Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach

• URL: http://arxiv.org/abs/2305.11789v3
• Date: Tue, 30 Jan 2024 06:52:43 GMT
• Title: Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach
• Authors: Masahiro Kaneko, Graham Neubig, Naoaki Okazaki
• Abstract summary: This research aims to create a dataset and computational framework for systems that discuss and refine their predictions through dialogue. We show that the proposed system can have beneficial discussions with humans improving the accuracy by up to 25 points in the natural language inference task.
• Score: 98.13835740351932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans work together to solve common problems by having discussions, explaining, and agreeing or disagreeing with each other. Similarly, if a system can have discussions with humans when solving tasks, it can improve the system's performance and reliability. In previous research on explainability, it has only been possible for the system to make predictions and for humans to ask questions about them rather than having a mutual exchange of opinions. This research aims to create a dataset and computational framework for systems that discuss and refine their predictions through dialogue. Through experiments, we show that the proposed system can have beneficial discussions with humans improving the accuracy by up to 25 points in the natural language inference task.

Related papers

• Dialogue You Can Trust: Human and AI Perspectives on Generated Conversations [1.178527785547223]
  This study explores the comparative performance of human and AI assessments across a range of dialogue scenarios. In Experiment 1, we evaluated multi-party conversations on Coherence, Innovation, Concreteness, and Goal Contribution. In Experiment 2, we focused on dyadic dialogues and assessing Commonsense Contradiction, Incorrect Fact, and Redundancy.
  arXiv  Detail & Related papers  (2024-09-03T11:40:38Z)
• Let's Negotiate! A Survey of Negotiation Dialogue Systems [56.01648785030208]
  Negotiation is a crucial ability in human communication. Recent interest in negotiation dialogue systems aims to create intelligent agents that can assist people in resolving conflicts or reaching agreements.
  arXiv  Detail & Related papers  (2024-02-02T02:12:46Z)
• Inconsistent dialogue responses and how to recover from them [45.933921383946576]
  One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself. In this work, we study methods to assess and bolster utterance consistency of chat systems.
  arXiv  Detail & Related papers  (2024-01-18T19:46:04Z)
• Let's Negotiate! A Survey of Negotiation Dialogue Systems [50.8766991794008]
  Negotiation is one of the crucial abilities in human communication. Goal is to empower intelligent agents with such ability to efficiently help humans resolve conflicts or reach beneficial agreements.
  arXiv  Detail & Related papers  (2022-12-18T12:03:53Z)
• Helpfulness and Fairness of Task-Oriented Dialogue Systems [35.135740285082356]
  We study computational measurements of helpfulness of goal-oriented dialogue systems. We propose to use the helpfulness level of a dialogue system towards different user queries to measure the fairness of a dialogue system.
  arXiv  Detail & Related papers  (2022-05-25T07:58:38Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• Self-supervised Dialogue Learning for Spoken Conversational Question Answering [29.545937716796082]
  In spoken conversational question answering (SCQA), the answer to the corresponding question is generated by retrieving and then analyzing a fixed spoken document, including multi-part conversations. We introduce a self-supervised learning approach, including incoherence discrimination, insertion detection, and question prediction, to explicitly capture the coreference resolution and dialogue coherence. Our proposed method provides more coherent, meaningful, and appropriate responses, yielding superior performance gains compared to the original pre-trained language models.
  arXiv  Detail & Related papers  (2021-06-04T00:09:38Z)
• Modeling Voting for System Combination in Machine Translation [92.09572642019145]
  We propose an approach to modeling voting for system combination in machine translation. Our approach combines the advantages of statistical and neural methods since it can not only analyze the relations between hypotheses but also allow for end-to-end training.
  arXiv  Detail & Related papers  (2020-07-14T09:59:38Z)
• 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.