Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing

Published in

Symmetry(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

This work proposes a novel end-to-end recurrent neural model which incorporates an entity-aware attention mechanism with a latent entity typing (LET) method and demonstrates that the model outperforms existing state-of-the-art models without any high-level features.

Abstract

Classifying semantic relations between entity pairs in sentences is an important task in natural language processing (NLP). Most previous models applied to relation classification rely on high-level lexical and syntactic features obtained by NLP tools such as WordNet, the dependency parser, part-of-speech (POS) tagger, and named entity recognizers (NER). In addition, state-of-the-art neural models based on attention mechanisms do not fully utilize information related to the entity, which may be the most crucial feature for relation classification. To address these issues, we propose a novel end-to-end recurrent neural model that incorporates an entity-aware attention mechanism with a latent entity typing (LET) method. Our model not only effectively utilizes entities and their latent types as features, but also builds word representations by applying self-attention based on symmetrical similarity of a sentence itself. Moreover, the model is interpretable by visualizing applied attention mechanisms. Experimental results obtained with the SemEval-2010 Task 8 dataset, which is one of the most popular relation classification tasks, demonstrate that our model outperforms existing state-of-the-art models without any high-level features.

Authors

Joohong Lee

2 papers

Sang-gyu Seo

2 papers

Y. Choi

2 papers

References39 items

Feature Selection

Deep Semantic Role Labeling with Self-Attention

Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering

DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding

Position-aware Attention and Supervised Data Improve Slot Filling

Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing

Published in

Symmetry(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Joohong Lee

2 papers

Sang-gyu Seo

2 papers

Y. Choi

2 papers

TL;DR

Abstract

Authors

References39 items

Feature Selection

Deep Semantic Role Labeling with Self-Attention

Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering

DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding

Position-aware Attention and Supervised Data Improve Slot Filling

TL;DR

Abstract

Authors

References39 items

Feature Selection

Deep Semantic Role Labeling with Self-Attention

Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering

DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding

Position-aware Attention and Supervised Data Improve Slot Filling

Attention is All you Need

Attention-Based Convolutional Neural Network for Semantic Relation Extraction

Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification

Hierarchical Attention Networks for Document Classification

Improved relation classification by deep recurrent neural networks with data augmentation

Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths

Relation Classification via Recurrent Neural Network

A Dependency-Based Neural Network for Relation Classification

Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

Relation Extraction: Perspective from Convolutional Neural Networks

Classifying Relations by Ranking with Convolutional Neural Networks

GloVe: Global Vectors for Word Representation

Recurrent Neural Network Regularization

Relation Classification via Convolutional Deep Neural Network

Distributed Representations of Words and Phrases and their Compositionality

Speech recognition with deep recurrent neural networks

Efficient Estimation of Word Representations in Vector Space

ADADELTA: An Adaptive Learning Rate Method

Semantic Compositionality through Recursive Matrix-Vector Spaces

Improving neural networks by preventing co-adaptation of feature detectors

Natural Language Processing (Almost) from Scratch

UTD: Classifying Semantic Relations by Combining Lexical and Semantic Resources

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals

Understanding the difficulty of training deep feedforward neural networks

2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Feature selection, L1 vs. L2 regularization, and rotational invariance

Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

Learning long-term dependencies with gradient descent is difficult

Semantic Relation Classification via Hierarchical Recurrent Neural Network with Attention

Bidirectional Long Short-Term Memory Networks for Relation Classification

Factor-based Compositional Embedding Models

A Fast and Accurate Dependency Parser using Neural Networks

Multi-way classification of semantic relations between pairs of nominals

Visualizing Data using t-SNE

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL