Weakly-Supervised Open-Retrieval Conversational Question Answering

by   Chen Qu, et al.

Recent studies on Question Answering (QA) and Conversational QA (ConvQA) emphasize the role of retrieval: a system first retrieves evidence from a large collection and then extracts answers. This open-retrieval ConvQA setting typically assumes that each question is answerable by a single span of text within a particular passage (a span answer). The supervision signal is thus derived from whether or not the system can recover an exact match of this ground-truth answer span from the retrieved passages. This method is referred to as span-match weak supervision. However, information-seeking conversations are challenging for this span-match method since long answers, especially freeform answers, are not necessarily strict spans of any passage. Therefore, we introduce a learned weak supervision approach that can identify a paraphrased span of the known answer in a passage. Our experiments on QuAC and CoQA datasets show that the span-match weak supervisor can only handle conversations with span answers, and has less satisfactory results for freeform answers generated by people. Our method is more flexible as it can handle both span answers and freeform answers. Moreover, our method can be more powerful when combined with the span-match method which shows it is complementary to the span-match method. We also conduct in-depth analyses to show more insights on open-retrieval ConvQA under a weak supervision setting.


page 1

page 2

page 3

page 4


Latent Retrieval for Weakly Supervised Open Domain Question Answering

Recent work on open domain question answering (QA) assumes strong superv...

Open-Retrieval Conversational Question Answering

Conversational search is one of the ultimate goals of information retrie...

A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering

In recent years, conversational agents have provided a natural and conve...

Sequence Tagging for Biomedical Extractive Question Answering

Current studies in extractive question answering (EQA) have modeled sing...

Reference-based Weak Supervision for Answer Sentence Selection using Web Data

Answer sentence selection (AS2) modeling requires annotated data, i.e., ...

Rethinking the objectives of extractive question answering

This paper describes two generally applicable approaches towards the sig...

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Many question answering (QA) tasks only provide weak supervision for how...