Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion
This addresses the challenge of handling ungrammatical and incomplete user queries in conversational QA systems, which is an incremental improvement for enhancing user interaction with knowledge graphs.
The authors tackled the problem of answering incomplete follow-up questions in conversational question answering over knowledge graphs by developing CONVEX, an unsupervised method that uses context expansion to infer missing information, and showed it outperforms state-of-the-art baselines on a new benchmark with 11,200 conversations.
Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop CONVEX: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate CONVEX, we release ConvQuestions, a crowdsourced benchmark with 11,200 distinct conversations from five different domains. We show that CONVEX: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.