Jiaqi Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiaqi Bai has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Zhoujun Li
Beihang University, Beijing, China
11 shared publications - Jian Yang
Beihang University, Beijing, China
10 shared publications - Hongcheng Guo
School of Data Science, Fudan University
6 shared publications - Tongliang Li
Beijing Information Science and Technology University, Beijing, China
5 shared publications - Jiaheng Liu
Nanjing University, Nanjing, China
4 shared publications - Shun Zhang
Beihang University
3 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13044-13055
ReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13044-13055
Open AccessReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding
- 13 December 2024
- Published by Springer Nature
- p. 104-119
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
- 13 December 2024
- Published by Springer Nature
- p. 104-119
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
- 22 August 2024
- Published by Springer Nature
- p. 195-212
TiNID: A Transfer and Interpretable LLM-Enhanced Framework for New Intent Discovery
- 22 August 2024
- Published by Springer Nature
- p. 195-212
TiNID: A Transfer and Interpretable LLM-Enhanced Framework for New Intent Discovery
- 14 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
mt4CrossOIE: Multi-stage tuning for cross-lingual open information extraction
- 14 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
mt4CrossOIE: Multi-stage tuning for cross-lingual open information extraction
- 3 May 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 296
Infusing internalized knowledge of language models into hybrid prompts for knowledgeable dialogue generation
- 3 May 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 296
Infusing internalized knowledge of language models into hybrid prompts for knowledgeable dialogue generation
- Open Access
- 17 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 98-105
Multilingual Entity and Relation Extraction from Unified to Language-specific Training
Entity and relation extraction is a key task in information extraction, where the output can be used for downstream NLP tasks. Existing approaches for entity and relation extraction task mainly focus on the English corpora and ignore other languages. Thus, it is critical to improve performance in a multilingual setting. Meanwhile, multilingual training is usually used to boost cross-lingual performance by transferring knowledge from languages (e.g., high-resource) to other (e.g., low-resource) languages. However, language interference usually exists in multilingual tasks as the model parameters are shared among all languages. In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages. Specifically, we randomly concatenate sentences in different languages to train a Language-universal Aggregator (LA), which narrows the distance of embedding representations by obtaining the unified language representation. Then, we separate parameters to mitigate interference via tuning a Language-specific Switcher (LS), which includes several independent submodules to refine the language-specific feature representation. After that, to enhance the relational triple extraction, the sentence representations concatenated with the relation feature are used to recognize the entities. Extensive experimental results show that our method outperforms both the monolingual and multilingual baseline methods. Besides, we also perform detailed analysis to show that mERE is lightweight but effective on relational triple extraction and mERE is easy to transfer to other backbone models of multi-field tasks, which further demonstrates the effectiveness of our method.
- 17 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 98-105
Open AccessMultilingual Entity and Relation Extraction from Unified to Language-specific Training
Entity and relation extraction is a key task in information extraction, where the output can be used for downstream NLP tasks. Existing approaches for entity and relation extraction task mainly focus on the English corpora and ignore other languages. Thus, it is critical to improve performance in a multilingual setting. Meanwhile, multilingual training is usually used to boost cross-lingual performance by transferring knowledge from languages (e.g., high-resource) to other (e.g., low-resource) languages. However, language interference usually exists in multilingual tasks as the model parameters are shared among all languages. In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages. Specifically, we randomly concatenate sentences in different languages to train a Language-universal Aggregator (LA), which narrows the distance of embedding representations by obtaining the unified language representation. Then, we separate parameters to mitigate interference via tuning a Language-specific Switcher (LS), which includes several independent submodules to refine the language-specific feature representation. After that, to enhance the relational triple extraction, the sentence representations concatenated with the relation feature are used to recognize the entities. Extensive experimental results show that our method outperforms both the monolingual and multilingual baseline methods. Besides, we also perform detailed analysis to show that mERE is lightweight but effective on relational triple extraction and mERE is easy to transfer to other backbone models of multi-field tasks, which further demonstrates the effectiveness of our method.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 36-46
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 36-46
Open AccessGripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.
- 17 September 2023
- Published by Springer Nature
- p. 525-542
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
- 17 September 2023
- Published by Springer Nature
- p. 525-542
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
- Open Access
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.
Open AccessGripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.
- 14 April 2023
- Published by Springer Nature
- p. 142-158
Modeling Intra-class and Inter-class Constraints for Out-of-Domain Detection
- 14 April 2023
- Published by Springer Nature
- p. 142-158
Modeling Intra-class and Inter-class Constraints for Out-of-Domain Detection