Capturing anomalies in the choice of content words in compositional distributional semantic space
Proceedings of Recent Advances in Natural Language Processing
9th International Conference on “Recent Advances in Natural Language Processing” (RANLP 2013)
ACL Home Association for Computational Linguistics
MetadataShow full item record
Kochmar, E., & Briscoe, E. (2013). Capturing anomalies in the choice of content words in compositional distributional semantic space. Proceedings of Recent Advances in Natural Language Processing, 365-372. https://doi.org/10.17863/CAM.9673
In this work, we present a new task for testing compositional distributional semantic models. Recently, there has been a spate of research into how distributional representations of individual words can be combined to represent the meaning of phrases. Vecchi et al. (2011) have shown that some compositional models, including the additive and multiplicative models of Mitchell and Lapata (2008; 2010) and the linear map-based model of Baroni and Zamparelli (2010), can be applied to detect semantically anomalous adjective- noun combinations. We extend their experiments and apply these models to the combinations extracted from texts written by learners of English. Our work contributes to the field of compositional distributional semantics by introducing a new test paradigm for semantic models and shows how these models can be used for error detection in language learners' content word combinations.
We are grateful to Cambridge ESOL, a division of Cambridge Assessment, and Cambridge University Press for supporting this research and for granting us access to the CLC for research purposes.
This record's DOI: https://doi.org/10.17863/CAM.9673
This record's URL: https://www.repository.cam.ac.uk/handle/1810/264266
Attribution-NonCommercial-ShareAlike 4.0 International, Attribution-NonCommercial-ShareAlike 4.0 International, Attribution-NonCommercial-ShareAlike 4.0 International
Recommended or similar items
The following licence files are associated with this item: