Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models

• URL: http://arxiv.org/abs/2406.09138v1
• Date: Thu, 13 Jun 2024 14:07:52 GMT
• Title: Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models
• Authors: Sarah E. Finch, Jinho D. Choi,
• Abstract summary: Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Existing approaches to commonsense-augmented dialogue rely on implicit reasoning to integrate commonsense inferences during response generation.
• Score: 12.116834890063146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Commonsense-augmented dialogue models have been proposed that aim to infer commonsense knowledge from dialogue contexts in order to improve response quality. However, existing approaches to commonsense-augmented dialogue rely on implicit reasoning to integrate commonsense inferences during response generation. In this study, we explore the impact of explicit reasoning against implicit reasoning over commonsense for dialogue response generation. Our findings demonstrate that separating commonsense reasoning into explicit steps for generating, selecting, and integrating commonsense into responses leads to better dialogue interactions, improving naturalness, engagement, specificity, and overall quality. Subsequent analyses of these findings unveil insights into the effectiveness of various types of commonsense in generating responses and the particular response traits enhanced through explicit reasoning for commonsense integration. Our work advances research in open-domain dialogue by achieving a new state-of-the-art in commonsense-augmented response generation.

Related papers

• An Empirical Bayes Framework for Open-Domain Dialogue Generation [27.83533924583182]
  We propose an empirical bayes framework for constructing an open-domain dialogue agent by leveraging pretrained parameters. Empirical results show that BODEB achieves better results in terms of both diversity and coherence compared to variational frameworks.
  arXiv  Detail & Related papers  (2023-11-18T02:48:41Z)
• PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems [59.1250765143521]
  Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
  arXiv  Detail & Related papers  (2023-09-19T08:27:09Z)
• Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge [39.536604198392375]
  In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker's emotion. We propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection.
  arXiv  Detail & Related papers  (2023-05-24T10:25:12Z)
• EM Pre-training for Multi-party Dialogue Response Generation [86.25289241604199]
  In multi-party dialogues, the addressee of a response utterance should be specified before it is generated. We propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels.
  arXiv  Detail & Related papers  (2023-05-21T09:22:41Z)
• A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects [100.75759050696355]
  We provide a comprehensive overview of the prominent problems and advanced designs for conversational agent's proactivity in different types of dialogues. We discuss challenges that meet the real-world application needs but require a greater research focus in the future.
  arXiv  Detail & Related papers  (2023-05-04T11:38:49Z)
• Dialogue Inspectional Summarization with Factual Inconsistency Awareness [34.97845384948336]
  We investigate the factual inconsistency problem for Dialogue Inspectional Summarization (DIS) under non-pretraining and pretraining settings. An innovative end-to-end dialogue summary generation framework is proposed with two auxiliary tasks. Comprehensive experiments demonstrate that the proposed model can generate a more readable summary with accurate coverage of factual aspects.
  arXiv  Detail & Related papers  (2021-11-05T06:26:22Z)
• Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization [0.0]
  The fourth version of the system was developed within the Alexa Prize Socialbot Grand Challenge 4. For innovations regarding coherence, we propose a novel hybrid approach combining hand-designed responses and a generative model. The innovations for engagement are mostly inspired by the famous exploration-exploitation dilemma.
  arXiv  Detail & Related papers  (2021-09-16T13:24:34Z)
• Commonsense-Focused Dialogues for Response Generation: An Empirical Study [39.49727190159279]
  We present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet. We then collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting.
  arXiv  Detail & Related papers  (2021-09-14T04:32:09Z)
• Rethinking Dialogue State Tracking with Reasoning [76.0991910623001]
  This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1.
  arXiv  Detail & Related papers  (2020-05-27T02:05:33Z)
• Dialogue-Based Relation Extraction [53.2896545819799]
  We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE. We argue that speaker-related information plays a critical role in the proposed task, based on an analysis of similarities and differences between dialogue-based and traditional RE tasks. Experimental results demonstrate that a speaker-aware extension on the best-performing model leads to gains in both the standard and conversational evaluation settings.
  arXiv  Detail & Related papers  (2020-04-17T03:51:57Z)
• You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
  The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
  arXiv  Detail & Related papers  (2020-04-11T12:51:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.