Learning Word Sense Embeddings from Word Sense Definitions

2016/06/15 by Qi Li, Li, Qi, Tianshi Li +3
Computer Science · #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1606.04835

To appear at NLPCC-ICCPOL 2016

arxiv created 2016/10/24 · arxiv updated 2016/10/25

Abstract

Word embeddings play a significant role in many modern NLP systems. Since learning one representation per word is problematic for polysemous words and homonymous words, researchers propose to use one embedding per word sense. Their approaches mainly train word sense embeddings on a corpus. In this paper, we propose to use word sense definitions to learn one embedding per word sense. Experimental results on word similarity tasks and a word sense disambiguation task show that word sense embeddings produced by our approach are of high quality.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network

Related

• Making Sense of Word Embeddings
• A Simple Approach to Learn Polysemous Word Embeddings
• Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
• Embeddings for Word Sense Disambiguation: An Evaluation Study
• Multi-sense Definition Modeling using Word Sense Decompositions