SubmissionNumber#=%=#148
FinalPaperTitle#=%=#YNU-HPCC at SemEval-2024 Task 7: Instruction Fine-tuning Models for Numerical Understanding and Generation
ShortPaperTitle#=%=#
NumberOfPages#=%=#9
CopyrightSigned#=%=#Kaiyuan Chen
JobTitle#==#
Organization#==#
Abstract#==#This paper presents our systems for Task 7, Numeral-Aware Language Understanding and Generation of SemEval 2024. As participants of Task 7, we engaged in all subtasks and implemented corresponding systems for each subtask. All subtasks cover three aspects: Quantitative understanding (English), Reading Comprehension of the Numbers in the text (Chinese), and Numeral-Aware Headline Generation (English). Our approach explores employing instruction-tuned models (Flan-T5) or text-to-text models (T5) to accomplish the respective subtasks. We implemented the instruction fine-tuning with or without demonstrations and employed similarity-based retrieval or manual methods to construct demonstrations for each example in instruction fine-tuning. Moreover, we reformulate the model's output into a chain-of-thought format with calculation expressions to enhance its reasoning performance for reasoning subtasks. The competitive results in all subtasks demonstrate the effectiveness of our systems.
Author{1}{Firstname}#=%=#Kaiyuan
Author{1}{Lastname}#=%=#Chen
Author{1}{Username}#=%=#kaiyuanchen
Author{1}{Email}#=%=#chenkaiyuan@stu.ynu.edu.cn
Author{1}{Affiliation}#=%=#Yunnan University
Author{2}{Firstname}#=%=#Jin
Author{2}{Lastname}#=%=#Wang
Author{2}{Username}#=%=#wangjin0818
Author{2}{Email}#=%=#wangjin@ynu.edu.cn
Author{2}{Affiliation}#=%=#Yunnan University
Author{3}{Firstname}#=%=#Xuejie
Author{3}{Lastname}#=%=#Zhang
Author{3}{Username}#=%=#xjzhang
Author{3}{Email}#=%=#xjzhang@ynu.edu.cn
Author{3}{Affiliation}#=%=#Yunnan University

==========
èéáğö