Semi-supervised Word Sense Disambiguation with Neural Models

2016/03/22 by Dayu Yuan, Julian Richardson, Yuan, Dayu +7
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1603.07012

openalex publication_date 2016/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Determining the intended sense of words in text - word sense disambiguation (WSD) - is a long standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.

Citations

• Character-Aware Neural Language Models
• Long Short-Term Memory
• BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network
• Sequence to Sequence Learning with Neural Networks
• Distributed Representations of Words and Phrases and their Compositionality

Related

• Word Sense Disambiguation using a Bidirectional LSTM
• A Novel Neural Sequence Model with Multiple Attentions for Word Sense Disambiguation
• One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation\n of Text Data
• Incorporating Word Sense Disambiguation in Neural Language Models
• Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation