Bowen Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bowen Yu has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Tingwen Liu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
7 shared publications - Tingwen Liu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
5 shared publications - Zhenyu Zhang
Institute of Information Engineering, Chinese Academy of Sciences
4 shared publications - Quangang Li
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
3 shared publications - Shiyao Cui
The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China
3 shared publications - Xin Cong
Department of Statistics and Data Science, Tsinghua University, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (5) , 1-32
Cross-Domain NER under a Divide-and-Transfer Paradigm
Cross-domain Named Entity Recognition (NER) transfers knowledge learned from a rich-resource source domain to improve the learning in a low-resource target domain. Most existing works are designed based on the sequence labeling framework, defining entity detection and type prediction as a monolithic process. However, they typically ignore the discrepant transferability of these two sub-tasks: the former locating spans corresponding to entities is largely domain-robust, whereas the latter owns distinct entity types across domains. Combining them into an entangled learning problem may contribute to the complexity of domain transfer. In this work, we propose the novel divide-and-transfer paradigm in which different sub-tasks are learned using separate functional modules for respective cross-domain transfer. To demonstrate the effectiveness of divide-and-transfer, we concretely implement two NER frameworks by applying this paradigm with different cross-domain transfer strategies. Experimental results on 10 different domain pairs show the notable superiority of our proposed frameworks. Experimental analyses indicate that significant advantages of the divide-and-transfer paradigm over prior monolithic ones originate from its better performance on low-resource data and a much greater transferability. It gives us a new insight into cross-domain NER. Our code is available on GitHub. 1
- 13 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (5) , 1-32
Open AccessCross-Domain NER under a Divide-and-Transfer Paradigm
Cross-domain Named Entity Recognition (NER) transfers knowledge learned from a rich-resource source domain to improve the learning in a low-resource target domain. Most existing works are designed based on the sequence labeling framework, defining entity detection and type prediction as a monolithic process. However, they typically ignore the discrepant transferability of these two sub-tasks: the former locating spans corresponding to entities is largely domain-robust, whereas the latter owns distinct entity types across domains. Combining them into an entangled learning problem may contribute to the complexity of domain transfer. In this work, we propose the novel divide-and-transfer paradigm in which different sub-tasks are learned using separate functional modules for respective cross-domain transfer. To demonstrate the effectiveness of divide-and-transfer, we concretely implement two NER frameworks by applying this paradigm with different cross-domain transfer strategies. Experimental results on 10 different domain pairs show the notable superiority of our proposed frameworks. Experimental analyses indicate that significant advantages of the divide-and-transfer paradigm over prior monolithic ones originate from its better performance on low-resource data and a much greater transferability. It gives us a new insight into cross-domain NER. Our code is available on GitHub. 1
- 30 January 2024
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 39 (1) , 227-242
Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network
- 30 January 2024
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 39 (1) , 227-242
Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1230-1240
Representation and Labeling Gap Bridging for Cross-lingual Named Entity Recognition
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1230-1240
Open AccessRepresentation and Labeling Gap Bridging for Cross-lingual Named Entity Recognition
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1683-1692
Learning Structural Co-occurrences for Structured Web Data Extraction in Low-Resource Settings
Extracting structured information from all manner of webpages is an important problem with the potential to automate many real-world applications. Recent work has shown the effectiveness of leveraging DOM trees and pre-trained language models to describe and encode webpages. However, they typically optimize the model to learn the semantic co-occurrence of elements and labels in the same webpage, thus their effectiveness depends on sufficient labeled data, which is labor-intensive. In this paper, we further observe structural co-occurrences in different webpages of the same website: the same position in the DOM tree usually plays the same semantic role, and the DOM nodes in this position also share similar surface forms. Motivated by this, we propose a novel method, Structor, to effectively incorporate the structural co-occurrences over DOM tree and surface form into pre-trained language models. Such structural co-occurrences help the model learn the task better under low-resource settings, and we study two challenging experimental scenarios: website-level low-resource setting and webpage-level low-resource setting, to evaluate our approach. Extensive experiments on the public SWDE dataset show that Structor significantly outperforms the state-of-the-art models in both settings, and even achieves three times the performance of the strong baseline model in the case of extreme lack of training data.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1683-1692
Open AccessLearning Structural Co-occurrences for Structured Web Data Extraction in Low-Resource Settings
Extracting structured information from all manner of webpages is an important problem with the potential to automate many real-world applications. Recent work has shown the effectiveness of leveraging DOM trees and pre-trained language models to describe and encode webpages. However, they typically optimize the model to learn the semantic co-occurrence of elements and labels in the same webpage, thus their effectiveness depends on sufficient labeled data, which is labor-intensive. In this paper, we further observe structural co-occurrences in different webpages of the same website: the same position in the DOM tree usually plays the same semantic role, and the DOM nodes in this position also share similar surface forms. Motivated by this, we propose a novel method, Structor, to effectively incorporate the structural co-occurrences over DOM tree and surface form into pre-trained language models. Such structural co-occurrences help the model learn the task better under low-resource settings, and we study two challenging experimental scenarios: website-level low-resource setting and webpage-level low-resource setting, to evaluate our approach. Extensive experiments on the public SWDE dataset show that Structor significantly outperforms the state-of-the-art models in both settings, and even achieves three times the performance of the strong baseline model in the case of extreme lack of training data.
- Open Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 78-86
Towards Universal Cross-Domain Recommendation
In industry, web platforms such as Alibaba and Amazon often provide diverse services for users. Unsurprisingly, some developed services are data-rich, while some newly started services are data-scarce accompanied by severe data sparsity and cold-start problems. To alleviate the above problems and incubate new services easily, cross-domain recommendation (CDR) has attracted much attention from industrial and academic researchers. Generally, CDR aims to transfer rich user-item interaction information from related source domains (e.g., developed services) to boost recommendation quality of target domains (e.g., newly started services). For different scenarios, previous CDR methods can be roughly divided into two branches: (1) Data sparsity CDR fulfills user preference aided by other domain data to make intra-domain recommendations for users with few interactions, (2) Cold-start CDR projects user preference from other domain to make inter-domain recommendations for users with none interactions. In the past years, many outstanding CDR methods are emerged, however, to the best of our knowledge, none of them attempts to solve the two branches simultaneously. In this paper, we provide a unified framework, namely UniCDR, which can universally model different CDR scenarios by transferring the domain-shared information. Extensive experiments under the above 2 branches on 4 CDR scenarios and 6 public and large-scale industrial datasets demonstrate the effectiveness and universal ability of our UniCDR.
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 78-86
Open AccessTowards Universal Cross-Domain Recommendation
In industry, web platforms such as Alibaba and Amazon often provide diverse services for users. Unsurprisingly, some developed services are data-rich, while some newly started services are data-scarce accompanied by severe data sparsity and cold-start problems. To alleviate the above problems and incubate new services easily, cross-domain recommendation (CDR) has attracted much attention from industrial and academic researchers. Generally, CDR aims to transfer rich user-item interaction information from related source domains (e.g., developed services) to boost recommendation quality of target domains (e.g., newly started services). For different scenarios, previous CDR methods can be roughly divided into two branches: (1) Data sparsity CDR fulfills user preference aided by other domain data to make intra-domain recommendations for users with few interactions, (2) Cold-start CDR projects user preference from other domain to make inter-domain recommendations for users with none interactions. In the past years, many outstanding CDR methods are emerged, however, to the best of our knowledge, none of them attempts to solve the two branches simultaneously. In this paper, we provide a unified framework, namely UniCDR, which can universally model different CDR scenarios by transferring the domain-shared information. Extensive experiments under the above 2 branches on 4 CDR scenarios and 6 public and large-scale industrial datasets demonstrate the effectiveness and universal ability of our UniCDR.
- Open Access
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identify-then-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/PA-CRF.
Open AccessFew-Shot Event Detection with Prototypical Amortized Conditional Random Field
Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identify-then-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/PA-CRF.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 35-41
FITAnnotator: A Flexible and Intelligent Text Annotation System
Yanzeng Li, Bowen Yu, Li Quangang, Tingwen Liu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 35-41
Open AccessFITAnnotator: A Flexible and Intelligent Text Annotation System
Yanzeng Li, Bowen Yu, Li Quangang, Tingwen Liu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations. 2021.
- Open Access
Coarse-to-Fine Pre-training for Named Entity Recognition
More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT. However, currentpre-training techniques focus on building lan-guage modeling objectives to learn a gen-eral representation, ignoring the named entity-related knowledge. To this end, we proposea NER-specific pre-training framework to in-ject coarse-to-fine automatically mined entityknowledge into pre-trained models. Specifi-cally, we first warm-up the model via an en-tity span identification task by training it withWikipedia anchors, which can be deemed asgeneral-typed entities. Then we leverage thegazetteer-based distant supervision strategy totrain the model extract coarse-grained typedentities. Finally, we devise a self-supervisedauxiliary task to mine the fine-grained namedentity knowledge via clustering.Empiricalstudies on three public NER datasets demon-strate that our framework achieves significantimprovements against several pre-trained base-lines, establishing the new state-of-the-art per-formance on three benchmarks. Besides, weshow that our framework gains promising re-sults without using human-labeled trainingdata, demonstrating its effectiveness in label-few and low-resource scenarios
Open AccessCoarse-to-Fine Pre-training for Named Entity Recognition
More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT. However, currentpre-training techniques focus on building lan-guage modeling objectives to learn a gen-eral representation, ignoring the named entity-related knowledge. To this end, we proposea NER-specific pre-training framework to in-ject coarse-to-fine automatically mined entityknowledge into pre-trained models. Specifi-cally, we first warm-up the model via an en-tity span identification task by training it withWikipedia anchors, which can be deemed asgeneral-typed entities. Then we leverage thegazetteer-based distant supervision strategy totrain the model extract coarse-grained typedentities. Finally, we devise a self-supervisedauxiliary task to mine the fine-grained namedentity knowledge via clustering.Empiricalstudies on three public NER datasets demon-strate that our framework achieves significantimprovements against several pre-trained base-lines, establishing the new state-of-the-art per-formance on three benchmarks. Besides, weshow that our framework gains promising re-sults without using human-labeled trainingdata, demonstrating its effectiveness in label-few and low-resource scenarios
- Open Access
Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
Event detection (ED), a key subtask of information extraction, aims to recognize instances of specific event types in text. Previous studies on the task have verified the effectiveness of integrating syntactic dependency into graph convolutional networks. However, these methods usually ignore dependency label information, which conveys rich and useful linguistic knowledge for ED. In this paper, we propose a novel architecture named Edge-Enhanced Graph Convolution Networks (EE-GCN), which simultaneously exploits syntactic structure and typed dependency label information to perform ED. Specifically, an edge-aware node update module is designed to generate expressive word representations by aggregating syntactically-connected words through specific dependency types. Furthermore, to fully explore clues hidden in dependency edges, a node-aware edge update module is introduced, which refines the relation representations with contextual information. These two modules are complementary to each other and work in a mutual promotion way. We conduct experiments on the widely used ACE2005 dataset and the results show significant improvement over competitive baseline methods.
Open AccessEdge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
Event detection (ED), a key subtask of information extraction, aims to recognize instances of specific event types in text. Previous studies on the task have verified the effectiveness of integrating syntactic dependency into graph convolutional networks. However, these methods usually ignore dependency label information, which conveys rich and useful linguistic knowledge for ED. In this paper, we propose a novel architecture named Edge-Enhanced Graph Convolution Networks (EE-GCN), which simultaneously exploits syntactic structure and typed dependency label information to perform ED. Specifically, an edge-aware node update module is designed to generate expressive word representations by aggregating syntactically-connected words through specific dependency types. Furthermore, to fully explore clues hidden in dependency edges, a node-aware edge update module is introduced, which refines the relation representations with contextual information. These two modules are complementary to each other and work in a mutual promotion way. We conduct experiments on the widely used ACE2005 dataset and the results show significant improvement over competitive baseline methods.
- 6 May 2020
- Published by Springer Nature in Lecture Notes in Computer Science
- Vol. 12084, 369-381
Strong Baselines for Author Name Disambiguation with and Without Neural Networks
Author name disambiguation (AND) is one of the most vital problems in scientometrics, which has become a great challenge with the rapid growth of academic digital libraries. Existing approaches for this task substantially rely on complex clustering-like architectures, and they usually assume the number of clusters is known beforehand or predict the number by applying another model, which involve increasingly complex and time-consuming architectures. In this paper, we combine simple neural networks with two sets of heuristic rules to explore strong baselines for the author name disambiguation problem without any priori knowledge or estimation about cluster size, which frees the model from unnecessary complexity. On a popular benchmark dataset AMiner, our solution significantly outperforms several state-of-the-art methods both in performance and efficiency, and it still achieves comparable performance with many complex models when only using a group of rules. Experimental results also indicate that gains from sophisticated deep learning techniques are quite modest in the author name disambiguation problem.
- 6 May 2020
- Published by Springer Nature in Lecture Notes in Computer Science
- Vol. 12084, 369-381
Strong Baselines for Author Name Disambiguation with and Without Neural Networks
Author name disambiguation (AND) is one of the most vital problems in scientometrics, which has become a great challenge with the rapid growth of academic digital libraries. Existing approaches for this task substantially rely on complex clustering-like architectures, and they usually assume the number of clusters is known beforehand or predict the number by applying another model, which involve increasingly complex and time-consuming architectures. In this paper, we combine simple neural networks with two sets of heuristic rules to explore strong baselines for the author name disambiguation problem without any priori knowledge or estimation about cluster size, which frees the model from unnecessary complexity. On a popular benchmark dataset AMiner, our solution significantly outperforms several state-of-the-art methods both in performance and efficiency, and it still achieves comparable performance with many complex models when only using a group of rules. Experimental results also indicate that gains from sophisticated deep learning techniques are quite modest in the author name disambiguation problem.