Published on Wed Nov 09 2016

A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation

Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran, Min-Yen Kan

Word embeddings are now ubiquitous forms of word representation in natural language processing. There have been applications of word embeddins for monolingual word sense disambiguation (WSD) in English, but few comparisons have been done.

0
0
0
Abstract

Word embeddings are now ubiquitous forms of word representation in natural language processing. There have been applications of word embeddings for monolingual word sense disambiguation (WSD) in English, but few comparisons have been done. This paper attempts to bridge that gap by examining popular embeddings for the task of monolingual English WSD. Our simplified method leads to comparable state-of-the-art performance without expensive retraining. Cross-Lingual WSD - where the word senses of a word in a source language e come from a separate target translation language f - can also assist in language learning; for example, when providing translations of target vocabulary for learners. Thus we have also applied word embeddings to the novel task of cross-lingual WSD for Chinese and provide a public dataset for further benchmarking. We have also experimented with using word embeddings for LSTM networks and found surprisingly that a basic LSTM network does not work well. We discuss the ramifications of this outcome.

Tue Aug 31 2021
NLP
Sense representations for Portuguese: experiments with sense embeddings and deep neural language models
Unsupervised sense representations are able to induce different senses of a word by analyzing its contextual semantics in a text. Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks.
3
0
0
Mon Jan 25 2021
NLP
PolyLM: Learning about Polysemy through Language Modeling
0
0
0
Mon Sep 23 2019
NLP
Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings
contextualized word embeddings (CWE) are a major innovation in NLP. CWEs provide a model for word sense disambiguation (WSD) We introduce a simple but effective approach to WSD using a nearest neighbor classification on CWE.
0
0
0
Sat Mar 14 2020
NLP
Word Sense Disambiguation for 158 Languages using Word Embeddings Only
Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. We present a method that takes as input a standard pre-trained word embedding model.
0
0
0
Thu Mar 11 2021
Artificial Intelligence
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
0
0
0
Sat Sep 15 2018
NLP
CLUSE: Cross-Lingual Unsupervised Sense Embeddings
The proposed approach shows the superior quality of sense embeddings evaluated in both monolingual and bilingual spaces. The model is evaluated on the Stanford Contextual Word Similarity (SCWS) dataset.
0
0
0