.png){kind=icon}
返回
Dependency-based syntax-aware word representations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.artint.2020.103427.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Dependency syntax has been demonstrated highly useful for a number of natural language processing (NLP) tasks. Typical approaches of utilizing dependency syntax include TreeRNN and Tree-Linearization, both of which exploit explicit 1-best tree outputs from a welltrained parser as inputs. However, these approaches may suffer from error propagation due to the inevitable errors contained in the 1-best tree outputs. In this work, we propose a novel approach to integrate dependency syntax without using the discrete tree outputs. The key idea is to use the intermediate hidden representations of a welltrained encoder-decoder dependency parser, which are referred to as Dependency-based Syntax-Aware Word Representations (Dep-SAWRs). Then, we simply concatenate such DepSAWRs with the conventional context-insensitive word embeddings to compose input word representations, without requiring to modify the model architecture of the downstream tasks. We evaluate the proposed method on four kinds of typical NLP tasks, including sentence classification, sentence matching, sequence labeling and machine translation. Experimental results show that the proposed approach is highly promising. On the one hand, it can utilize dependency syntax effectively, bringing consistently better performance on the four tasks compared with baselines without using syntax. On the other hand, the proposed method can outperform the Tree-RNN and Tree-Linearization approaches in most settings, and meanwhile are highly efficient in syntax integration. In addition, the proposed method would be easily extendable to encoding other structural attributes of language. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Dependency syntax
Sentence classification
Sentence matching
Sequence labeling
Neural machine translation
Syntax integration
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
13.9
论文数:
6.1K
被引数:
1.9W
机构
引用论文
MS InterView: An elemental mass spectrometry spectral interference data base for Microsoft Windows
PREAI
分享收藏
Effect of Subcutaneous and Intraperitoneal Administration of Recombinant Human Erythropoietin on Blood Pressure and Vasoactive Hormones in Patients on Continuous Ambulatory Peritoneal Dialysis.png)
Nephron
NephronIF0
PREAI
分享收藏Distributed model predictive control of constrained nonlinear systems with communication delays
PREAI
分享收藏The Sex Determination Gene Shows No Founder Effect in the Giant Honey Bee, Apis dorsataPLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容