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

Wu, Fangzhao; Liu, Junxin; Wu, Chuhan; Huang, Yudong; Xie, Xing

doi:10.1145/3308558.3313743

Cited by 78 publications

(27 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other hybrid approaches have also reported significantly enhanced performances of NER by combining LSTM and CNN (e.g. [29][30][31][32][33][34]). To name a few, Chiu [29] implemented CNNs to identify the character-level features and then exploited BiLSTM-based modules for sequence-labelling.…”

Section: B Dl-based Neural Network For Ner Tasksmentioning

confidence: 99%

“…For the second phase, we propose an encoder-decoder architecture for NER sequential tagger by adapting the existing model structure of "LSTM-CNNs-CRF" [40,41], as illustrated in the right half of Figure 1. This advanced model includes four layers: an embedding layer, a local context layer, a sequential semantic layer and a generative layer.…”

Section: Proposed Frameworkmentioning

confidence: 99%

“…are handled separately. To avoid above mis-interpretation, we adopt CNN-based network to distill n-gram character features following the previous works [30,31,40,44], where the potential semantic relations can be fully transmitted to the subsequent networks without any signal loss. However, the difference is that we replace the original CNN with a self-defined stacked module -"MoGCN" (Mixture of Gated Convolutional Network), which manifests a stronger fitting capability.…”

Section: B Local Contextual Layermentioning

confidence: 99%

See 2 more Smart Citations

MoGCN: Mixture of Gated Convolutional Neural Network for Named Entity Recognition of Chinese Historical Texts

Yan

Su²,

Wang³

2020

IEEE Access

View full text Add to dashboard Cite

Named Entity Recognition (NER) systems have been largely advanced by deep neural networks in the recent decade. However, the state-of-the-arts on NER have been less applied to Chinese historical texts due to the lack of standard corpora in Chinese historical domains and the difficulty of accessing a quality ancient corpus. This paper addresses the respective issues and proposes an efficient automatic processing solution for tackling NER of ancient Chinese data, including the implementation of data-driven tagging and an innovative end-to-end network namely "MoGCN" (Mixture of Gated Convolutional Neural Network). A corpus consisting of three genres of Chinese historical classics is generated by our tagging approach, which is experimented for uncovering the generalization ability of proposed model. The empirical analysis demonstrates that our proposed model achieves the best results with above 1.5% F1-score improvement over other sophisticated models in this dataset, where the experimental performance shows positive dependence on the quality of corpus. Furthermore, our model can perform much better on shorter entities especially for 2-charater ones, while many long-range entities can be only identified by our model based on our auxiliary attribute analysis. This work serves as a preliminary exploitation of NER for historical data, providing unique insights and reference values for similar tasks. Future work should be focused on more exploration about NER optimization on massive Chinese traditional texts with linguistic features and learning strategies. INDEX TERMS Named entity recognition, gated neural network, Chinese historical texts

show abstract

Section: B Dl-based Neural Network For Ner Tasksmentioning

confidence: 99%

Section: Proposed Frameworkmentioning

confidence: 99%

Section: B Local Contextual Layermentioning

confidence: 99%

See 1 more Smart Citation

MoGCN: Mixture of Gated Convolutional Neural Network for Named Entity Recognition of Chinese Historical Texts

Yan

Su²,

Wang³

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For example, the English word segmentation is generally divided into words based on spaces, while Chinese is more complicated. There is generally no obvious division mark between words, and different methods need to be selected according to different task needs [25]. A programming language is similar to natural language and can also be viewed as a sequence of English characters.…”

Section: ) Function To Tokensmentioning

confidence: 99%

Automated Data-Processing Function Identification Using Deep Neural Network

Kuang

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The number of software vulnerabilities is increasing year by year. In the era of big data, data-processing software with many users is more concerned by hackers. It is essential to improve the efficiency of discovering vulnerabilities in data-processing software. We noticed that in the process of discovering vulnerabilities, some problems of existing technology such as fuzzing, symbolic execution, and taint analysis have more or fewer relationships with data-processing functions. In fuzzing, there are two types of sanity checks toward the target program: NCC (Non-critical check) and CC (critical check). It is usually challenging to bypass such a sanity check, which leads to low code coverage during fuzzing. In symbolic execution, the constraint solver still has the problem of trying to deal with the constraints of complex algorithms. In taint analysis, the problem of over-taint and under-taint is always the key to affect the accuracy of the results. Therefore, to solve the above problems, it is necessary to identify the data-processing function. Based on identifying data-processing functions, we could identify those sanity checks, ease the solution of complex constraints, and understand the way of taints propagation to assist in software vulnerability discovery and analysis. This paper proposed a method called DPFI(data-processing function identification) for identifying data-processing functions with deep neural networks. We collected 37000 functions from GitHub and implemented the method on the data set with several neural networks, among which the performance of CNN achieved best and F 1-score was 0.90. We then applied the trained model on CGC(cyber grand challenge) data and real softwares for testing. For CGC, we got 448 functions in 20 programs, in which 35 were identified as data-processing functions. For real softwares, such as FFmpeg, 7zip, jpeg, the precision rate all reached 0.90 and F 1-score was above 0.87.

show abstract

“…However, the pipeline method suffers from error propagation, since the error of CWS may affect the performance of NER. The second one is to learn CWS and NER tasks jointly (Xu et al, 2013;Peng and Dredze, 2016;Cao et al, 2018;Wu et al, 2019). However, the joint models must rely on CWS annotation datasets, which are costly and are annotated under many diverse segmentation criteria (Chen et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

Sui

Chen

Liu

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

136

View full text Add to dashboard Cite

The lack of word boundaries information has been seen as one of the main obstacles to develop a high performance Chinese named entity recognition (NER) system. Fortunately, the automatically constructed lexicon contains rich word boundaries information and word semantic information. However, integrating lexical knowledge in Chinese NER tasks still faces challenges when it comes to self-matched lexical words as well as the nearest contextual lexical words. We present a Collaborative Graph Network to solve these challenges. Experiments on various datasets show that our model not only outperforms the stateof-the-art (SOTA) results, but also achieves a speed that is six to fifteen times faster than that of the SOTA model. 1

show abstract

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

Cited by 78 publications

References 26 publications

MoGCN: Mixture of Gated Convolutional Neural Network for Named Entity Recognition of Chinese Historical Texts

MoGCN: Mixture of Gated Convolutional Neural Network for Named Entity Recognition of Chinese Historical Texts

Automated Data-Processing Function Identification Using Deep Neural Network

Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

Contact Info

Product

Resources

About