A Unified Model for Reverse Dictionary and Definition Modelling
This work addresses the problem of dictionary-related tasks for natural language processing applications, though it appears incremental as it builds on existing benchmarks without introducing a new paradigm.
The paper tackles the dual tasks of retrieving words from definitions and generating definitions for words using a unified neural model, achieving promising automatic scores and human preference in evaluations.
We build a dual-way neural dictionary to retrieve words given definitions, and produce definitions for queried words. The model learns the two tasks simultaneously and handles unknown words via embeddings. It casts a word or a definition to the same representation space through a shared layer, then generates the other form in a multi-task fashion. Our method achieves promising automatic scores on previous benchmarks without extra resources. Human annotators prefer the model's outputs in both reference-less and reference-based evaluation, indicating its practicality. Analysis suggests that multiple objectives benefit learning.