CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning
Proceedings of the AAAI Conference on Artificial IntelligencePublished 3 April 2020Open access
Daojian Zeng, Ranran Haoran Zhang, Qianying Liu
Citations199
SJR score0.13
SNIP0.00
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A detailed analysis of the reasons behind the inaccurate entity extraction problem is given, and a simple but extremely effective model structure is proposed to solve this problem, called CopyMTL, to allow the model to predict multi-token entities.
Abstract
Joint extraction of entities and relations has received significant attention due to its potential of providing higher performance for both tasks. Among existing methods, CopyRE is effective and novel, which uses a sequence-to-sequence framework and copy mechanism to directly generate the relation triplets. However, it suffers from two fatal problems. The model is extremely weak at differing the head and tail entity, resulting in inaccurate entity extraction. It also cannot predict multi-token entities (e.g. Steven Jobs). To address these problems, we give a detailed analysis of the reasons behind the inaccurate entity extraction problem, and then propose a simple but extremely effective model structure to solve this problem. In addition, we propose a multi-task learning framework equipped with copy mechanism, called CopyMTL, to allow the model to predict multi-token entities. Experiments reveal the problems of CopyRE and show that our model achieves significant improvement over the current state-of-the-art method by 9% in NYT and 16% in WebNLG (F1 score). Our code is available at https://github.com/WindChimeRan/CopyMTL
Keywords
Computer ScienceDecision Sciences
UvA-DARE (University of Amsterdam)Adam: A Method for Stochastic Optimization
84,783 Citations2014Diederik P. Kingma, Jimmy Ba
arXiv (Cornell University)Sequence to Sequence Learning with Neural Networks
13,362 Citations2014Ilya Sutskever, Oriol Vinyals +1 more
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
IEEE Transactions on Signal ProcessingBidirectional recurrent neural networks
10,022 Citations1997Mike Schuster, Kuldip K. Paliwal
It is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution.
Distant supervision for relation extraction without labeled data
2,913 Citations2009Mike D. Mintz, Steven Bills +2 more
This work investigates an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size.
Lingvisticae InvestigationesA survey of named entity recognition and classification
2,488 Citations2007David R. Nadeau, Satoshi Sekine
Observations about languages, named entity types, domains and textual genres studied in the literature, along with other critical aspects of NERC such as features and evaluation methods, are reported.
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
1,422 Citations2016Jiatao Gu, Zhengdong Lu +2 more
This paper incorporates copying into neural network-based Seq2Seq learning and proposes a new model called CopyNet with encoder-decoder structure which can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
Relation Classification via Convolutional Deep Neural Network
1,412 Citations2014Daojian Zeng, Kang Liu +3 more
This paper exploits a convolutional deep neural network (DNN) to extract lexical and sentence level features from the output of pre-existing natural language processing systems and significantly outperforms the state-of-the-art methods.
Lecture notes in computer scienceModeling Relations and Their Mentions without Labeled Text
1,331 Citations2010Sebastian Riedel, Limin Yao +1 more
A novel approach to distant supervision that can alleviate the problem of noisy patterns that hurt precision by using a factor graph and applying constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in the authors' training KB.
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
1,253 Citations2016Makoto Miwa, Mohit Bansal
A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).
Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
735 Citations2017Suncong Zheng, Feng Wang +4 more
A novel tagging scheme is proposed that can convert the joint extraction task to a tagging problem, and different end-to-end models are studied to extract entities and their relations directly, without identifying entities and relations separately.
Incremental Joint Extraction of Entity Mentions and Relations
553 Citations2014Qi Li, Heng Ji
An incremental joint framework to simultaneously extract entity mentions and relations using structured perceptron with efficient beam-search is presented, which significantly outperforms a strong pipelined baseline, which attains better performance than the best-reported end-to-end system.
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism
518 Citations2018Xiangrong Zeng, Daojian Zeng +3 more
This paper proposes an end-to-end model based on sequence- to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of any of these classes, including Normal, EntityPairOverlap and SingleEntiyOverlap.
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
453 Citations2019Tsu-Jui Fu, Peng-Hsuan Li +1 more
GraphRel, an end-to-end relation extraction model which uses graph convolutional networks (GCNs) to jointly learn named entities and relations, outperforms previous work by 3.2% and 5.8% and achieves a new state-of-the-art for relation extraction.
arXiv (Cornell University)SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals
447 Citations2019Iris Hendrickx, Su‐Nam Kim +7 more
This paper defines the task, describes the training and test data and the process of their creation, lists the participating systems (10 teams, 28 runs), and discusses their results.
Modeling Joint Entity and Relation Extraction with Table Representation
388 Citations2014Makoto Miwa, Yutaka Sasaki
The experimental results demonstrate that a joint learning approach significantly outperforms a pipeline approach by incorporating global features and by selecting appropriate learning methods and search orders.
Creating Training Corpora for NLG Micro-Planners
373 Citations2017Claire Gardent, Anastasia Shimorina +2 more
This paper proposes the corpus generation framework as a novel method for creating challenging data sets from which NLG models can be learned which are capable of handling the complex interactions occurring during in micro-planning between lexicalisation, aggregation, surface realisation, referring expression generation and sentence segmentation.
Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees
281 Citations2017Arzoo Katiyar, Claire Cardie
It is shown that attention along with long short term memory (LSTM) network can extract semantic relations between entity mentions without having access to dependency trees.
arXiv (Cornell University)Incorporating Copying Mechanism in Sequence-to-Sequence Learning
258 Citations2016Jiatao Gu, Zhengdong Lu +2 more
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
235 Citations2018Pengda Qin, Weiran Xu +1 more
A deep reinforcement learning strategy is explored to generate the false-positive indicator, where it is argued that incorrectly-labeled candidate sentences must be treated with a hard decision, rather than being dealt with soft attention weights.
Bidirectional Recurrent Convolutional Neural Network for Relation Classification
225 Citations2016Rui Cai, Xiaodong Zhang +1 more
A novel model BRCNN is presented to classify the relation of two entities in a sentence by combining convolutional neural networks and twochannel recurrent neural networks with long short term memory (LSTM) units and a bidirectional architecture is proposed.
Proceedings of the AAAI Conference on Artificial IntelligenceA Hierarchical Framework for Relation Extraction with Reinforcement Learning
218 Citations2019Ryuichi Takanobu, Tianyang Zhang +2 more
This paper presents a novel paradigm to deal with relation extraction by regarding the related entities as the arguments of a relation and applies a hierarchical reinforcement learning (HRL) framework in this paradigm to enhance the interaction between entity mentions and relation types.
arXiv (Cornell University)End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
197 Citations2016Makoto Miwa, Mohit Bansal
Exploiting Syntactico-Semantic Structures for Relation Extraction
193 Citations2011Yee Seng Chan, Dan Roth
A novel algorithmic approach to RE is proposed that starts by first identifying structures and then, within these, identifying the semantic type of the relation, which provides significant improvement in RE performance.
International Conference on Computational LinguisticsTable Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction
188 Citations2016Pankaj Gupta, Hinrich Schütze +1 more
A Table Filling Multi-Task Recurrent Neural Network model that reduces the entity recognition and relation classification tasks to a table-filling problem and models their interdependencies and shows that a simple approach of piggybacking candidate entities to model the label dependencies from relations to entities improves performance.
Proceedings of the AAAI Conference on Artificial IntelligenceJoint Extraction of Entities and Overlapping Relations Using Position-Attentive Sequence Labeling
151 Citations2019Dai Dai, Xinyan Xiao +4 more
A novel unified joint extraction model which directly tags entity and relation labels according to a query word position p, i.e., detecting entity at p, and identifying entities at other positions that have relationship with the former.
arXiv (Cornell University)Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
106 Citations2017Suncong Zheng, Feng Wang +4 more
A Walk-based Model on Entity Graphs for Relation Extraction
106 Citations2018Fenia Christopoulou, Makoto Miwa +1 more
A novel graph-based neural network model for relation extraction that treats multiple pairs in a sentence simultaneously and considers interactions among them and achieves performance comparable to the state-of-the-art systems on the ACE 2005 dataset without using any external tools.