Conditional Generators of Words Definitions
This work addresses the issue of polysemy in definition modeling for natural language processing, representing an incremental improvement over existing techniques.
The paper tackled the problem of word ambiguities in definition modeling by employing latent variable modeling and soft attention mechanisms, resulting in performance improvement as shown in quantitative and qualitative evaluations.
We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word ambiguities in definition modeling and propose a possible solution by employing latent variable modeling and soft attention mechanisms. Our quantitative and qualitative evaluation and analysis of the model shows that taking into account words ambiguity and polysemy leads to performance improvement.