Question Rewriting for Conversational Question Answering

Vakulenko, Svitlana; Longpre, Shayne; Tu, Zhucheng; Anantha, Raviteja

doi:10.1145/3437963.3441748

Cited by 90 publications

(66 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…QR effectively modifies all follow-up questions such that they can be correctly interpreted outside of the conversational context as well. This extension to the conversational QA task proved especially useful while allowing retrieval models to incorporate conversational context (Voskarides et al, 2020;Vakulenko et al, 2020;Lin et al, 2020).…”

Section: Datasetmentioning

confidence: 99%

Open-Domain Question Answering Goes Conversational via Question Rewriting

Anantha¹,

Vakulenko²,

Tu³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web pages (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehension required for the end-to-end conversational question answering (QA) task. We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA. Our results set the first baseline for the QReCC dataset with F1 of 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.

show abstract

Section: Datasetmentioning

confidence: 99%

Open-Domain Question Answering Goes Conversational via Question Rewriting

Anantha¹,

Vakulenko²,

Tu³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many recent works attempted to conquer this task with graph-based neural architectures. Talmor and Berant (2018) and Kumar et al (2019) ( Elgohary et al, 2019;Vakulenko et al, 2020), and QA pipelines could also decompose the original complex question into multiple shorter questions to improve model performance Khot et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

Yi¹,

Li²,

Liu³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-bystep rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.

show abstract

“…1, four simplification operations are applied to obtain the conversational question (CQ4), which is context-dependent and superior to its origin one (SQ4) in terms of naturalness and conveying. The reverse process, i.e., Conversational Question Rewriting (CQR) (Elgohary et al, 2019;Voskarides et al, 2020) which rewrites CQ4 into SQ4, has been widely explored in the literature (Vakulenko et al, 2020;. Although the proposed methods for CQR can be easily adopted for CQS, they do not always generate satisfactory results as they are all trained to optimize a maximum likelihood estimation (MLE) objective, which gives equal attention to generate each question token.…”

Section: Ira Hayes Himmentioning

confidence: 99%

“…As with previous studies (Elgohary et al, 2019;Vakulenko et al, 2020;Lin et al, 2020a), we conduct experiments on the CANARD 1 (Elgohary et al, 2019) In addition, we evaluate the model performance on the CAsT 2 dataset (Dalton et al, 2019), which is built for conversational search. Different from CANARD, its context only contains questions without corresponding answers.…”

Section: Datasetsmentioning

confidence: 99%

“…CQS rewrites the retrieved self-contained questions into conversational ones by incorporating the conversational characteristics. Existing applicable methods for CQS are all MLE based Lin et al, 2020b;Vakulenko et al, 2020), which often get stuck in easily learned tokens as each token is treated equally by MLE. Instead, we propose a MLD based RISE framework to formulate CQS as a HCMDP, which is able to discriminate different tokens through explicit editing actions, so that it can learn to emphasize the conversational tokens and generate more natural and appropriate questions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

Liu¹,

Ren²,

Chen³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation based methods often get trapped in easily learned tokens as all tokens are treated equally during training. In this work, we introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. To train RISE, we devise an Iterative Reinforce Training (IRT) algorithm with a Dynamic Programming based Sampling (DPS) process to improve exploration. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods and generalizes well on unseen data.

show abstract

Question Rewriting for Conversational Question Answering

Cited by 90 publications

References 23 publications

Open-Domain Question Answering Goes Conversational via Question Rewriting

Open-Domain Question Answering Goes Conversational via Question Rewriting

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

Contact Info

Product

Resources

About