Evaluating Word Embeddings for Language Acquisition
| Autor: | Alhama, R.G., Rowland, C.F., Kidd, E., Chersoni, E., Jacobs, C., Oseki, Y., Prévot, L., Santus, E. |
|---|---|
| Přispěvatelé: | Cognitive Science & AI, Chersoni, E., Jacobs, C., Oseki, Y., Prévot, L., Santus, E. |
| Rok vydání: | 2020 |
| Předmět: |
Language Acquisition
Psycholinguistics business.industry Process (engineering) Computer science 05 social sciences Word Embeddings Semantic Relations Context (language use) 010501 environmental sciences computer.software_genre Language acquisition 01 natural sciences 050105 experimental psychology Age of Acquisition Semantic memory 0501 psychology and cognitive sciences Artificial intelligence business computer Word (computer architecture) Natural language processing 0105 earth and related environmental sciences |
| Zdroj: | Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, 38-42 STARTPAGE=38;ENDPAGE=42;TITLE=Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics Chersoni, E.; Jacobs, C.; Oseki, Y. (ed.), Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, 38-42. Stroudsburg, PA : Association for Computational Linguistics (ACL) STARTPAGE=38;ENDPAGE=42;TITLE=Chersoni, E.; Jacobs, C.; Oseki, Y. (ed.), Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics Chersoni, E.; Jacobs, C.; Oseki, Y. (ed.), Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pp. 38-42 |
| DOI: | 10.18653/v1/2020.cmcl-1.4 |
| Popis: | Item does not contain fulltext Continuous vector word representations (or word embeddings) have shown success in capturing semantic relations between words, as evidenced by evaluation against behavioral data of adult performance on semantic tasks (Pereira et al., 2016). Adult semantic knowledge is the endpoint of a language acquisition process; thus, a relevant question is whether these models can also capture emerging word representations of young language learners. However, the data for children’s semantic knowledge across development is scarce. In this paper, we propose to bridge this gap by using Age of Acquisition norms to evaluate word embeddings learnt from child-directed input. We present two methods that evaluate word embeddings in terms of (a) the semantic neighbourhood density of learnt words, and (b) convergence to adult word associations. We apply our methods to bag-of-words models, and find that (1) children acquire words with fewer semantic neighbours earlier, and (2) young learners only attend to very local context. These findings provide converging evidence for validity of our methods in understanding the prerequisite features for a distributional model of word learning. Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2020) (2020, 19 November) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|