PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance
This work addresses conversational question answering for finance professionals by creating a dataset and method, but it is incremental as it builds on existing CQA approaches.
The authors tackled the problem of conversational question answering in finance by introducing a new dataset, PACIFIC, with proactive, numerical reasoning, and hybrid tabular-text features, and proposed UniPCQA, a method that achieved competitive results on benchmark tasks.
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.