Boleda, GemmaGulordava, KristinaAina, Laura2019-10-022019-10-022019Aina L, Gulordava K, Boleda G. Putting words in context: LSTM language models and lexical ambiguity. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics; 2019 Jul 28 - Aug 2; Florence, Italy. Stroudsburg (PA): ACL; 2019. p. 3342–8.http://hdl.handle.net/10230/42372Comunicació presentada al 57th Annual Meeting of the Association for Computational Linguistic (ACL 2019), celebrat els dies 28 de juliol a 2 d'agost de 2019 a Florència, Itàlia.In neural network models of language, words are commonly represented using context invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the contextually relevant information is not trivial. We investigate how an LSTM language model deals with lexical ambiguity in English, designing a method to probe its hidden representations for lexical and contextual information about words. We find that both types of information are represented to a large extent, but also that there is room for improvement for contextual information.application/pdfeng© ACL, Creative Commons Attribution 4.0 Licenseinfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.18653/v1/P19-1324Language modelsLexical ambiguityNeural networksinfo:eu-repo/semantics/openAccess