Xiaocheng Zhang


2024

pdf
LI4: Label-Infused Iterative Information Interacting Based Fact Verification in Question-answering Dialogue
Xiaocheng Zhang | Chang Wang | Guoping Zhao | Xiaohong Su
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Fact verification constitutes a pivotal application in the effort to combat the dissemination of disinformation, a concern that has recently garnered considerable attention. However, previous studies in the field of fact verification, particularly those focused on question-answering dialogue, have exhibited limitations, such as failing to fully exploit the potential of question structures and ignoring relevant label information during the verification process. In this paper, we introduce Label-Infused Iterative Information Interacting (LI4), a novel approach designed for the task of question-answering dialogue based fact verification. LI4 consists of two meticulously designed components, namely the Iterative Information Refining and Filtering Module (IIRF) and the Fact Label Embedding Module (FLEM). The IIRF uses the Interactive Gating Mechanism to iteratively filter out the noise of question and evidence, concurrently refining the claim information. The FLEM is conceived to strengthen the understanding ability of the model towards labels by injecting label knowledge. We evaluate the performance of the proposed LI4 on HEALTHVER, FAVIQ, and COLLOQUIAL. The experimental results confirm that our LI4 model attains remarkable progress, manifesting as a new state-of-the-art performance.

2023

pdf
Exploration of multilingual prompts in document-grounded dialogue
Xiaocheng Zhang | Huang Qing | Fu Lin
Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering

Transferring DGD models from high-resource languages to low-resource languages is a meaningful but challenging task. Being able to provide multilingual responses to multilingual documents further complicates the task. This paper describes our method at DialDoc23 Shared Task (Document-Grounded Dialogue and Conversational Question Answering) for generate responses based on the most relevant passage retrieved. We divide it into three steps of retrieval, re-ranking and generation. Our methods include negative sample augmentation, prompt learning, pseudo-labeling and ensemble. On the submission page, we rank 2nd based on the sum of token-level F1, SacreBleu and Rouge-L scores used for the final evaluation, and get the total score of 210.25.