Can You Unpack That? Learning to Rewrite Questions-in-Context

By Ahmed Elgohary, Denis Peskov, Jordan L. Boyd-Graber. 2019

242 citations recorded by the source corpus.

Question answering is an AI-complete problem, but existing datasets lack key elements of language understanding such as coreference and ellipsis resolution. We consider sequential question answering: multiple questions are asked one-by-one in a conversation between a questioner and an answerer. Answering these questions is only possible through understanding the conversation history. We introduce the task of question-in-context rewriting: given the context of a conversation’s history, rewrite a context-dependent into a self-contained question with the same answer. We construct, CANARD, a dataset of 40,527 questions based on QuAC (Choi et al., 2018) and train Seq2Seq models for incorporating context into standalone questions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

AmbigQA: Answering Ambiguous Open-domain Questions (2020, background): “To the best of our knowledge, it has not been studied for resolving ambiguity; we are only aware of Elgohary et al. (2019) which use question rewriting to convert conversational questions into self-contained questions.”
Ditch the Gold Standard: Re-evaluating Conversational Question Answering (2021, methodology): “Question replacement using CANARD.”
A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering (2020, methodology): “In particular, we found that the majority of questions in CANARD test set (77% F1 = 1) can be correctly answered using only the Original questions without any question rewriting, i.e., even when the questions are ambiguous.”
Open-Domain Question Answering Goes Conversational via Question Rewriting (2020, methodology): “CANARD (Elgohary et al., 2019) provides rewrites for the conversational questions from the QuAC dataset.”
What Question Answering can Learn from Trivia Nerds (2019, background): “…focusing on identifying useful clarification questions (Rao and Daumé III), thematically linked questions (El-gohary et al., 2018) or resolving ambiguities that arise from coreference or pragmatic constraints by rewriting underspecified question strings (Elgohary et al., 2019; Min et al., 2020).”
Open-Retrieval Conversational Question Answering (2020, methodology): “It is an aggregation of three existing datasets: (1) the QuAC dataset [6] that offers information-seeking conversations, (2) the CANARD dataset [15] that consists of context-independent rewrites of QuAC questions, and (3) the Wikipedia corpus that serves as the knowledge source of answering question”
Dialog Inpainting: Turning Documents into Dialogs (2022, background): “Subsequent work address this problem by instead posing queries to a non-conversational retriever and using its answers (Roller et al., 2021; Komeili et al., 2021; Nakano et al., 2021; Thoppilan et al., 2022; Elgohary et al., 2019).”
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning (2021, methodology): “the dialogue context (Elgohary et al., 2019), and gets recently adopted to address more downstream”