Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Erschienen in: Neural Processing Letters 4/2022

22.04.2022

TFM: A Triple Fusion Module for Integrating Lexicon Information in Chinese Named Entity Recognition

verfasst von: Haitao Liu, Jihua Song, Weiming Peng, Jingbo Sun, Xianwei Xin

Erschienen in: Neural Processing Letters | Ausgabe 4/2022

Einloggen, um Zugang zu erhalten
share
TEILEN

Abstract

Due to the characteristics of the Chinese writing system, character-based Chinese named entity recognition models ignore the word information in sentences, which harms their performance. Recently, many works try to alleviate the problem by integrating lexicon information into character-based models. These models, however, either simply concatenate word embeddings, or have complex structures which lead to low efficiency. Furthermore, word information is viewed as the only resource from lexicon, thus the value of lexicon is not fully explored. In this work, we observe another neglected information, i.e., character position in a word, which is beneficial for identifying character meanings. To fuse character, word and character position information, we modify the key-value memory network and propose a triple fusion module, termed as TFM. TFM is not limited to simple concatenation or suffers from complicated computation, compatibly working with the general sequence labeling model. Experimental evaluations show that our model has performance superiority. The F1-scores on Resume, Weibo and MSRA are 96.19%, 71.12% and 95.63% respectively.
Literatur
1.
Zurück zum Zitat Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135–146 CrossRef Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135–146 CrossRef
2.
Zurück zum Zitat Cai Q, Pan Y, Yao T, Yan C, Mei T (2018) Memory matching networks for one-shot image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4080–4088 Cai Q, Pan Y, Yao T, Yan C, Mei T (2018) Memory matching networks for one-shot image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4080–4088
3.
Zurück zum Zitat Cao P, Chen Y, Liu K, Zhao J, Liu S (2018) Adversarial transfer learning for chinese named entity recognition with self-attention mechanism. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 182–192 Cao P, Chen Y, Liu K, Zhao J, Liu S (2018) Adversarial transfer learning for chinese named entity recognition with self-attention mechanism. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 182–192
4.
Zurück zum Zitat Chang N, Zhong J, Li Q, Zhu J (2020) A mixed semantic features model for Chinese NER with characters and words. Adv Inf Retr 12035:356 Chang N, Zhong J, Li Q, Zhu J (2020) A mixed semantic features model for Chinese NER with characters and words. Adv Inf Retr 12035:356
5.
Zurück zum Zitat Chiu JP, Nichols E (2016) Named entity recognition with bidirectional LSTM-CNNS. Trans Assoc Comput Linguist 4:357–370 CrossRef Chiu JP, Nichols E (2016) Named entity recognition with bidirectional LSTM-CNNS. Trans Assoc Comput Linguist 4:357–370 CrossRef
6.
Zurück zum Zitat Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:​1810.​04805 Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:​1810.​04805
8.
Zurück zum Zitat Ding R, Xie P, Zhang X, Lu W, Li L, Si L (2019) A neural multi-digraph model for chinese ner with gazetteers. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 1462–1467 Ding R, Xie P, Zhang X, Lu W, Li L, Si L (2019) A neural multi-digraph model for chinese ner with gazetteers. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 1462–1467
9.
Zurück zum Zitat Dong C, Zhang J, Zong C, Hattori M, Di H (2016) Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. In: Natural language understanding and intelligent applications. Springer, pp 239–250 Dong C, Zhang J, Zong C, Hattori M, Di H (2016) Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. In: Natural language understanding and intelligent applications. Springer, pp 239–250
10.
Zurück zum Zitat Elhammadi S, Lakshmanan LV, Ng R, Simpson M, Huai B, Wang Z, Wang L (2020) A high precision pipeline for financial knowledge graph construction. In: Proceedings of the 28th international conference on computational linguistics, pp 967–977 Elhammadi S, Lakshmanan LV, Ng R, Simpson M, Huai B, Wang Z, Wang L (2020) A high precision pipeline for financial knowledge graph construction. In: Proceedings of the 28th international conference on computational linguistics, pp 967–977
12.
Zurück zum Zitat Gong C, Li Z, Xia Q, Chen W, Zhang M (2020) Hierarchical LSTM with char-subword-word tree-structure representation for Chinese named entity recognition. Sci China Inf Sci 63(10):1–15 CrossRef Gong C, Li Z, Xia Q, Chen W, Zhang M (2020) Hierarchical LSTM with char-subword-word tree-structure representation for Chinese named entity recognition. Sci China Inf Sci 63(10):1–15 CrossRef
13.
Zurück zum Zitat Goyal A, Gupta V, Kumar M (2021) A deep learning-based bilingual hindi and punjabi named entity recognition system using enhanced word embeddings. Knowl Based Syst, 107601 Goyal A, Gupta V, Kumar M (2021) A deep learning-based bilingual hindi and punjabi named entity recognition system using enhanced word embeddings. Knowl Based Syst, 107601
14.
Zurück zum Zitat Gui T, Ma R, Zhang Q, Zhao L, Jiang YG, Huang X (2019) CNN-based Chinese ner with lexicon rethinking. In: IJCAI, pp 4982–4988 Gui T, Ma R, Zhang Q, Zhao L, Jiang YG, Huang X (2019) CNN-based Chinese ner with lexicon rethinking. In: IJCAI, pp 4982–4988
15.
Zurück zum Zitat Gui T, Zou Y, Zhang Q, Peng M, Fu J, Wei Z, Huang XJ (2019) A lexicon-based graph neural network for Chinese NER. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 1039–1049 Gui T, Zou Y, Zhang Q, Peng M, Fu J, Wei Z, Huang XJ (2019) A lexicon-based graph neural network for Chinese NER. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 1039–1049
16.
Zurück zum Zitat Gui T, Ye J, Zhang Q, Zhou Y, Gong Y, Huang X (2020) Leveraging document-level label consistency for named entity recognition. In: IJCAI, pp 3976–3982 Gui T, Ye J, Zhang Q, Zhou Y, Gong Y, Huang X (2020) Leveraging document-level label consistency for named entity recognition. In: IJCAI, pp 3976–3982
17.
20.
Zurück zum Zitat Lafferty J, McCallum A, Pereira FC (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data Lafferty J, McCallum A, Pereira FC (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data
21.
Zurück zum Zitat Levow GA (2006) The third international chinese language processing bakeoff: Word segmentation and named entity recognition. In: Proceedings of the Fifth SIGHAN workshop on Chinese language processing, pp 108–117 Levow GA (2006) The third international chinese language processing bakeoff: Word segmentation and named entity recognition. In: Proceedings of the Fifth SIGHAN workshop on Chinese language processing, pp 108–117
24.
Zurück zum Zitat Lin BY, Lee DH, Shen M, Moreno R, Huang X, Shiralkar P, Ren X (2020) Triggerner: learning with entity triggers as explanations for named entity recognition. arXiv:​2004.​07493 Lin BY, Lee DH, Shen M, Moreno R, Huang X, Shiralkar P, Ren X (2020) Triggerner: learning with entity triggers as explanations for named entity recognition. arXiv:​2004.​07493
25.
Zurück zum Zitat Liu T, Yao JG, Lin CY (2019) Towards improving neural named entity recognition with gazetteers. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 5301–5307 Liu T, Yao JG, Lin CY (2019) Towards improving neural named entity recognition with gazetteers. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 5301–5307
26.
Zurück zum Zitat Liu W, Xu T, Xu Q, Song J, Zu Y (2019) An encoding strategy based word-character LSTM for Chinese NER. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol. 1 (Long and Short Papers), pp 2379–2389 Liu W, Xu T, Xu Q, Song J, Zu Y (2019) An encoding strategy based word-character LSTM for Chinese NER. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol. 1 (Long and Short Papers), pp 2379–2389
27.
Zurück zum Zitat Luo Y, Xiao F, Zhao H (2020) Hierarchical contextualized representation for named entity recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 8441–8448 Luo Y, Xiao F, Zhao H (2020) Hierarchical contextualized representation for named entity recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 8441–8448
29.
Zurück zum Zitat Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. arXiv:​1310.​4546 Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. arXiv:​1310.​4546
30.
31.
Zurück zum Zitat Misawa S, Taniguchi M, Miura Y, Ohkuma T (2017) Character-based bidirectional lstm-crf with words and characters for japanese named entity recognition. In: Proceedings of the first workshop on subword and character level models in NLP, pp 97–102 Misawa S, Taniguchi M, Miura Y, Ohkuma T (2017) Character-based bidirectional lstm-crf with words and characters for japanese named entity recognition. In: Proceedings of the first workshop on subword and character level models in NLP, pp 97–102
32.
Zurück zum Zitat Nie Y, Tian Y, Song Y, Ao X, Wan X (2020) Improving named entity recognition with attentive ensemble of syntactic information. arXiv:​2010.​15466 Nie Y, Tian Y, Song Y, Ao X, Wan X (2020) Improving named entity recognition with attentive ensemble of syntactic information. arXiv:​2010.​15466
33.
34.
Zurück zum Zitat Peng N, Dredze M (2016) Improving named entity recognition for Chinese social media with word segmentation representation learning. arXiv:​1603.​00786 Peng N, Dredze M (2016) Improving named entity recognition for Chinese social media with word segmentation representation learning. arXiv:​1603.​00786
36.
Zurück zum Zitat Prakash A, Zhao S, Hasan SA, Datla V, Lee K, Qadir A, Liu J, Farri O (2017) Condensed memory networks for clinical diagnostic inferencing. In: Thirty-first AAAI conference on artificial intelligence Prakash A, Zhao S, Hasan SA, Datla V, Lee K, Qadir A, Liu J, Farri O (2017) Condensed memory networks for clinical diagnostic inferencing. In: Thirty-first AAAI conference on artificial intelligence
37.
Zurück zum Zitat Sui D, Chen Y, Liu K, Zhao J, Liu S (2019) Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 3821–3831 Sui D, Chen Y, Liu K, Zhao J, Liu S (2019) Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 3821–3831
38.
Zurück zum Zitat Sun Y, Wang S, Li Y, Feng S, Chen X, Zhang H, Tian X, Zhu D, Tian H, Wu H (2019) Ernie: enhanced representation through knowledge integration. arXiv:​1904.​09223 Sun Y, Wang S, Li Y, Feng S, Chen X, Zhang H, Tian X, Zhu D, Tian H, Wu H (2019) Ernie: enhanced representation through knowledge integration. arXiv:​1904.​09223
39.
Zurück zum Zitat Tian Y, Shen W, Song Y, Xia F, He M, Li K (2020) Improving biomedical named entity recognition with syntactic information. BMC Bioinform 21(1):1–17 CrossRef Tian Y, Shen W, Song Y, Xia F, He M, Li K (2020) Improving biomedical named entity recognition with syntactic information. BMC Bioinform 21(1):1–17 CrossRef
40.
Zurück zum Zitat Tian Y, Song Y, Xia F, Zhang T, Wang Y (2020) Improving chinese word segmentation with wordhood memory networks. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 8274–8285 Tian Y, Song Y, Xia F, Zhang T, Wang Y (2020) Improving chinese word segmentation with wordhood memory networks. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 8274–8285
41.
Zurück zum Zitat Tong M, Xu B, Wang S, Cao Y, Hou L, Li J, Xie J (2020) Improving event detection via open-domain trigger knowledge. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 5887–5897 Tong M, Xu B, Wang S, Cao Y, Hou L, Li J, Xie J (2020) Improving event detection via open-domain trigger knowledge. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 5887–5897
42.
Zurück zum Zitat Tu Z, Liu Y, Shi S, Zhang T (2018) Learning to remember translation history with a continuous cache. Trans Assoc Comput Linguist 6:407–420 CrossRef Tu Z, Liu Y, Shi S, Zhang T (2018) Learning to remember translation history with a continuous cache. Trans Assoc Comput Linguist 6:407–420 CrossRef
43.
44.
Zurück zum Zitat Wu F, Liu J, Wu C, Huang Y, Xie X (2019) Neural Chinese named entity recognition via CNN-LSTM-CRF and joint training with word segmentation. In: The World Wide Web conference, pp 3342–3348 Wu F, Liu J, Wu C, Huang Y, Xie X (2019) Neural Chinese named entity recognition via CNN-LSTM-CRF and joint training with word segmentation. In: The World Wide Web conference, pp 3342–3348
45.
Zurück zum Zitat Wu J, Harris I, Zhao H (2021) Spoken language understanding for task-oriented dialogue systems with augmented memory networks. In: Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 797–806 Wu J, Harris I, Zhao H (2021) Spoken language understanding for task-oriented dialogue systems with augmented memory networks. In: Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 797–806
46.
Zurück zum Zitat Xu H, Chen Z, Wang S, Jiang X (2021) Chinese NER using Albert and multi-word information. In: ACM turing award celebration conference-China (ACM TURC 2021), pp 141–145 Xu H, Chen Z, Wang S, Jiang X (2021) Chinese NER using Albert and multi-word information. In: ACM turing award celebration conference-China (ACM TURC 2021), pp 141–145
47.
Zurück zum Zitat Yan R, Jiang X, Dang D (2021) Named entity recognition by using XLNet-BILSTM-CRF. Neural Process Lett 53:1–18 CrossRef Yan R, Jiang X, Dang D (2021) Named entity recognition by using XLNet-BILSTM-CRF. Neural Process Lett 53:1–18 CrossRef
49.
Metadaten
Titel
TFM: A Triple Fusion Module for Integrating Lexicon Information in Chinese Named Entity Recognition
verfasst von
Haitao Liu
Jihua Song
Weiming Peng
Jingbo Sun
Xianwei Xin
Publikationsdatum
22.04.2022
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 4/2022
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-022-10768-y

Weitere Artikel der Ausgabe 4/2022

Neural Processing Letters 4/2022 Zur Ausgabe