Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy

• URL: http://arxiv.org/abs/2109.05312v1
• Date: Sat, 11 Sep 2021 16:28:58 GMT
• Title: Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy
• Authors: Alberto Testoni and Raffaella Bernardi
• Abstract summary: State-Of-The-Art systems are shown to generate questions that, although grammatically correct, often lack an effective strategy and sound unnatural to humans. We design Confirm-it, a model based on a beam search re-ranking algorithm that guides an effective goal-oriented strategy. We show that dialogues generated by Confirm-it are more natural and effective than beam search decoding without re-ranking.
• Score: 6.02280861819024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating goal-oriented questions in Visual Dialogue tasks is a challenging and long-standing problem. State-Of-The-Art systems are shown to generate questions that, although grammatically correct, often lack an effective strategy and sound unnatural to humans. Inspired by the cognitive literature on information search and cross-situational word learning, we design Confirm-it, a model based on a beam search re-ranking algorithm that guides an effective goal-oriented strategy by asking questions that confirm the model's conjecture about the referent. We take the GuessWhat?! game as a case-study. We show that dialogues generated by Confirm-it are more natural and effective than beam search decoding without re-ranking.

Related papers

• SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning [17.125080112897102]
  SECURE is an interactive task learning framework designed to solve such problems. It uses embodied conversation to fix its deficient domain model. We demonstrate that learning to solve rearrangement under unawareness is more data efficient when the agent is semantics-aware.
  arXiv  Detail & Related papers  (2024-09-26T11:40:07Z)
• Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models [56.93074140619464]
  We propose RiC (Reasoning in Conversation), a method that focuses on solving subjective tasks through dialogue simulation. The motivation of RiC is to mine useful contextual information by simulating dialogues instead of supplying chain-of-thought style rationales. We evaluate both API-based and open-source LLMs including GPT-4, ChatGPT, and OpenChat across twelve tasks.
  arXiv  Detail & Related papers  (2024-02-27T05:37:10Z)
• Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog [83.63849872250651]
  Video-grounded dialog requires profound understanding of both dialog history and video content for accurate response generation. We present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator.
  arXiv  Detail & Related papers  (2023-10-11T07:37:13Z)
• Are Current Decoding Strategies Capable of Facing the Challenges of Visual Dialogue? [3.491999371287298]
  We compare different decoding strategies in a Visual Dialogue referential game. None of them successfully balance lexical richness, accuracy in the task, and visual grounding. We believe our findings and suggestions may serve as a starting point for designing more effective decoding algorithms.
  arXiv  Detail & Related papers  (2022-10-24T07:34:39Z)
• 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)
• Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems [109.16553492049441]
  We propose a novel method to incorporate the knowledge reasoning capability into dialogue systems in a more scalable and generalizable manner. To the best of our knowledge, this is the first work to have transformer models generate responses by reasoning over differentiable knowledge graphs.
  arXiv  Detail & Related papers  (2022-03-20T17:51:49Z)
• Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters [52.725200145600624]
  We propose KnowExpert to bypass the retrieval process by injecting prior knowledge into the pre-trained language models with lightweight adapters. Experimental results show that KnowExpert performs comparably with the retrieval-based baselines.
  arXiv  Detail & Related papers  (2021-05-13T12:33:23Z)
• Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension [49.92173751203827]
  In multi-turn dialog, utterances do not always take the full form of sentences. We propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question.
  arXiv  Detail & Related papers  (2020-12-14T10:58:01Z)

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.