No abstract

Question answering (QA) over text passages is a problem of longstanding interest in information retrieval. Recently, the conversational setting has attracted attention, where a user asks a sequence of questions to satisfy her information needs around a topic. While this setup is a natural one and similar to humans conversing with each other, it introduces two key research challenges: understanding the context left implicit by the user in follow-up questions, and dealing with ad hoc question formulations. In this work, we demonstrate Crown (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns. To this end, Crown first builds a word proximity network (WPN) from large corpora to store statistically significant term co-occurrences. At answering time, passages are ranked by a combination of their similarity to the question, and coherence of query terms within: these factors are measured by reading off node and edge weights from the WPN. Crown provides an interface that is both intuitive for end-users, and insightful for experts for reconfiguration to individual setups. Crown was evaluated on TREC CAsT data, where it achieved above-median performance in a pool of neural methods. CCS CONCEPTS• Information systems → Question answering.

The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp question-answer pairs found in popular benchmarks. In reality, however, such training data is hard to come by: users would rarely mark answers explicitly as correct or wrong. In this work, we take a step towards a more natural learning paradigm -from noisy and implicit feedback via question reformulations. A reformulation is likely to be triggered by an incorrect system response, whereas a new follow-up question could be a positive signal on the previous turn's answer. We present a reinforcement learning model, termed Conqer, that can learn from a conversational stream of questions and reformulations. Conqer models the answering process as multiple agents walking in parallel on the KG, where the walks are determined by actions sampled using a policy network. This policy network takes the question along with the conversational context as inputs and is trained via noisy rewards obtained from the reformulation likelihood. To evaluate Conqer, we create and release ConvRef, a benchmark with about 11 natural conversations containing around 205 reformulations. Experiments show that Conqer successfully learns from noisy rewards, significantly improving over a state-of-the-art baseline.

No abstract

No abstract