Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Baheti, Ashutosh; Ritter, Alan; Li, Jiwei; Dolan, Bill

doi:10.18653/v1/d18-1431

Cited by 75 publications

(83 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The coherence and relevance of a piece of text in a discourse is highly correlated with the perceived quality of the generated text. Previous work has approached generating coherent utterances in conversations through encouraging the model to learn similar distributed representations throughout the conversation (Baheti et al, 2018;Xu et al, 2018;Zhang et al, 2018a). In contrast, we achieve the same goal with a discriminative classifier, which is trained to contrast the true follow-up question (relevant and coherent) against randomly sampled questions (irrelevant) from other conversations and out-of-order questions (uncoherent).…”

Section: Evaluating Question Specificitymentioning

confidence: 99%

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

Zhang

Manning

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

We investigate the problem of generating informative questions in information-asymmetric conversations. Unlike previous work on question generation which largely assumes knowledge of what the answer might be, we are interested in the scenario where the questioner is not given the context from which answers are drawn, but must reason pragmatically about how to acquire new information, given the shared conversation history. We identify two core challenges: (1) formally defining the informativeness of potential questions, and (2) exploring the prohibitively large space of potential questions to find the good candidates. To generate pragmatic questions, we use reinforcement learning to optimize an informativeness metric we propose, combined with a reward function designed to promote more specific questions. We demonstrate that the resulting pragmatic questioner substantially improves the informativeness and specificity of questions generated over a baseline model, as evaluated by our metrics as well as humans.

show abstract

Section: Evaluating Question Specificitymentioning

confidence: 99%

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

Zhang

Manning

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

show abstract

“…In the dialog domain, we use an LSTM-based sequence-to-sequence (Seq2Seq) model implemented in the OpenNMT framework (Klein et al, 2017). We match the model architecture and training data of Baheti et al (2018). The Seq2Seq model has four layers each in the encoder and decoder, with hidden size 1000, and was trained on a cleaned version of OpenSubtitles (Tiedemann, 2009) to predict the next utterance given the previous one.…”

Section: Open-ended Dialog Taskmentioning

confidence: 99%

Comparison of Diverse Decoding Methods from Conditional Language Models

Ippolito

Kriz

Sedoc

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies aim to, within a givensized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that re-rank and combine candidate outputs. Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods. In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from conditional language models. We also show how diversity can be improved without sacrificing quality by oversampling additional candidates, then filtering to the desired number.

show abstract

“…Such responses understandably bore users, so there has been much research focus on generating more diverse responses (Li et al, 2016a;Xu et al, 2018;Baheti et al, 2018).…”

Section: Diverse Response Generationmentioning

confidence: 99%

Conversation Initiation by Diverse News Contents Introduction

Akasaki¹,

Kaji²

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

In our everyday chitchat , there is a conversation initiator, who proactively casts an initial utterance to start chatting. However, most existing conversation systems cannot play this role. Previous studies on conversation systems assume that the user always initiates conversation, and have placed emphasis on how to respond to the given user's utterance. As a result, existing conversation systems become passive. Namely they continue waiting until being spoken to by the users. In this paper, we consider the system as a conversation initiator and propose a novel task of generating the initial utterance in open-domain non-task-oriented conversation. Here, in order not to make users bored, it is necessary to generate diverse utterances to initiate conversation without relying on boilerplate utterances like greetings. To this end, we propose to generate initial utterance by summarizing and chatting about news articles, which provide fresh and various contents everyday. To address the lack of the training data for this task, we constructed a novel largescale dataset through crowd-sourcing. We also analyzed the dataset in detail to examine how humans initiate conversations (the dataset will be released to facilitate future research activities). We present several approaches to conversation initiation including information retrieval based and generation based models. Experimental results showed that the proposed models trained on our dataset performed reasonably well and outperformed baselines that utilize automatically collected training data in both automatic and manual evaluation. * This work was done during research internship at Yahoo Japan Corporation. 1 "Conversation" in this paper refers to open-domain nontask-oriented conversations and chitchat .

show abstract

Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Cited by 75 publications

References 35 publications

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

Comparison of Diverse Decoding Methods from Conditional Language Models

Conversation Initiation by Diverse News Contents Introduction

Contact Info

Product

Resources

About