1,589 Hits in 3.5 sec

Trigger-GNN: A Trigger-Based Graph Neural Network for Nested Named Entity Recognition [article]

Yuan Sui, Fanyang Bu, Yingting Hu, Wei Yan, Liang Zhang
2022 arXiv   pre-print
Nested named entity recognition (NER) aims to identify the entity boundaries and recognize categories of the named entities in a complex hierarchical sentence.  ...  In this paper, we propose a trigger-based graph neural network (Trigger-GNN) to leverage the nested NER.  ...  INTRODUCTION Named entity recognition (nested-NER) aims to identify the entity boundaries and recognize the categories of named entities in a sentence [1] , [2] .  ... 
arXiv:2204.05518v2 fatcat:5zwqaktriffeba56wmnti36en4

Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation

Fangzhao Wu, Junxin Liu, Chuhan Wu, Yongfeng Huang, Xing Xie
2019 The World Wide Web Conference on - WWW '19  
Experiments on two benchmark datasets show that our approach can effectively improve the performance of Chinese named entity recognition, especially when training data is insufficient.  ...  Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly context-dependent.  ...  CONCLUSION In this paper we propose a neural approach for Chinese named entity recognition.  ... 
doi:10.1145/3308558.3313743 dblp:conf/www/WuLWHX19 fatcat:22gxznga7nfjre3zcisxkfouny

Multi-grained Named Entity Recognition

Congying Xia, Chenwei Zhang, Tao Yang, Yaliang Li, Nan Du, Xian Wu, Wei Fan, Fenglong Ma, Philip Yu
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be nonoverlapping or totally nested.  ...  named entities without explicitly assuming non-overlapping or totally nested structures.  ...  GPE GPE To tackle the aforementioned drawbacks, we propose a novel neural framework, named MGNER, for Multi-Grained Named Entity Recognition.  ... 
doi:10.18653/v1/p19-1138 dblp:conf/acl/XiaZYLDWFMY19 fatcat:44cyxbfn7jafvdnxmqrktuuh2y

Myanmar named entity corpus and its use in syllable-based neural named entity recognition

Hsu Myat Mo, Khin Mar Soe
2020 International Journal of Electrical and Computer Engineering (IJECE)  
This work also contributes the first evaluation of various deep neural network architectures on Myanmar Named Entity Recognition.  ...  This work also aims to discover the effectiveness of neural network approaches to textual processing for Myanmar language as well as to promote future research works on this understudied language.  ...  INTRODUCTION Named Entity Recognition (NER) is the process of automatically tagging, identifying or labeling different named entities (NE) in text in accordance with the predefined sets of NE categories  ... 
doi:10.11591/ijece.v10i2.pp1544-1551 fatcat:ijmmsb7qnrfffmzetnnlgpcb7q

BERT-Based Transfer-Learning Approach for Nested Named-Entity Recognition Using Joint Labeling

Ankit Agrawal, Sarsij Tripathi, Manu Vardhan, Vikas Sihag, Gaurav Choudhary, Nicola Dragoni
2022 Applied Sciences  
Most of the current state-of-the-art models deal with the problem of embedded/nested entity recognition with very complex neural network architectures.  ...  Two nested named-entity-recognition datasets, i.e., GENIA and GermEval 2014, were used for the experiment, with four and two levels of annotation, respectively.  ...  Source Used Approach F1-Score [13] Neural-network-based (boundary aware Bi-LSTM) 71.7 [53] Neural-network-based (feed forward, Bi-LSTM, Win-bi-LSTM) 76.12 [54] Neural-network-based (Bi-LSTM-CRF) 75.3 [  ... 
doi:10.3390/app12030976 fatcat:ics5x5znkvhuziuydjcsvbcscm

Chemlistem: chemical named entity recognition using recurrent neural networks

Peter Corbett, John Boyle
2018 Journal of Cheminformatics  
We present here several chemical named entity recognition systems.  ...  Chemical named entity recognition (NER) has traditionally been dominated by conditional random fields (CRF)-based approaches but given the success of the artificial neural network techniques known as "  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1186/s13321-018-0313-8 pmid:30523437 pmcid:PMC6755713 fatcat:2mi6zdehqfahpibaxww6mw3h6q

An Algorithm of Vocabulary Enhanced Intelligent Question Answering Based on FLAT1 [chapter]

Jing Sheng Lei, Shi Chao Ye, Sheng Ying Yang, Wei Song, Guan Mian Liang
2021 Frontiers in Artificial Intelligence and Applications  
In recent years, the lexical enhancement structure of word nodes combined with word nodes has been proved to be an effective method for Chinese named entity recognition.  ...  Among them, the entity recognition part is one of the key points.  ...  The deep neural network model has become a research trend in named entity recognition tasks because it does not require manual feature engineering and expert knowledge in related fields [4] .  ... 
doi:10.3233/faia210460 fatcat:vdhu3vyqzbhgngiuryagzof2vi

Named Entity Recognition of Traditional Chinese Medicine Patents Based on BiLSTM-CRF

Na Deng, Hao Fu, Xu Chen, Arun K. Sangaiah
2021 Wireless Communications and Mobile Computing  
In this paper, a method combining Bidirectional Long Short-Term Memory neural network with Conditional Random Field (BiLSTM-CRF) is proposed to automatically recognize entities of interest (i.e., herb  ...  Named entity recognition (NER) is a fundamental task in natural language processing and a crucial step before indepth analysis of TCM patent.  ...  Compared with the HMM model, the LSTM model uses a deeper and more complex neural network.  ... 
doi:10.1155/2021/6696205 fatcat:75gubhmcc5dsvd4mot263zllte

Context-Aware Bidirectional Neural Model for Sindhi Named Entity Recognition

Wazir Ali, Jay Kumar, Zenglin Xu, Rajesh Kumar, Yazhou Ren
2021 Applied Sciences  
Named entity recognition (NER) is a fundamental task in many natural language processing (NLP) applications, such as text summarization and semantic information retrieval.  ...  Recently, deep neural networks (NNs) with the attention mechanism yield excellent performance in NER by taking advantage of character-level and word-level representation learning.  ...  [6] proposed a neural model by incorporating the word-level and entity-level contextualized representations, entity-aware self-attention, and bidirectional transformer, which obtain state-of-the-art  ... 
doi:10.3390/app11199038 fatcat:xlkuygvsk5c2nc7knvdni3qcsq

A Survey on Recent Advances in Sequence Labeling from Deep Learning Models [article]

Zhiyong He, Zanbo Wang, Wei Wei, Shanshan Feng, Xianling Mao, Sheng Jiang
2020 arXiv   pre-print
., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc.  ...  In this paper, we aim to present a comprehensive review of existing deep learning-based sequence labeling models, which consists of three related tasks, e.g., part-of-speech tagging, named entity recognition  ...  [113] employ stacked Gated Convolutional Neural Networks(GCNN) for named entity recognition, which extend the convolutional layer with gating mechanism.  ... 
arXiv:2011.06727v1 fatcat:lbephd7kdjh6libg2v5xju7lri

Multi-Directional Heuristic Search

Dor Atzmon, Jiaoyang Li, Ariel Felner, Eliran Nachmani, Shahaf Shperberg, Nathan Sturtevant, Sven Koenig
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
MM* generalizes the Meet in the Middle (MM) bidirectional search algorithm to the case of finding an optimal meeting location for multiple agents.  ...  Traditionally, the task of extracting semantic relations between entities is decoupled into a pipeline of two separated * Corresponding Author † Corresponding Author subtasks, namely named entity recognition  ...  We use the strict evaluation: the boundary and type of extracted entities should be both correct for NER; named entities and the type of their relationships should be both correct for RE.  ... 
doi:10.24963/ijcai.2020/558 dblp:conf/ijcai/ZhaoHC020 fatcat:ijjx26naczchnj253oxqgsnphe

Bipartite Flat-Graph Network for Nested Named Entity Recognition [article]

Ying Luo, Hai Zhao
2020 arXiv   pre-print
In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outermost entities and a graph  ...  Bidirectional LSTM (BiLSTM) and graph convolutional network (GCN) are adopted to jointly learn flat entities and their inner dependencies.  ...  Nested named entity recognition requires to identity all the entities in texts that may be nested with each other.  ... 
arXiv:2005.00436v1 fatcat:rqsgcxs5jnc2zgzot2pdgwfsky

Improving Graph Convolutional Networks Based on Relation-aware Attention for End-to-End Relation Extraction

Yin Hong, Yanxia Liu, Suizhu Yang, Kaiwen Zhang, Aiqing Wen, Jianjun Hu
2020 IEEE Access  
In this paper, we present a novel end-to-end neural model based on graph convolutional networks (GCN) for jointly extracting entities and relations between them.  ...  To consider the complete interaction between entities and relations, we propose a novel relation-aware attention mechanism to obtain the relation representation between two entity spans.  ...  The pipeline method treats the task as two separate subtasks, namely named entity recognition (NER) and relation classification (RC).  ... 
doi:10.1109/access.2020.2980859 fatcat:ueeiv74fmndkpgthcofndyktta

Attention-Based LSTM with Filter Mechanism for Entity Relation Classification

Yanliang Jin, Dijia Wu, Weisi Guo
2020 Symmetry  
In this paper, we present a novel model multi-head attention long short term memory (LSTM) network with filter mechanism (MALNet) to extract the text features and classify the relation of two entities  ...  The noise caused by irrelevant words and the word distance between the tagged entities may affect the relation classification accuracy.  ...  [29] proposed a model bidirectional LSTM networks with entity-aware attention to learn more semantic features. Yan et al.  ... 
doi:10.3390/sym12101729 fatcat:6c2chaucijf75muqyllmy2ssqu

Leveraging Knowledge Bases in LSTMs for Improving Machine Reading

Bishan Yang, Tom Mitchell
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
To effectively integrate background knowledge with information from the currently processed text, our model employs an attention mechanism with a sentinel to adaptively decide whether to attend to background  ...  We propose KBLSTM, a novel neural model that leverages continuous representations of KBs to enhance the learning of recurrent neural networks for machine reading.  ...  , such as parsing (Dyer et al., 2015) , named entity recognition (Lample et al., 2016) , and semantic role labeling (Zhou and Xu, 2015) ).  ... 
doi:10.18653/v1/p17-1132 dblp:conf/acl/YangM17 fatcat:ricckwiwizgappmuwxusjpl4wm
« Previous Showing results 1 — 15 out of 1,589 results