Question Rewrite Based Dialogue Response Generation

Liu, Hengrui; Rong, Wenge; Shi, Libin; Ouyang, Yuanxin; Zhang, Xiong

doi:10.1007/978-3-030-04224-0_15

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other models 19,20 treat question answering (QA) and question generation (QG) as complementary tasks and focus on jointly training for these two tasks. Most of the Question Generation work mentioned above was use in task‐driven 21 or question‐answer 22 domain. Even though they involved the generation of questions, their main design pattern still does not deviate from the user input‐result generation.…”

Section: Related Workmentioning

confidence: 99%

Question generation based on chat‐response conversion

Zhong

Peng

Liu

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary Today, thanks to the major breakthrough of sequences to sequences model in the field of natural language, most of the dialogue generation tasks are focused on generating more effective responses. However, the responses proposed by the chat‐bot are only a passive answer or assentation, which does not arouse the desire of people to continue communicating. How to transform the chat robot from a passive reply to an active questioner has become an urgent problem. In this paper, a question generalization method with four types of question proposing schemes are designed, implemented, and tested to automate question generation process. The proposed system is controlled by a probability‐triggered multiple conversion mechanism to actively propose different types of questions. We embed our methods in the mainstream dialogue generation model and demonstrate its effectiveness in dialogue response generalization on a standard dataset. In addition, it achieves good performance in subjective conversational assessment.

show abstract

Section: Related Workmentioning

confidence: 99%

Question generation based on chat‐response conversion

Zhong

Peng

Liu

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Query reformulation and paraphrase generation techniques are employed for a variety of purposes in natural language processing (NLP), such as dialogue generation (Liu et al 2018), machine translation (Madnani and Dorr 2010), and especially in question answering (QA) systems (Figueroa and Neumann 2013; Witteveen and Andrews 2019; Elgohary, Peskov, and Boyd-Graber 2019). Generating coherent and clean texts can reduce potential errors in downstream systems.…”

Section: Introductionmentioning

confidence: 99%

Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning

Chen,

Yu,

Wang

2020

Preprint

View full text Add to dashboard Cite

Query reformulation aims to alter potentially noisy or ambiguous text sequences into coherent ones closer to natural language questions. In this process, it is also crucial to maintain and even enhance performance in a downstream environments like question answering when rephrased queries are given as input. We explore methods to generate these query reformulations by training reformulators using text-to-text transformers and apply policy-based reinforcement learning algorithms to further encourage reward learning. Query fluency is numerically evaluated by the same class of model fine-tuned on a human-evaluated well-formedness dataset. The reformulator leverages linguistic knowledge obtained from transfer learning and generates more well-formed reformulations than a translation-based model in qualitative and quantitative analysis. During reinforcement learning, it better retains fluency while optimizing the RL objective to acquire question answering rewards and can generalize to out-ofsample textual data in qualitative evaluations. Our RL framework is demonstrated to be flexible, allowing reward signals to be sourced from different downstream environments such as intent classification.

show abstract

Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension

Niu

et al. 2019

Proceedings of the 2nd Workshop on Machine Reading for Question Answering

View full text Add to dashboard Cite

In conversational machine comprehension, it has become one of the research hotspots integrating conversational history information through question reformulation for obtaining better answers. However, the existing question reformulation models are trained only using supervised question labels annotated by annotators without considering any feedback information from answers. In this paper, we propose a novel Answer-Supervised Question Reformulation (ASQR) model for enhancing conversational machine comprehension with reinforcement learning technology. ASQR utilizes a pointer-copy-based question reformulation model as an agent, takes an action to predict the next word, and observes a reward for the whole sentence state after generating the end-of-sequence token. The experimental results on QuAC dataset prove that our ASQR model is more effective in conversational machine comprehension. Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.

show abstract

Question Rewrite Based Dialogue Response Generation

Cited by 3 publications

References 17 publications

Question generation based on chat‐response conversion

Question generation based on chat‐response conversion

Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning

Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension

Contact Info

Product

Resources

About