2000 character limit reached
Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology (2405.09293v1)
Published 15 May 2024 in cs.CL and cs.AI
Abstract: Markedness in natural language is often associated with non-literal meanings in discourse. Differential Object Marking (DOM) in Korean is one instance of this phenomenon, where post-positional markers are selected based on both the semantic features of the noun phrases and the discourse features that are orthogonal to the semantic features. Previous work has shown that distributional models of language recover certain semantic features of words -- do these models capture implied discourse-level meanings as well? We evaluate whether a set of LLMs are capable of associating discourse meanings with different object markings in Korean. Results suggest that discourse meanings of a grammatical marker can be more challenging to encode than that of a discourse marker.
- Judith Aissen. 2003. Differential Object Marking: Iconicity vs. Economy. Natural Language & Linguistic Theory, 21:435–483.
- Gemma Boleda. 2020. Distributional Semantics and Linguistic Theory. Annual Review of Linguistics, 6(1):213–234.
- Georg Bossong. 1991. Differential Object Marking in Romance and Beyond. In Dieter Wanner and Douglas A. Kibbee, editors, New analyses in Romance linguistics, pages 143–170. John Benjamins Publishing Company, Amsterdam.
- Daniel Büring. 2003. On D-Trees, Beans, And B-Accents. Linguistics and Philosophy, 26:511–545.
- Hye-Won Choi. 1996. Optimizing structure in context: Scrambling and information structure. Ph.D. thesis, Stanford University.
- Injoo Choi-Jonin. 2008. Particles and Propositions in Korean. In Adpositions: Pragmatics, Semantic and Syntactic Perspectives, number 74 in Typological Studies in Language, pages 133–170. John Benjamins Publishing Company, Amsterdam/Philadelphia.
- Neural language models as psycholinguistic subjects: Representations of syntactic state. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 32–42, Minneapolis, Minnesota. Association for Computational Linguistics.
- H. Paul Grice. 1989. Studies in the Way of Words. Harvard University Press, Cambridge, MA.
- Zellig S. Harris. 1954. Distributional Structure. WORD, 10(2-3):146–162.
- Laurence R Horn. 1981. Exhaustiveness and the Semantics of Clefts. In Proceedings of the Eleventh Annual Meeting of the North Eastern Linguistic Society, volume 11, pages 125–142.
- A fine-grained comparison of pragmatic language understanding in humans and language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4194–4213, Toronto, Canada. Association for Computational Linguistics.
- Jennifer Hu and Roger Levy. 2023. Prompt-based methods may underestimate large language models’ linguistic generalizations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5040–5060. Association for Computational Linguistics.
- Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8690–8705, Online. Association for Computational Linguistics.
- Scaling Laws for Neural Language Models. ArXiv:2001.08361 [cs, stat].
- Jieun Kim. 2018. Deriving the contrastiveness of contrastive -nun in Korean. Linguistics and Philosophy, 41(4):457–482.
- Song-Nim Kwon and Anne Zribi-Hertz. 2008. Differential Function Marking, Case, and Information Structure: Evidence from Korean. Language, 84(2):258–299.
- Knud Lambrecht. 1994. Information Structure and Sentence Form: Topic, focus, and the mental representations of discourse referents. Cambridge University Press.
- Chungmin Lee. 2003. Contrastive topic and/or contrastive focus. In Japanese/Korean Linguistics, volume 12, pages 352–364.
- Chungmin Lee. 2017. Contrastiveness in Information Structure, Alternatives and Scalar Implicatures. 91. Springer International Publishing, Cham, Switzerland.
- Hanjung Lee. 2006. Iconicity and Variation in the Choice of Object Forms in Korean. Language Research, 42(2):323–355.
- Hanjung Lee. 2007. Case ellipsis at the grammar/pragmatics interface: A formal analysis from a typological perspective. Journal of Pragmatics, 39(9):1465–1481.
- Alessandro Lenci. 2018. Distributional Models of Word Meaning. Annual Review of Linguistics, 4(1):151–171.
- Marco Marelli and Marco Baroni. 2015. Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. Psychological Review, 122(3):485–515.
- Mats Rooth. 1992. A theory of focus interpretation. Natural Language Semantics, 1(1):75–116.
- BERT Rediscovers the Classical NLP Pipeline. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4593–4601. Association for Computational Linguistics.
- What do you learn from context? Probing for sentence structure in contextualized word representations.
- Sean Trott and Benjamin Bergen. 2021. RAW-C: Relatedness of Ambiguous Words–in Context (A New Lexical Resource for English). In 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), pages 7077–7087, Online. Association for Computational Linguistics.
- Do Large Language Models Know What Humans Know? Cognitive Science, 47(7):e13309.
- Robert Van Rooij and Katrin Schulz. 2004. Exhaustive Interpretation of Complex Sentences. Journal of Logic, Language and Information, 13(4):491–519.
- Hagyeong Shin (2 papers)
- Sean Trott (11 papers)