PACIFIC: Towards proactive conversational question answering over tabular and textual data in finance

• Main Authors: DENG, Yang, LEI, Wenqiang, ZHANG, Wenxuan, LAM, Wai, CHUA, Tat-Seng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Hybrid formats; Key feature; Multitask learning; Novel methods; Numerical reasoning; Proactivity; Question Answering; Subtask; Tabular data; Textual data; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/9139; https://ink.library.smu.edu.sg/context/sis_research/article/10142/viewcontent/2210.08817v2.pdf
• Institution: Singapore Management University

To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical reasoning, and (iii) hybrid context of tables and text. A new task is defined accordingly to study Proactive Conversational Question Answering (PCQA), which combines clarification question generation and CQA. In addition, we propose a novel method, namely UniPCQA, to adapt a hybrid format of input and output content in PCQA into the Seq2Seq problem, including the reformulation of the numerical reasoning process as code generation. UniPCQA performs multi-task learning over all sub-tasks in PCQA and incorporates a simple ensemble strategy to alleviate the error propagation issue in the multi-task learning by cross-validating top-k sampled Seq2Seq outputs. We benchmark the PACIFIC dataset with extensive baselines and provide comprehensive evaluations on each sub-task of PCQA.