Towards Unification of Discourse Annotation Frameworks

Fu, Yingxue

doi:10.18653/v1/2022.acl-srw.12

Cited by 1 publication

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose a novel RL-based method to jointly train the retriever and the style-based generator in RAST. Our method is potentially adaptable for other retrieval-augmented tasks such as document-grounded dialog systems (Feng et al, 2020;Fu, 2022).…”

Section: Introductionmentioning

confidence: 99%

Diversify Question Generation with Retrieval-Augmented Style Transfer

Gou,

Xia,

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the internal knowledge within the given passage or the semantic word space for diverse content planning. These methods, however, have not considered the potential of external knowledge for expression diversity. To bridge this gap, we propose RAST, a framework for Retrieval-Augmented Style Transfer, where the objective is to utilize the style of diverse templates for question generation. For training RAST, we develop a novel Reinforcement Learning (RL) based approach that maximizes a weighted combination of diversity reward and consistency reward. Here, the consistency reward is computed by a Question-Answering (QA) model, whereas the diversity reward measures how much the final output mimics the retrieved template. Experimental results show that our method outperforms previous diversity-driven baselines on diversity while being comparable in terms of consistency scores. Our code is available at https://github.com/gouqi666/RAST.

show abstract

Section: Introductionmentioning

confidence: 99%