Cross-lingual Lexical Sememe Prediction

Published in

Conference on Empirical Methods in Natural Lang...(2017)

External Links:

Generate Graph DownloadPDF

TL;DR

This work proposes a novel framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction, and shows that the proposed model achieves consistent and significant improvements as compared to baseline methods in cross-lingUAL sememe Prediction.

Abstract

Sememes are defined as the minimum semantic units of human languages. As important knowledge sources, sememe-based linguistic knowledge bases have been widely used in many NLP tasks. However, most languages still do not have sememe-based linguistic knowledge bases. Thus we present a task of cross-lingual lexical sememe prediction, aiming to automatically predict sememes for words in other languages. We propose a novel framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction. Experimental results on real-world datasets show that our proposed model achieves consistent and significant improvements as compared to baseline methods in cross-lingual sememe prediction. The codes and data of this paper are available at https://github.com/thunlp/CL-SP.

Authors

Zhiyuan Liu

34 papers

Yankai Lin

9 papers

Maosong Sun

46 papers

References46 items

Language Modeling with Sparse Product of Sememe Experts

Incorporating Chinese Characters of Words for Lexical Sememe Prediction

Chinese LIWC Lexicon Expansion via Hierarchical Classification of Word Embeddings with Sememe Attention

Word Translation Without Parallel Data

Lexical Sememe Prediction via Word Embeddings and Matrix Factorization

Cross-lingual Lexical Sememe Prediction

Published in

Conference on Empirical Methods in Natural Lang...(2017)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Zhiyuan Liu

34 papers

Yankai Lin

9 papers

Maosong Sun

46 papers

References46 items

Language Modeling with Sparse Product of Sememe Experts

Incorporating Chinese Characters of Words for Lexical Sememe Prediction

Chinese LIWC Lexicon Expansion via Hierarchical Classification of Word Embeddings with Sememe Attention

Word Translation Without Parallel Data

Lexical Sememe Prediction via Word Embeddings and Matrix Factorization

Fanchao Qi

10 papers

Ruobing Xie

10 papers

TL;DR

Abstract

Authors

References46 items

Language Modeling with Sparse Product of Sememe Experts

Incorporating Chinese Characters of Words for Lexical Sememe Prediction

Chinese LIWC Lexicon Expansion via Hierarchical Classification of Word Embeddings with Sememe Attention

Word Translation Without Parallel Data

Lexical Sememe Prediction via Word Embeddings and Matrix Factorization

TL;DR

Abstract

Authors

References46 items

Language Modeling with Sparse Product of Sememe Experts

Incorporating Chinese Characters of Words for Lexical Sememe Prediction

Chinese LIWC Lexicon Expansion via Hierarchical Classification of Word Embeddings with Sememe Attention

Word Translation Without Parallel Data

Lexical Sememe Prediction via Word Embeddings and Matrix Factorization

Learning bilingual word embeddings with (almost) no bilingual data

Improved Word Representation Learning with Sememes

A survey of cross-lingual embedding models

Bilingual Lexicon Induction from Non-Parallel Data with Minimal Supervision

Learning Crosslingual Word Embeddings without Bilingual Corpora

Cross-lingual Models of Word Embeddings: An Empirical Comparison

Counter-fitting Word Vectors to Linguistic Constraints

Minimally-Constrained Multilingual Embeddings via Artificial Code-Switching

Massively Multilingual Word Embeddings

Joint Word Representation Learning Using a Corpus and a Semantic Lexicon

Trans-gram, Fast Cross-lingual Word-embeddings

Learning Semantic Word Embeddings based on Ordinal Knowledge Constraints

Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning

Learning Cross-lingual Word Embeddings via Matrix Co-factorization

Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction

Bilingual Word Representations with Monolingual Quality in Mind

Improving zero-shot learning by mitigating the hubness problem

BilBOWA: Fast Bilingual Distributed Representations without Word Alignments

GloVe: Global Vectors for Word Representation

SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation

Learning Bilingual Word Representations by Marginalizing Alignments

Improving Vector Space Word Representations Using Multilingual Correlation

An Autoencoder Approach to Learning Bilingual Word Representations

Multilingual Distributed Representations without Word Alignment

Bilingual Word Embeddings for Phrase-Based Machine Translation

Exploiting Similarities among Languages for Machine Translation

Efficient Estimation of Word Representations in Vector Space

SemEval-2012 Task 4: Evaluating Chinese Word Similarity

A hybrid approach for Chinese word similarity computing based on HowNet

Punctuation as Implicit Annotations for Chinese Word Segmentation

Chinese Word Sense Disambiguation Using HowNet

HowNet - a hybrid language and knowledge resource

WordNet: A Lexical Database for English

A Set of Postulates for the Science of Language

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

Deep Multilingual Correlation for Improved Word Embeddings

Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon

Method of discriminant for Chinese sentence sentiment orientation based on HowNet

Visualizing Data using t-SNE

HowNet Based Chinese Question Automatic Classification

Placing search in context: the concept revisited

Field of Study

Venue Information

Name

Type

URL

Alternate Names