most citedxCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

7 citations · 11 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20241 cited

RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations

Shun Zhang, Chaoran Yan, Jian Yang +4

New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-la…

cs.CL2024

New Intent Discovery with Attracting and Dispersing Prototype

Shun Zhang, Jian Yang, Jiaqi Bai +4

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a featu…

cs.CL20247 cited

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

Linzheng Chai, Jian Yang, Tao Sun +8

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent…

cs.CL20232 cited

MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction

Tongliang Li, Zixiang Wang, Linzheng Chai +8

Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages. Previous work uses a shared cross-lingual pre-trained mode…

cs.CL2023

Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation

Xianjie Wu, Jian Yang, Tongliang Li +4

Incorporating external knowledge into dialogue generation (KIDG) is crucial for improving the correctness of response, where evidence fragments serve as knowledgeable snippets supp…

cs.CL20231 cited

Multilingual Entity and Relation Extraction from Unified to Language-specific Training

Zixiang Wang, Jian Yang, Tongliang Li +5

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 extractio…