paper-with-me

Papers

Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction

2020-12-01 · COLING 2020 8 · Angrosh Mandya, Danushka Bollegala, Frans Coenen

We propose a contextualised graph convolution network over multiple dependency-based sub-graphs for relation extraction. A novel method to construct multiple sub-graphs using words in shortest dependency path and words linked to entities in the dependency parse is proposed. Graph convolution operation is performed over the resulting multiple sub-graphs to obtain more informative features useful for relation extraction. Our experimental results show that the proposed method achieves superior performance over the existing GCN-based models achieving state-of-the-art performance on cross-sentence n-ary relation extraction dataset and SemEval 2010 Task 8 sentence-level relation extraction dataset. Our model also achieves a comparable performance to the SoTA on the TACRED dataset.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

RelationRelation ExtractionSentence

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

2020-11-01 · EMNLP 2020 11 · Chenhua Chen, Zhiyang Teng, Yue Zhang

Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task.…

ClassificationDependency ParsingGeneral ClassificationSentiment Analysis+1

Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis

2020-11-01 · EMNLP 2020 11 · Mi Zhang, Tieyun Qian

The state-of-the-art methods in aspect-level sentiment classification have leveraged the graph based models to incorporate the syntactic structure of a sentence. While being effective, these methods ignore the corpus lev…

RelationSentenceSentiment AnalysisSentiment Classification

Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs

2019-11-01 · WS 2019 11 · Wuti Xiong, Fei Li, Ming Cheng, Hong Yu 외

abstract In this article, we describe our approach for the Bacteria Biotopes relation extraction (BB-rel) subtask in the BioNLP Shared Task 2019. This task aims to promote the development of text mining systems that extr…

graph constructionRelationRelation ExtractionSentence

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

2017-03-14 · EMNLP 2017 9 · Diego Marcheggiani, Ivan Titov

Semantic role labeling (SRL) is the task of identifying the predicate-argument structure of a sentence. It is typically regarded as an important step in the standard NLP pipeline. As the semantic representations are clos…

Semantic Role LabelingSentence

Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction

2024-12-31 · Jiexin Wang, Yiju Guo, Bing Su

Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing rel…

Human motion predictionmotion predictionTransfer Learning