Matching The Statements: A Simple and Accurate Model for Key Point Analysis
Hoang Phan, Long Nguyen, Long Nguyen, Khanh Doan · 2021
Key Point Analysis (KPA) is one of the most essential tasks in building an Opinion Summarization system, which is capable of generating key points for a collection of arguments toward a particular topic.Furthermore, KPA allows quantifying the coverage of each summary by counting its matched arguments.With the aim of creating high-quality summaries, it is necessary to have an in-depth understanding of each individual argument as well as its universal semantic in a specified context.In this paper, we introduce a promising model, named Matching the Statements (MTS) that incorporates the discussed topic information into arguments/key points comprehension to fully understand their meanings, thus accurately performing ranking and retrieving best-match key points for an input argument.Our approach 1 has achieved the 4 th place in Track 1 of the Quantitative Summarization -Key Point Analysis Shared Task by IBM, yielding a competitive performance of 0.8956 (3 rd ) and 0.9632 (7 th ) strict and relaxed mean Average Precision, respectively.Argument Analysis Key point Analysis Matching Input argument Topic: We should end mandatory retirement Argument: Older workers have more experience and expertise than young workers.Stance: 1 (supportive) Input key points Key points: -We should let everyone retire when they are ready -A mandatory retirement age decreases institutional knowledge -A mandatory retirement age harms the economy -A mandatory retirement is not fair/discriminatory