Neural Sequence Learning Models for Word Sense Disambiguation
Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features.
PDF Abstract
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Word Sense Disambiguation | Supervised: | Bi-LSTM<sub>att+LEX+POS</sub> | Senseval 2 | 72.0 | # 19 | |
| Senseval 3 | 69.1 | # 22 | ||||
| SemEval 2007 | 64.8* | # 22 | ||||
| SemEval 2013 | 66.9 | # 18 | ||||
| SemEval 2015 | 71.5 | # 22 | ||||
| Word Sense Disambiguation | Supervised: | Bi-LSTM<sub>att+LEX</sub> | Senseval 2 | 72.0 | # 19 | |
| Senseval 3 | 69.4 | # 21 | ||||
| SemEval 2007 | 63.7* | # 22 | ||||
| SemEval 2013 | 66.4 | # 21 | ||||
| SemEval 2015 | 72.4 | # 18 |
