. Comm.
    [Google Scholar]
  52. Kipper K, Korhonen A, Ryant N, Palmer M. 2006. Extending VerbNet with novel verb classes. Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC'06)1027–32 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  53. Kipper Schuler K 2005. VerbNet: a broad-coverage, comprehensive verb lexicon PhD Thesis, Univ. Pa. Philadelphia:
    [Google Scholar]
  54. Kondratyuk D, Straka M. 2019. 75 languages, 1 model: parsing Universal Dependencies universally. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)2779–95 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  55. Lapata M. 1999. Acquiring lexical generalizations from corpora: a case study for diathesis alternations. Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics397–404 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  56. Laughren M. 1988. Toward a lexical representation of Warlpiri verbs. Thematic Relations W Wilkins 215–42 Leiden, Neth: Brill
    [Google Scholar]
  57. Lauscher A, Majewska O, Ribeiro LFR, Gurevych I, Rozanov N, Glavaš G. 2020a. Common sense or world knowledge? Investigating adapter-based knowledge injection into pretrained transformers. Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures43–49 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  58. Lauscher A, Vulić I, Ponti EM, Korhonen A, Glavaš G. 2020b. Specializing unsupervised pretraining models for word-level semantic similarity. Proceedings of the 28th International Conference on Computational Linguistics1371–83 n.p.: Int. Comm. Comput. Linguist .
    [Google Scholar]
  59. Lederer A, Gleitman H, Gleitman L 1995. Verbs of a feather flock together: semantic information in the structure of maternal speech. Beyond Names for Things: Young Children's Acquisition of Verbs M Tomasello, WE Merriman 277–97 Hillsdale, NJ: Lawrence Erlbaum
    [Google Scholar]
  60. Levin B. 1985. Lexical Semantics in Review Cambridge, MA: MIT Cent. Cogn. Sci.
    [Google Scholar]
  61. Levin B. 1993. English Verb Classes and Alternations: A Preliminary Investigation Chicago: Univ. Chicago Press
    [Google Scholar]
  62. Levin B. 2015. Semantics and pragmatics of argument alternations. Annu. Rev. Linguist. 1:63–83
    [Google Scholar]
  63. Li J, Brew C. 2008. Which are the best features for automatic verb classification. Proceedings of ACL-08: HLT434–42 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  64. Li W, Wong KF, Yuan C. 2003. A design of temporal event extraction from Chinese financial news. Int. J. Comput. Proc. Orient. Lang. 16:21–39
    [Google Scholar]
  65. Liu M-c, Chiang T-y. 2008. The construction of Mandarin VerbNet: a frame-based study of statement verbs. Lang. Linguist. 9:2239–70
    [Google Scholar]
  66. Liu NF, Gardner M, Belinkov Y, Peters ME, Smith NA. 2019. Linguistic knowledge and transferability of contextual representations. 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)1073–94 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  67. Liu Q, McCarthy D, Vulić I, Korhonen A. 2019. Investigating cross-lingual alignment methods for contextualized embeddings with token-level evaluation. Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)33–43 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  68. Longacre RE. 1976. An Anatomy of Speech Notions Berlin: De Gruyter
    [Google Scholar]
  69. Majewska O. 2021. Acquiring and harnessing verb knowledge for multilingual natural language processing PhD Thesis, Univ. Cambridge Cambridge, UK:
    [Google Scholar]
  70. Majewska O, McCarthy D, van den Bosch J, Kriegeskorte N, Vulić I, Korhonen A. 2021a. Semantic data set construction from human clustering and spatial arrangement. Comput. Linguist. 47:169–116
    [Google Scholar]
  71. Majewska O, Vulić I, Glavaš G, Ponti EM, Korhonen A. 2021b. Verb knowledge injection for multilingual event processing. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)6952–69 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  72. Majewska O, Vulić I, McCarthy D, Huang Y, Murakami A et al. 2018. Investigating the cross-lingual translatability of VerbNet-style classification. Lang. Resour. Eval. 52:3771–99
    [Google Scholar]
  73. Majewska O, Vulić I, McCarthy D, Korhonen A. 2020. Manual clustering and spatial arrangement of verbs for multilingual evaluation and typology analysis. Proceedings of the 28th International Conference on Computational Linguistics4810–24 n.p.: Int. Comm. Comput. Linguist.
    [Google Scholar]
  74. Manning CD, Clark K, Hewitt J, Khandelwal U, Levy O. 2020. Emergent linguistic structure in artificial neural networks trained by self-supervision. PNAS 117:4830046–54
    [Google Scholar]
  75. Materna J 2012. LDA-frames: an unsupervised approach to generating semantic frames. Lecture Notes in Computer Science, Vol. 7181: Computational Linguistics and Intelligent Text Processing (CICLing 2012) A Gelbukh 376–87 Berlin: Springer
    [Google Scholar]
  76. Mikelić Preradović N, Boras D 2013. Semi-automatic verb valence frame assignment through VerbNet classification. Lecture Notes in Computer Science, Vol. 8082: Text, Speech, and Dialogue (TSD 2013) I Habernal, V Matoušek 492–500 Berlin: Springer
    [Google Scholar]
  77. Mousser J 2010. A large coverage verb taxonomy for Arabic. Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)2675–81 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  78. Mrkšić N, Vulić I, Ó Séaghdha D, Leviant I, Reichart R et al. 2017. Semantic specialization of distributional word vector spaces using monolingual and cross-lingual constraints. Trans. Assoc. Comput. Linguist. 5:309–24
    [Google Scholar]
  79. Nguyen KA, Schulte im Walde S, Vu NT. 2016. Integrating distributional lexical contrast into word embeddings for antonym-synonym distinction. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)454–59 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  80. Ó Séaghdha D, Copestake A. 2008. Semantic classification with distributional kernels. Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)649–56 Manchester, UK: COLING 2008 Organ. Comm.
    [Google Scholar]
  81. Ohara K. 2012. Semantic annotations in Japanese FrameNet: comparing frames in Japanese and English. Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)1559–62 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  82. Pala K, Horák A 2008. Can complex valency frames be universal?. Proceedings of Recent Advances in Slavonic Natural Language Processing (RASLAN 2008) P Sojka, A Horák 41–49 Brno, Czech Repub: Masaryk Univ.
    [Google Scholar]
  83. Palmer M. 2009. Semlink: linking PropBank, VerbNet and FrameNet Presented at the Generative Lexicon Conference (GenLex-09) Pisa, Italy:
    [Google Scholar]
  84. Parker R, Graff D, Kong J, Chen K, Maeda K 2011. English Gigaword Fifth Edition LDC2011T07 Tech. Rep., Linguist. Data Consort. Philadelphia:
    [Google Scholar]
  85. Peters ME, Neumann M, Logan RL IV, Schwartz R, Joshi V et al. 2019. Knowledge enhanced contextual word representations. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)43–54 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  86. Peterson D, Brown S, Palmer M. 2020. Verb class induction with partial supervision. Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20)8616–23 Palo Alto, CA: Assoc. Adv. Artif. Intell.
    [Google Scholar]
  87. Peterson D, Palmer M. 2018. Bayesian verb sense clustering. Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18)5398–405 Palo Alto, CA: Assoc. Adv. Artif. Intell.
    [Google Scholar]
  88. Peterson DW, Boyd-Graber J, Palmer M, Kawhara D 2016. Leveraging VerbNet to build corpus-specific verb clusters. Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*SEM 2016)102–7 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  89. Pinker S. 1989. Learnability and Cognition: The Acquisition of Argument Structure Cambridge, MA: MIT Press
    [Google Scholar]
  90. Ponti EM, Vulić I, Glavaš G, Mrkšić N, Korhonen A. 2018. Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing282–93 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  91. Ponti EM, Vulić I, Glavaš G, Reichart R, Korhonen A. 2019. Cross-lingual semantic specialization via lexical relation induction. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)2206–17 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  92. Pradet Q, Danlos L, de Chalendar G. 2014. Adapting VerbNet to French using existing resources. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)1122–26 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  93. Preradovic NM, Boras D, Kisicek S. 2009. CROVALLEX: Croatian verb valence lexicon. Proceedings of the ITI 2009 31st International Conference on Information Technology Interfaces533–38 New York: IEEE
    [Google Scholar]
  94. Radford A, Narasimhan K, Salimans T, Sutskever I. 2018. Improving language understanding by generative pre-training Tech. Rep., OpenAI San Francisco:
    [Google Scholar]
  95. Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. 2019. Language models are unsupervised multitask learners. OpenAI Blog Feb. 14. https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
    [Google Scholar]
  96. Raffel C, Shazeer N, Roberts A, Lee K, Narang S et al. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21:1401–67
    [Google Scholar]
  97. Scarton C, Alusio S. 2012. Towards a cross-linguistic VerbNet-style lexicon for Brazilian Portuguese. Proceedings of the LREC 2012 Workshop on Creating Cross-Language Resources for Disconnected Languages and Styles11–18 Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  98. Scarton C, Sun L, Kipper-Schuler K, Duran MS, Palmer M, Korhonen A 2014. Verb clustering for Brazilian Portuguese. Lecture Notes in Computer Science, Vol. 8403: Computational Linguistics and Intelligent Text Processing (CICLing 2014) A Gelbukh 25–39 Berlin: Springer
    [Google Scholar]
  99. Schick T, Schütze H. 2021. It's not just size that matters: Small language models are also few-shot learners. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies2339–52 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  100. Schulte im Walde S. 2000. Clustering verbs semantically according to their alternation behaviour. Proceedings of the 18th Conference on Computational Linguistics, Vol. 2747–53 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  101. Schulte im Walde S. 2006. Experiments on the automatic induction of German semantic verb classes. Comput. Linguist. 32:2159–94
    [Google Scholar]
  102. Sedoc J, Wijaya D, Rouhizadeh M, Schwartz A, Ungar L. 2017. Deriving verb predicates by clustering verbs with arguments. arXiv:1708.00416 [cs.CL]
  103. She L, Chai J. 2017. Interactive learning of grounded verb semantics towards human-robot communication. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)1634–44 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  104. Subirats C, Sato H. 2004. Spanish FrameNet and FrameSQL Presented at the 4th International Conference on Language Resources and Evaluation (LREC'04) Workshop on Building Lexical Resources from Semantically Annotated Corpora Lisbon, Port.: May 30
    [Google Scholar]
  105. Sun L. 2013. Automatic induction of verb classes using clustering PhD Thesis, Univ. Cambridge Cambridge, UK:
    [Google Scholar]
  106. Sun L, Korhonen A. 2009. Improving verb clustering with automatically acquired selectional preferences. Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing638–47 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  107. Sun L, Korhonen A, Krymolowski Y 2008. Verb class discovery from rich syntactic data. Lecture Notes in Computer Science, Vol. 4919: Computational Linguistics and Intelligent Text Processing (CICLing 2008) A Gelbukh 16–27 Berlin: Springer
    [Google Scholar]
  108. Sun L, Korhonen A, Poibeau T, Messiant C. 2010. Investigating the cross-linguistic potential of VerbNet-style classification. Proceedings of the 23rd International Conference on Computational Linguistics1056–64 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  109. Talmy L 1985. Lexicalization patterns: semantic structure in lexical forms. Language Typology and Syntactic Description, Vol. 3: Grammatical Categories and the Lexicon T Shopen 57–149 Cambridge, UK: Cambridge Univ. Press
    [Google Scholar]
  110. Tenney I, Xia P, Chen B, Wang A, Poliak A et al. 2019. What do you learn from context? Probing for sentence structure in contextualized word representations. arXiv:1905.06316 [cs.CL]
  111. Torrent TT, Baker CF, Czulo O, Ohara K, Petruck MR, eds. 2020. Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  112. Torrent TT, Salomão MM, Campos F, Braga R, Matos E et al. 2014. Copa 2014 FrameNet Brasil: a frame-based trilingual electronic dictionary for the Football World Cup. Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations10–14 Dublin, Irel./Stroudsburg, PA: Dublin City Univ./Assoc. Comput. Linguist.
    [Google Scholar]
  113. Tourille J. 2018. Extracting clinical event timelines: temporal information extraction and coreference resolution in electronic health records PhD Thesis, Univ. Paris-Saclay Paris:
    [Google Scholar]
  114. Turner JC, Hogg MA, Oakes PJ, Reicher SD, Wetherell MS. 1987. Rediscovering the Social Group: A Self-Categorization Theory Oxford, UK: Basil Blackwell
    [Google Scholar]
  115. Urešová Z, Fučíková E, Hajicová E, Hajic J. 2018. Creating a verb synonym lexicon based on a parallel corpus. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) Paris: Eur. Lang. Resour. Assoc.
    [Google Scholar]
  116. Urešová Z, Fučíková E, Šindlerová J. 2016. CzEngVallex: a bilingual Czech-English valency lexicon. Prague Bull. Math. Linguist. 105:117–50
    [Google Scholar]
  117. Urešová Z, Štěpánek J, Hajič J, Panevova J, Mikulová M. 2014. PDT-Vallex: Czech Valency Lexicon Linked to Treebanks Prague: Charles Univ., Fac. Math. Phys.
    [Google Scholar]
  118. UzZaman N, Llorens H, Derczynski L, Allen J, Verhagen M, Pustejovsky J. 2013. SemEval-2013 task 1: TempEval-3: evaluating time expressions, events, and temporal relations. Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)1–9 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  119. Van Valin RD. 1993. A synopsis of role and reference grammar. Advances in Role and Reference Grammar1–164 Amsterdam: John Benjamins
    [Google Scholar]
  120. Vendler Z. 1967. Linguistics in Philosophy Ithaca, NY: Cornell Univ. Press
    [Google Scholar]
  121. Vendler Z. 1972. Res Cogitans: An Essay in Rational Psychology Ithaca, NY: Cornell Univ. Press
    [Google Scholar]
  122. Verhagen M, Saurí R, Caselli T, Pustejovsky J. 2010. SemEval-2010 task 13: TempEval-2. Proceedings of the 5th International Workshop on Semantic Evaluation57–62 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  123. Vlachos A, Korhonen A, Ghahramani Z. 2009. Unsupervised and constrained Dirichlet process mixture models for verb clustering. Proceedings of the EACL Workshop on Geometrical Models of Natural Language Semantics74–82 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  124. Vulić I, Ponti EM, Litschko R, Glavaš G, Korhonen A. 2020. Probing pretrained language models for lexical semantics. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)7222–40 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  125. Wang R, Tang D, Duan N, Wei Z, Huang X et al. 2020. K-adapter: infusing knowledge into pre-trained models with adapters. arXiv:2002.01808 [cs.CL]
  126. White AS, Dudley R, Hacquard V, Lidz J. 2014. Discovering classes of attitude verbs using subcategorization frame distributions. Proceedings of the 43rd Annual Meeting of the North East Linguistic Society (NELS 43)249–60 Amherst, MA: Grad. Linguist. Stud. Assoc.
    [Google Scholar]
  127. Wieting J, Bansal M, Gimpel K, Livescu K. 2015. From paraphrase database to compositional paraphrase model and back. Trans. Assoc. Comput. Linguist. 3:345–58
    [Google Scholar]
  128. You L, Liu K. 2005. Building Chinese FrameNet database. Proceedings of the 2005 International Conference on Natural Language Processing and Knowledge Engineering301–6 New York: IEEE
    [Google Scholar]
  129. Zhang Z, Han X, Liu Z, Jiang X, Sun M, Liu Q. 2019. ERNIE: enhanced language representation with informative entities. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics1441–51 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  130. Zhou J, Zhao H. 2019. Head-driven phrase structure grammar parsing on Penn Treebank. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics2396–408 Stroudsburg, PA: Assoc. Comput. Linguist.
    [Google Scholar]
  131. Zwicky AM. 1971. In a manner of speaking. Linguist. Inq. 2:2223–33
    [Google Scholar]
/content/journals/10.1146/annurev-linguistics-030521-043632
Loading
/content/journals/10.1146/annurev-linguistics-030521-043632
Loading

Data & Media loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error