Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network
Published 1 January 2019Open access
Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu
Citations155
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
Experiments show that the model not only outperforms the state-of-the-art (SOTA) results, but also achieves a speed that is six to fifteen times faster than that of the SOTA model.
Abstract
Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Keywords
Computer Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
UvA-DARE (University of Amsterdam)Adam: A Method for Stochastic Optimization
84,783 Citations2014Diederik P. Kingma, Jimmy Ba
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
50,318 Citations2021Mandi, Jayanta, Canoy, Rocsildes +2 more
A simple numeric simulation of DNA-co-polymerized hydrogel shape change and a genetic algorithm that generates and selects large batches of material designs that compete with one another to evolve and converge on optimal objective-matching designs are constructed.
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Dagstuhl Research Online Publication ServerDetecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
16,170 Citations2025Chen, Tianyu, Wang, Zeyu +8 more
A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
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.
arXiv (Cornell University)Graph Attention Networks
8,350 Citations2017Veli\v{c}kovi\'c, Petar, Guillem Cucurull +4 more
IEEE Transactions on Information TheoryError bounds for convolutional codes and an asymptotically optimum decoding algorithm
6,705 Citations1967Andrew J. Viterbi
The upper bound is obtained for a specific probabilistic nonsequential decoding algorithm which is shown to be asymptotically optimum for rates above R_{0} and whose performance bears certain similarities to that of sequential decoding algorithms.
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks
5,398 Citations2024Silva, Gabriel, Rodrigues, Mário +2 more
This work presents a graph neural network approach for selecting the next branching vertex, which uses a population-based genetic algorithm to evolve the model’s parameters instead and results in a speedup on 73% of the benchmark instances with a median speedup of 24%.
arXiv (Cornell University)Natural Language Processing (almost) from Scratch
5,172 Citations2011Ronan Collobert, Jason Weston +4 more
Neural Architectures for Named Entity Recognition
4,428 Citations2016Guillaume Lample, Miguel Ballesteros +3 more
Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 of juny 2016.
Natural Language Processing (almost) from Scratch
3,987 Citations2011Ronan Collobert, Jason Weston +4 more
Leibniz-Zentrum für Informatik (Schloss Dagstuhl)NER in Archival Finding Aids
3,270 Citations2021Zhiheng Huang, Wei Xu +1 more
This work has created a set of datasets to train Machine Learning algorithms to find named entities and geographical locations and tested them in several datasets and registered their precision and accuracy.
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
2,589 Citations2016Xuezhe Ma, Eduard Hovy
A novel neutral network architecture is introduced that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF, thus making it applicable to a wide range of sequence labeling tasks.
Proceedings of the AAAI Conference on Artificial IntelligenceGraph Convolutional Networks for Text Classification
1,960 Citations2019Liang Yao, Chengsheng Mao +1 more
This work builds a single text graph for a corpus based on word co-occurrence and document word relations, then learns a Text Graph Convolutional Network (Text GCN) for the corpus, which jointly learns the embeddings for both words and documents as supervised by the known class labels for documents.
A Neural Probabilistic Language Model
1,156 Citations2000Yoshua Bengio, Réjean Ducharme +1 more
International Conference on Computational LinguisticsContextual String Embeddings for Sequence Labeling
1,004 Citations2018Alan Akbik, Duncan A. J. Blythe +1 more
This paper proposes to leverage the internal states of a trained character language model to produce a novel type of word embedding which they refer to as contextual string embeddings, which are fundamentally model words as sequences of characters and are contextualized by their surrounding text.
A shortest path dependency kernel for relation extraction
971 Citations2005Răzvan Bunescu, Raymond J. Mooney
Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels.
Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
929 Citations2015Yubo Chen, Liheng Xu +3 more
A word-representation model to capture meaningful semantic regularities for words and a framework based on a convolutional neural network to capture sentence-level clues are introduced.
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
910 Citations2017Diego Marcheggiani, Ivan Titov
A version of graph convolutional networks (GCNs), a recent class of neural networks operating on graphs, suited to model syntactic dependency graphs, is proposed, observing that GCN layers are complementary to LSTM ones.
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
868 Citations2018Yuhao Zhang, Peng Qi +1 more
An extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel is proposed, and a novel pruning strategy is applied to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold.
Chinese NER Using Lattice LSTM
849 Citations2018Yue Zhang, Jie Yang
A lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon, is investigated, which outperforms both word-based and character-based L STM baselines.
Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks
610 Citations2018Zhichun Wang, Qingsong Lv +2 more
This paper proposes a novel approach for cross-lingual KG alignment via graph convolutional networks (GCNs) given a set of pre-aligned entities, and trains GCNs to embed entities of each language into a unified vector space.
Analogical Reasoning on Chinese Morphological and Semantic Relations
413 Citations2018Li Shen, Zhe Zhao +4 more
An analogical reasoning task on Chinese lexical knowledge is proposed and the influences of vector representations, context features, and corpora on analogical Reasoning are systematically explored.
Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings
403 Citations2015Nanyun Peng, Mark Dredze
A new corpus of Weibo messages annotated for both name and nominal mentions is presented and a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text is proposed.
Efficient support vector classifiers for named entity recognition
324 Citations2002Hideki Isozaki, Hideto Kazawa
It is shown that an NE recognizer based on Support Vector Machines (SVMs) gives better scores than conventional systems, but off-the-shelf SVM classifiers are too inefficient for this task.
Pooled Contextualized Embeddings for Named Entity Recognition
307 Citations2019Alan Akbik, Tanja Bergmann +1 more
This work proposes a method in which it dynamically aggregate contextualized embeddings of each unique string that the authors encounter and uses a pooling operation to distill a ”global” word representation from all contextualized instances.
Meeting of the Association for Computational LinguisticsThe Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition
299 Citations2006Gina‐Anne Levow
The Third International Chinese Language Processing Bakeoff was held in Spring 2006 to assess the state of the art in two important tasks: word segmentation and named entity recognition.
Proceedings of the AAAI Conference on Artificial IntelligenceEmpower Sequence Labeling with Task-Aware Neural Language Model
298 Citations2018Liyuan Liu, Jingbo Shang +5 more
This study develops a neural framework to extract knowledge from raw texts and empower the sequence labeling task, and leverages character-level knowledge from self-contained order information of training sequences.
Lecture notes in computer scienceCharacter-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition
288 Citations2016Chuanhai Dong, Jiajun Zhang +3 more
A bidirectional LSTM-CRF neural network that utilizes both character-level and radical-level representations for CNER is applied, and this paper is the first to use character-based BLSTm- CRF neural architecture for Cner.
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
258 Citations2019Ningyu Zhang, Shumin Deng +5 more
This work proposes to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks and integrates that relational knowledge into relation extraction model by coarse-to-fine knowledge-aware attention mechanism.
Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
224 Citations2016Nanyun Peng, Mark Dredze
It is shown that new state-of-the-art word segmentation systems use neural models to learn representations for predicting word boundaries, and these same representations, jointly trained with an NER system, yield significant improvements in NER for Chinese social media.
Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism
202 Citations2018Pengfei Cao, Yubo Chen +3 more
This paper proposes a novel adversarial transfer learning framework to make full use of task-shared boundaries information and prevent the task-specific features of CWS, and exploits self-attention to explicitly capture long range dependencies between two tokens.
Adversarial Multi-Criteria Learning for Chinese Word Segmentation
167 Citations2017Xinchi Chen, Zhan Shi +2 more
This paper proposes adversarial multi-criteria learning for CWS by integrating shared knowledge from multiple heterogeneous segmentation criteria, and shows that the performance of each corpus obtains a significant improvement, compared to single-criterion learning.
Named Entity Recognition for Question Answering
166 Citations2006Diego Mollá, Menno van Zaanen +1 more
A NER that aims at higher recall by allowing multiple entity labels to strings is presented and it is shown that the added noise produced introduced by the additional labels is offset by the higher recall gained, therefore enabling the QA system to have a better chance to find the answer.
arXiv (Cornell University)Empower Sequence Labeling with Task-Aware Neural Language Model
151 Citations2017Liyuan Liu, Jingbo Shang +5 more
arXiv (Cornell University)GMNN: Graph Markov Neural Networks
146 Citations2019Meng Qu, Yoshua Bengio +1 more
Proceedings of the AAAI Conference on Artificial IntelligenceA Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media
133 Citations2017Hangfeng He, Xu Sun
A unified model which can learn from out-of-domain corpora and in-domain unannotated texts and outperform existing methods for NER in Chinese social media is proposed.
F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
131 Citations2017Hangfeng He, Xu Sun
To bridge the gap between label accuracy and F-score of NER, a model which can be directly trained on F- score is constructed which yields 7.44% improvement over previous state-of-the-art result.
Named Entity Recognition with Bilingual Constraints
90 Citations2013Wanxiang Che, Mengqiu Wang +2 more
A method is proposed that formulates the problem of exploring signals on unannotated bilingual text as a simple Integer Linear Program, which encourages entity tags to agree via bilingual constraints and can improve strong baselines for both Chinese and English.
Better Modeling of Incomplete Annotations for Named Entity Recognition
85 Citations2019Zhanming Jie, Pengjun Xie +3 more
This work highlights several pitfalls associated with learning under such a setup in the context of NER and proposes a novel yet easy-to-implement approach for recognizing named entities with incomplete data annotations.
Meeting of the Association for Computational LinguisticsChinese Named Entity Recognition with Conditional Probabilistic Models
77 Citations2006Aitao Chen, Fuchun Peng +2 more
Two conditional probabilistic models are used for identifying names of people, places, and organizations in unsegmented Chinese texts by Yahoo team at the third International Chinese Language Processing Bakeoff.
Journal of the American Medical Informatics AssociationJoint segmentation and named entity recognition using dual decomposition in Chinese discharge summaries
74 Citations2013Yan Xu, Yining Wang +6 more
The joint model is efficient and effective in both segmentation and recognition compared with the two individual tasks, and achieves encouraging results, demonstrating the feasibility of the two tasks.
arXiv (Cornell University)CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
68 Citations2019Yuying Zhu, Guoxin Wang +1 more
Meeting of the Association for Computational LinguisticsWord Segmentation and Named Entity Recognition for SIGHAN Bakeoff3
55 Citations2006Suxiang Zhang, Ying Qin +2 more
This work takes a probabilistic feature based Maximum Entropy (ME) model as a basic frame to combine multiple sources of knowledge to improve performance of word segmentation and named entity recognition in SIGHAN Bakeoff3.
Proceedings of the AAAI Conference on Artificial IntelligenceEffective Bilingual Constraints for Semi-Supervised Learning of Named Entity Recognizers
52 Citations2013Mengqiu Wang, Wanxiang Che +1 more
This work proposes a factored probabilistic sequence model that encourages both crosslanguage and intra-document consistency and demonstrates a method that makes effective use of vast amounts of bilingual text to improve monolingual systems.
Lecture notes in computer scienceCombining Discrete and Neural Features for Sequence Labeling
48 Citations2018Jie Yang, Zhiyang Teng +2 more
The results on standard benchmarks show that state-of-the-art neural models can give accuracies comparable to the best discrete models in the literature for most tasks and combing discrete and neural features unanimously yield better results.
arXiv (Cornell University)BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
46 Citations2019Yu Cao, Meng Fang +1 more
arXiv (Cornell University)Abusive Language Detection with Graph Convolutional Networks
46 Citations2019Pushkar Mishra, Marco Del Tredici +2 more
arXiv (Cornell University)Graph Convolutional Networks for Named Entity Recognition
37 Citations2017Alberto Cetoli, Stefano Bragaglia +2 more
The role of the dependency tree in a named entity recognizer upon using a set of GCN is investigated and it is shown that the grammar of a sentence positively influences the results.
arXiv (Cornell University)Combining Discrete and Neural Features for Sequence Labeling
36 Citations2017Jie Yang, Zhiyang Teng +2 more
31 Citations2019Pushkar Mishra, Marco Del Tredici +2 more
This work works with graph convolutional networks to present the first approach that captures not only the structure of online communities but also the linguistic behavior of the users within them and significantly advances the current state of the art in abusive language detection.
30 Citations2019Yu Cao, Meng Fang +1 more
A Bi-directional Attention Entity Graph Convolutional Network (BAG) is proposed, leveraging relationships between nodes in an entity graph and attention information between a query and the entity graph to solve the multi-hop reasoning question answering task.
IEEE Transactions on Learning TechnologiesGraph Convolutional Networks for Named Entity Recognition
14 Citations2017Alberto Cetoli, Stefano Bragaglia +2 more