Approches d'analyse distributionnelle pour améliorer la désambiguïsation sémantique
This work addresses a computational bottleneck in WSD for NLP applications like information retrieval and machine translation, but it appears incremental as it builds on existing distributional approaches.
The paper tackles the combinatorial explosion problem in word sense disambiguation (WSD) by proposing two distributional analysis methods that reduce exponential complexity while maintaining coherence, with results showing that selecting distributional neighbors outperforms linearly nearest neighbors.
Word sense disambiguation (WSD) improves many Natural Language Processing (NLP) applications such as Information Retrieval, Machine Translation or Lexical Simplification. WSD is the ability of determining a word sense among different ones within a polysemic lexical unit taking into account the context. The most straightforward approach uses a semantic proximity measure between the word sense candidates of the target word and those of its context. Such a method very easily entails a combinatorial explosion. In this paper, we propose two methods based on distributional analysis which enable to reduce the exponential complexity without losing the coherence. We present a comparison between the selection of distributional neighbors and the linearly nearest neighbors. The figures obtained show that selecting distributional neighbors leads to better results.