Attention-Based Joint Entity Linking with Entity Embedding
Entity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/10/2/46 |
id |
doaj-9c77917c9db0425a9290b68418372191 |
---|---|
record_format |
Article |
spelling |
doaj-9c77917c9db0425a9290b684183721912020-11-25T00:27:20ZengMDPI AGInformation2078-24892019-02-011024610.3390/info10020046info10020046Attention-Based Joint Entity Linking with Entity EmbeddingChen Liu0Feng Li1Xian Sun2Hongzhe Han3Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Technology in Geo-Spatial Information Processing and Application System, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Technology in Geo-Spatial Information Processing and Application System, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Electronics, Chinese Academy of Sciences, Beijing 100190, ChinaEntity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context, and modeling the coherence among mentions. For the encoding of entity, we use long short term memory (LSTM) and a convolutional neural network (CNN) to encode the entity context and entity description, respectively. Then, we design a function to combine all the different entity information aspects, in order to generate unified, dense entity embeddings. For the encoding of mention context, unlike standard attention mechanisms which can only capture important individual words, we introduce a novel, attention mechanism-based LSTM model, which can effectively capture the important text spans around a given mention with a conditional random field (CRF) layer. In addition, we take the coherence among mentions into consideration with a Forward-Backward Algorithm, which is less time-consuming than previous methods. Our experimental results show that our model obtains a competitive, or even better, performance than state-of-the-art models across different datasets.https://www.mdpi.com/2078-2489/10/2/46entity linkingLSTMCNNCRFForward-Backward Algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chen Liu Feng Li Xian Sun Hongzhe Han |
spellingShingle |
Chen Liu Feng Li Xian Sun Hongzhe Han Attention-Based Joint Entity Linking with Entity Embedding Information entity linking LSTM CNN CRF Forward-Backward Algorithm |
author_facet |
Chen Liu Feng Li Xian Sun Hongzhe Han |
author_sort |
Chen Liu |
title |
Attention-Based Joint Entity Linking with Entity Embedding |
title_short |
Attention-Based Joint Entity Linking with Entity Embedding |
title_full |
Attention-Based Joint Entity Linking with Entity Embedding |
title_fullStr |
Attention-Based Joint Entity Linking with Entity Embedding |
title_full_unstemmed |
Attention-Based Joint Entity Linking with Entity Embedding |
title_sort |
attention-based joint entity linking with entity embedding |
publisher |
MDPI AG |
series |
Information |
issn |
2078-2489 |
publishDate |
2019-02-01 |
description |
Entity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context, and modeling the coherence among mentions. For the encoding of entity, we use long short term memory (LSTM) and a convolutional neural network (CNN) to encode the entity context and entity description, respectively. Then, we design a function to combine all the different entity information aspects, in order to generate unified, dense entity embeddings. For the encoding of mention context, unlike standard attention mechanisms which can only capture important individual words, we introduce a novel, attention mechanism-based LSTM model, which can effectively capture the important text spans around a given mention with a conditional random field (CRF) layer. In addition, we take the coherence among mentions into consideration with a Forward-Backward Algorithm, which is less time-consuming than previous methods. Our experimental results show that our model obtains a competitive, or even better, performance than state-of-the-art models across different datasets. |
topic |
entity linking LSTM CNN CRF Forward-Backward Algorithm |
url |
https://www.mdpi.com/2078-2489/10/2/46 |
work_keys_str_mv |
AT chenliu attentionbasedjointentitylinkingwithentityembedding AT fengli attentionbasedjointentitylinkingwithentityembedding AT xiansun attentionbasedjointentitylinkingwithentityembedding AT hongzhehan attentionbasedjointentitylinkingwithentityembedding |
_version_ |
1725340605820698624 |