On the Use of Automatically Acquired Examples for All-Nouns Word Sense Disambiguation
By David Martínez, Oier Lopez de Lacalle, Eneko Agirre. 2008
32 citations recorded by the source corpus.
This article focuses on Word Sense Disambiguation (WSD), which is a Natural Language Processing task that is thought to be important for many Language Technology applications, such as Information Retrieval, Information Extraction, or Machine Translation. One of the main issues preventing the deployment of WSD technology is the lack of training examples for Machine Learning systems, also known as the Knowledge Acquisition Bottleneck. A method which has been shown to work for small samples of words is the automatic acquisition of examples. We have previously shown that one of the most promising example acquisition methods scales up and produces a freely available database of 150 million examples from Web snippets for all polysemous nouns in WordNet. This paper focuses on the issues that arise when using those examples, all alone or in addition to manually tagged examples, to train a supervised WSD system for all nouns. The extensive evaluation on both lexical-sample and all-words Senseval benchmarks shows that we are able to improve over commonly used baselines and to achieve top-rank performance. The good use of the prior distributions from the senses proved to be a crucial factor.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jason Aaron Edward Weston
- Yoshua Bengio
- Antoine Bordes
- Mohit Bansal
- Jianfeng Gao
- Kyunghyun Cho
- Christopher D. Manning
- Percy Liang
Citations in the corpus
- Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing (2012, background): “Finally, several previous works have targeted to improve WSD by using extra-knowledge by either automatically acquiring examples (Martinez et al., 2008) or by connecting different knowledge bases (Havasi et al.”
- Constrained Semi-supervised Learning in the Presence of Unanticipated Classes (2016, background): “[84] which trains a decision list classifier on monosemous (unambiguous) words for the word sense disambiguation task.”