AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We try baselines that use direct summation to leverage the semantic information carried by the similar words, where the embeddings of the words are directly summed without weighting through attentions

Named Entity Recognition for Social Media Texts with Semantic Augmentation

EMNLP 2020, pp.1383-1391, (2020)

Cited by: 0|Views234
Full Text
Bibtex
Weibo

Abstract

Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts, especially user-generated social media content. Semantic augmentation is a potential way to alleviate this problem. Given that rich semantic information is implicitly preserved in pre-trained word embeddings, the...More

Code:

Data:

0
Introduction
  • The increasing popularity of microblogs results in a large amount of user-generated data, in which texts are usually short and informal.
  • The augmentation module use an attention mechanism to weight the semantic information carried by the extracted words.
Highlights
  • The increasing popularity of microblogs results in a large amount of user-generated data, in which texts are usually short and informal
  • We propose semantic augmentation mechanism for social media named entity recognition (NER) by enhancing the representation of each token in the input sentence with the most similar words in their semantic space, which can be measured by pre-trained embeddings
  • We try baselines that use direct summation (DS) to leverage the semantic information carried by the similar words, where the embeddings of the words are directly summed without weighting through attentions
  • Compared to the baseline without semantic augmentation (ID=1), models using direct summation (DS, ID=2) to incorporate different semantic information undermines NER performance on two of three datasets, namely, W17 and WB; on the contrary, the models using the proposed attentive semantic augmentation module (AU, ID=4) consistently outperform the baselines (ID=1 and ID=2) on all datasets. It indicates that AU could distinguish the contributions of different semantic information carried by different words in the given context and leverage them to improve NER performance
  • Comparing the results of models with and without the gate module (GA) (i.e. ID=3 vs. ID=2 and ID=5 vs. ID=4), we find that the models with gate module achieves superior performance to the others without it. This observation suggests that the importance of the information from the context encoder and AU varies, and the proposed gate module is effective in adjusting the weights according to their contributions
  • To demonstrate how the augmented semantic infor- is suggested to encode semantic information and a mation improves NER with the attentive augmenta- gate module is applied to aggregate such information module and the gate module, we show the ex- tion to tagging process
Results
  • The authors propose semantic augmentation mechanism for social media NER by enhancing the representation of each token in the input sentence with the most similar words in their semantic space, which can be measured by pre-trained embeddings.
  • Consider that the attention and weight based approaches are demonstrated to be effective choices to selectively leverage extra information in many tasks (Kumar et al, 2018; Margatina et al, 2019; Tian et al, 2020a,d,b,c), the authors propose an attentive semantic augmentation module to weight the words according to their contributions to the task in different contexts.
  • The authors observe that the contribution of the obtained augmented semantic information to the NER task could vary in different contexts and a gate module is naturally desired to weight such information in the varying contexts.
  • To explore the effect of the proposed attentive semantic augmentation module (AU ) and the gate module (GA), the authors run different settings of the model with and without the modules.
  • The authors try baselines that use direct summation (DS) to leverage the semantic information carried by the similar words, where the embeddings of the words are directly summed without weighting through attentions.
  • This observation suggests that the importance of the information from the context encoder and AU varies, and the proposed gate module is effective in adjusting the weights according to their contributions.
  • Be that compared to previous studies, the model is effective to alleviate the data sparsity problem in social media NER with the augmentation module to encode augmented semantic information.
  • To analyze whether the approach with attentive semantic augmentation (AU ) and the gate module (GA) can address this problem, the authors report the recall of the approach (i.e., “+AU +GA”) to recognize the unseen NEs on the test set of all datasets in Table 4.
Conclusion
  • It is clearly observed that the approach outperforms the baseline and previous the model with the gate module can distinguish that the information from semantic augmentation is more important and make correct prediction.
  • Experiments conducted on tracted augmented information for the word “Chris” three benchmark datasets in English and Chinese and visualize the weights for each augmented term show that the model outperforms previous studies in Figure 3, where deeper color refers to higher and achieves the new state-of-the-art result.
Tables
  • Table1: The statistics of all benchmark datasets w.r.t. the number of sentences (# Sent.), named entities (# Ent.) and the percentage of unseen entities (% Uns.)
  • Table2: F 1 scores of the baseline model and ours enhanced with semantic augmentation (“SE”) and the gate module (“GA”) on the development (a) and test (b) sets. “DS” and “AU ” represent the direct summation and attentive augmentation module, respectively. Y and N denote the use and non-use of corresponding modules
  • Table3: Comparison of F 1 scores of our best performing model (the full model with augmentation module and gate module) with that reported in previous studies on all English and Chinese social media datasets
  • Table4: The recall of our models with and without the attentive semantic augmentation (AU ) and the gate module (GA) on unseen named entities (whose numbers are also reported at the first row) on all three datasets. The results of our runs of previous models (marked with “∗”) are also reported for references
  • Table5: Experimental results (F 1 scores) of our approach with semantic augmentation (AU ) and gate module (GA) on all datasets, where only one type of embeddings is used in the embedding layer to represent the input sentence. The results of their corresponding baseline without AU and GA are also reported
  • Table6: Experimental results (F 1 scores) of our model with AU and GA on the WB dataset, where BERT or ZEN is used as one of the two types of embeddings (the other one is Tencent Embedding) to represent the input sentence for the embedding layer
  • Table7: Experimental results (F 1 scores) of our best performing models (i.e., the ones with AU and GA) using different types of pre-trained embeddings as the source to extract similar words. The results of baseline (the one without AU and GA) are also reported
  • Table8: All values of different hyper-parameters as well as the best one used in our experiments
Download tables as Excel
Funding
  • The model that achieves the best performance on the development set is evaluated on the test set with the F 1 scores obtained from the official conlleval toolkits7
Study subjects and analysis
benchmark datasets: 3
In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively. Extensive experiments are performed on three benchmark datasets collected from English and Chinese social media platforms, where the results demonstrate the superiority of our approach to previous studies across all three datasets. Methods in Natural Language

Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pages 3860– 3870.

Jungo Kasai, Dan Friedman, Robert Frank, Dragomir R

benchmark datasets: 3
In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively. Extensive experiments are performed on three benchmark datasets collected from English and Chinese social media platforms, where the results demonstrate the superiority of our approach to previous studies across all three datasets. The increasing popularity of microblogs results in a large amount of user-generated data, in which texts are usually short and informal

benchmark datasets: 3
To further improve NER performance, we also attempt multiple types of pre-trained word embeddings for feature extraction, which has been demonstrated to be effective in previous studies (Akbik et al, 2018; Jie and Lu, 2019; Kasai et al, 2019; Kim et al, 2019; Yan et al, 2019). To evaluate our approach, we conduct experiments on three benchmark datasets, where the results show that our model outperforms the stateof-the-arts with clear advantage across all datasets. 2 The Proposed Model

social media benchmark datasets: 3
3.1 Settings. In our experiments, we use three social media benchmark datasets, including WNUT16 (W16) (Strauss et al, 2016), WNUT17 (W17) (Derczynski et al, 2017), and Weibo (WB) (Peng and Dredze, 2015), where W16 and W17 are English datasets constructed from Twitter, and WB is built from Chinese social media platform (Sina Weibo). For all three datasets, we use their original splits and report the statistics of them in Table 1 (e.g., the number of sentences (#Sent.), entities (#Ent.), and the percentage of unseen entities (%Uns.) with respect to the entities appearing in the training set)

datasets: 3
In our experiments, we use three social media benchmark datasets, including WNUT16 (W16) (Strauss et al, 2016), WNUT17 (W17) (Derczynski et al, 2017), and Weibo (WB) (Peng and Dredze, 2015), where W16 and W17 are English datasets constructed from Twitter, and WB is built from Chinese social media platform (Sina Weibo). For all three datasets, we use their original splits and report the statistics of them in Table 1 (e.g., the number of sentences (#Sent.), entities (#Ent.), and the percentage of unseen entities (%Uns.) with respect to the entities appearing in the training set). For model implementation, we follow Lample et al (2016) to use the BIOES tag schema to represent the NE labels of tokens in the input sentence

datasets: 3
This observation suggests that the importance of the information from the context encoder and AU varies, and the proposed gate module is effective in adjusting the weights according to their contributions. Moreover, we compare our model under the best setting with previous models on all three datasets in Table 3, where our model outperforms others on all datasets. We believe that the new state-of-theconll2000/chunking/conlleval.txt

benchmark datasets: 3
To demonstrate how the augmented semantic infor- is suggested to encode semantic information and a mation improves NER with the attentive augmenta- gate module is applied to aggregate such information module and the gate module, we show the ex- tion to tagging process. Experiments conducted on tracted augmented information for the word “Chris” three benchmark datasets in English and Chinese and visualize the weights for each augmented term show that our model outperforms previous studies in Figure 3, where deeper color refers to higher and achieves the new state-of-the-art result.

datasets: 3
Comparison of F 1 scores of our best performing model (the full model with augmentation module and gate module) with that reported in previous studies on all English and Chinese social media datasets. The recall of our models with and without the attentive semantic augmentation (AU ) and the gate module (GA) on unseen named entities (whose numbers are also reported at the first row) on all three datasets. The results of our runs of previous models (marked with “∗”) are also reported for references. Experimental results (F 1 scores) of our approach with semantic augmentation (AU ) and gate module (GA) on all datasets, where only one type of embeddings is used in the embedding layer to represent the input sentence. The results of their corresponding baseline without AU and GA are also reported

Reference
  • Gustavo Aguilar, Suraj Maharjan, Adrian Pastor LopezMonroy, and Thamar Solorio. 2017. A Multi-task Approach for Named Entity Recognition in Social Media Data. In Proceedings of the 3rd Workshop on Noisy User-generated Text, NUT@EMNLP 2017, Copenhagen, Denmark, September 7, 2017, pages 148–153.
    Google ScholarLocate open access versionFindings
  • Alan Akbik, Tanja Bergmann, and Roland Vollgraf. 2019. Pooled Contextualized Embeddings for Named Entity Recognition. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 724–728.
    Google ScholarLocate open access versionFindings
  • Alan Akbik, Duncan Blythe, and Roland Vollgraf. 2018. Contextual String Embeddings for Sequence Labeling. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, pages 1638–1649.
    Google ScholarLocate open access versionFindings
  • Maaz Amjad, Grigori Sidorov, and Alisa Zhila. 2020. Data Augmentation using Machine Translation for Fake News Detection in the Urdu Ulanguage. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 2537–2542, Marseille, France.
    Google ScholarLocate open access versionFindings
  • Leon Derczynski, Eric Nichols, Marieke van Erp, and Nut Limsopatham. 2017. Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition. In Proceedings of the 3rd Workshop on Noisy User-generated Text, NUT@EMNLP 2017, Copenhagen, Denmark, September 7, 2017, pages 140– 147.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 4171–4186.
    Google ScholarLocate open access versionFindings
  • Shizhe Diao, Jiaxin Bai, Yan Song, Tong Zhang, and Yonggang Wang. 2019. ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations. Arxiv, abs/1911.00720.
    Findings
  • Tao Gui, Ruotian Ma, Qi Zhang, Lujun Zhao, Yu-Gang Jiang, and Xuanjing Huang. 2019. CNN-Based Chinese NER with Lexicon Rethinking. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, August 10-16, 2019, pages 4982–4988.
    Google ScholarLocate open access versionFindings
  • Zhanming Jie and Wei Lu. 201Dependency-Guided LSTM-CRF for Named Entity Recognition. In Proceedings of the 2019 Conference on Empirical
    Google ScholarLocate open access versionFindings
  • Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pages 3860– 3870.
    Google ScholarLocate open access versionFindings
  • Jungo Kasai, Dan Friedman, Robert Frank, Dragomir R. Radev, and Owen Rambow. 2019. Syntax-aware Neural Semantic Role Labeling with Supertags. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 701–709.
    Google ScholarLocate open access versionFindings
  • Seonhoon Kim, Inho Kang, and Nojun Kwak. 2019. Semantic Sentence Matching with DenselyConnected Recurrent and Co-Attentive Information. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pages 6586–6593.
    Google ScholarLocate open access versionFindings
  • Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
    Google ScholarLocate open access versionFindings
  • Abhishek Kumar, Daisuke Kawahara, and Sadao Kurohashi. 2018. Knowledge-Enriched Two-Layered Attention Network for Sentiment Analysis. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 253–258, New Orleans, Louisiana.
    Google ScholarLocate open access versionFindings
  • Varun Kumar, Hadrien Glaude, Cyprien de Lichy, and Wlliam Campbell. 2019. A Closer Look at Feature Space Data Augmentation for Few-Shot Intent Classification. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 1–10, Hong Kong, China.
    Google ScholarLocate open access versionFindings
  • Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 20Neural Architectures for Named Entity Recognition. In NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, June 12-17, 2016, pages 260–270.
    Google ScholarFindings
  • Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David McClosky. 2014. The Stanford Corenlp Natural Language Processing Toolkit. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, System Demonstrations, pages 55–60.
    Google ScholarLocate open access versionFindings
  • Katerina Margatina, Christos Baziotis, and Alexandros Potamianos. 2019. Attention-based Conditioning Methods for External Knowledge Integration. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3944– 3951, Florence, Italy.
    Google ScholarLocate open access versionFindings
  • Pedro Henrique Martins, Zita Marinho, and Andre F. T. Martins. 20Joint Learning of Named Entity Recognition and Entity Linking. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28 - August 2, 2019, Volume 2: Student Research Workshop, pages 190–196.
    Google ScholarLocate open access versionFindings
  • Yuxian Meng, Wei Wu, Fei Wang, Xiaoya Li, Ping Nie, Fan Yin, Muyu Li, Qinghong Han, Xiaofei Sun, and Jiwei Li. 2019. Glyce: Glyph-vectors for Chinese Character Representations. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada, pages 2742–2753.
    Google ScholarLocate open access versionFindings
  • Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings.
    Google ScholarLocate open access versionFindings
  • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Lixin Su, and Xueqi Cheng. 2019. HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pages 6875–6882.
    Google ScholarLocate open access versionFindings
  • Nanyun Peng and Mark Dredze. 2015. Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 548–554.
    Google ScholarLocate open access versionFindings
  • Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1532–1543.
    Google ScholarLocate open access versionFindings
  • Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep Contextualized Word Representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 2227–2237.
    Google ScholarLocate open access versionFindings
  • Alan Ritter, Sam Clark, Mausam, and Oren Etzioni. 2011. Named Entity Recognition in Tweets: An Experimental Study. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, 27-31 July 2011, John McIntyre Conference Centre, Edinburgh, UK, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1524–1534.
    Google ScholarLocate open access versionFindings
  • Damien Sileo, Tim Van De Cruys, Camille Pradel, and Philippe Muller. 2019. Mining Discourse Markers for Unsupervised Sentence Representation Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3477– 3486, Minneapolis, Minnesota.
    Google ScholarLocate open access versionFindings
  • Yan Song, Chia-Jung Lee, and Fei Xia. 2017. Learning Word Representations with Regularization from Prior Knowledge. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 143–152.
    Google ScholarLocate open access versionFindings
  • Yan Song, Shuming Shi, and Jing Li. 2018a. Joint Learning Embeddings for Chinese Words and their Components via Ladder Structured Networks. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI18, pages 4375–4381.
    Google ScholarLocate open access versionFindings
  • Yan Song, Shuming Shi, Jing Li, and Haisong Zhang. 2018b. Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pages 175– 180.
    Google ScholarLocate open access versionFindings
  • Yan Song and Fei Xia. 2013. A Common Case of Jekyll and Hyde: The Synergistic Effect of Using Divided Source Training Data for Feature Augmentation. In Proceedings of the Sixth International Joint Conference on Natural Language Processing, pages 623–631, Nagoya, Japan.
    Google ScholarLocate open access versionFindings
  • Benjamin Strauss, Bethany Toma, Alan Ritter, MarieCatherine de Marneffe, and Wei Xu. 2016. Results of the WNUT16 Named Entity Recognition Shared Task. In Proceedings of the 2nd Workshop on Noisy User-generated Text, NUT@COLING 2016, Osaka, Japan, December 11, 2016, pages 138–144.
    Google ScholarLocate open access versionFindings
  • Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, and Shengping Liu. 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 2019, Hong Kong, China, November 3-7, 2019, pages 3828–3838.
    Google ScholarLocate open access versionFindings
  • Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, and Yonggang Wang. 2020a. Joint Chinese Word Segmentation and Partof-speech Tagging via Two-way Attentions of Autoanalyzed Knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8286–8296, Online.
    Google ScholarLocate open access versionFindings
  • Yuanhe Tian, Yan Song, and Fei Xia. 2020b. Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • Yuanhe Tian, Yan Song, Fei Xia, and Tong Zhang. 2020c. Improving Constituency Parsing with Span Attention. In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang, and Yonggang Wang. 2020d. Improving Chinese Word Segmentation with Wordhood Memory Networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8274–8285.
    Google ScholarLocate open access versionFindings
  • Canwen Xu, Feiyang Wang, Jialong Han, and Chenliang Li. 2019. Exploiting Multiple Embeddings for Chinese Named Entity Recognition. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, November 3-7, 2019, pages 2269– 2272.
    Google ScholarLocate open access versionFindings
  • Hang Yan, Bocao Deng, Xiaonan Li, and Xipeng Qiu. 2019. TENER: Adapting Transformer Encoder for Named Entity Recognition. arXiv, abs/1911.04474.
    Findings
  • Yue Zhang and Jie Yang. 2018. Chinese NER Using Lattice LSTM. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 1520, 2018, Volume 1: Long Papers, pages 1554–1564.
    Google ScholarLocate open access versionFindings
  • Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, and Kenneth Kwok. 2019. Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 3461–3471.
    Google ScholarLocate open access versionFindings
  • Yuying Zhu and Guoxin Wang. 2019. CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 3384–3393.
    Google ScholarLocate open access versionFindings
Author
Yuyang Nie
Yuyang Nie
Yuanhe Tian
Yuanhe Tian
Xiang Wan
Xiang Wan
Bo Dai
Bo Dai
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科