Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present CONVINSE, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this frame-like representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines.

翻译：对话式问答（ConvQA）处理序列化信息需求，其中后续问题中的上下文被隐含地省略。当前的ConvQA系统仅基于单一信息源运行：知识库（KB）、文本语料库或表格集合。本文首次探讨联合利用所有上述信息源的问题，从而提升答案覆盖率和置信度。我们提出CONVINSE，一种用于异构源上ConvQA的端到端流水线，包含三个阶段：i) 学习输入问题及其对话上下文的显式结构化表示，ii) 利用这种框架式表示统一从知识库、文本和表格中捕获相关证据，以及iii) 运行融合解码器模型生成答案。我们构建并发布了首个面向异构源ConvQA的基准数据集ConvMix，包含3000个真实用户对话（含16000个问题），并附有实体标注、完整问题表述及问题转述。实验证明，与最先进的基线方法相比，我们的方法具有可行性和优势。