Dialogue Management by Estimating User’s Internal State Using the Movie Recommendation Dialogue

人間と機械の間の新たなインターフェースとして知的な対話システムの実現が期待 されている.知的な対話システムは対話中の話者の内部状態を推測し,その結果に 応じて適切に応答を変更する必要がある.本研究では映画推薦対話を具体例として, 対話中の話者内部状態のモデル化とその話者内部状態を踏まえて応答を変更する対 話システムの構築に取り組む.映画推薦をドメインとした対話システムを構築し, 対話収集を行う.収集した対話データの分析に基づき,話者内部状態を話題に関す る知識の有無,話題への興味の有無,対話意欲の有無の 3つの軸でモデル化する.モ デル化した話者内部状態を収集した対話データにアノテートし,これを学習データ として話者内部状態の自動推定を行った結果,高い推定精度を達成した.また,各 話者内部状態に応じてシステムの応答を変更するルールを設計する.学習した話者 内部状態推定器を用いて各話者内部状態を判定し,対話システムの応答を変更する ことでシステム発話の自然さが向上することを対話単位での評価と発話単位での評 価の両方で確認した. キーワード:対話システム,話者内部状態,知識,興味,対話意欲

• Publication year

  2021

• Venue

  Journal of Natural Language Processing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.5715/JNLP.28.104
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills

  2020cited by this paper
• Generating Responses with a Specific Emotion in Dialog

  2019cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• Minimally Supervised Learning of Affective Events Using Discourse Relations

  2019cited by this paper
• Engagement Recognition in Spoken Dialogue via Neural Network by Aggregating Different Annotators' Models

  2018cited by this paper
• Estimating interviewee's willingness in multimodal human robot interview interaction

  2018cited by this paper
• Personalizing Dialogue Agents: I have a dog, do you have pets too?

  2018cited by this paper
• Collection of Multimodal Dialog Data and Analysis of the Result of Annotation of Users’ Interest Level

  2018cited by this paper
• Estimating User Interest from Open-Domain Dialogue

  2018cited by this paper
• Decoupled Weight Decay Regularization

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• MojiTalk: Generating Emotional Responses at Scale

  2017cited by this paper
• A Persona-Based Neural Conversation Model

  2016cited by this paper
• Native vs. non-native language fluency implications on multimodal interaction for interpersonal skills training

  2016cited by this paper
• Conversational system for information navigation based on POMDP with user focus tracking

  2015cited by this paper
• Estimating callers' levels of knowledge in call center dialogues

  2013cited by this paper
• Building a Diverse Document Leads Corpus Annotated with Semantic Relations

  2012cited by this paper
• ISO 24617-2: A semantically-based standard for dialogue annotation

  2012cited by this paper
• Dialogue act modeling for automatic tagging and recognition of conversational speech

  2000cited by this paper
• On the Theory of Scales of Measurement.

  1946cited by this paper

• Observation and Visualization of Subjectivity-based Annotation Tasks

  2022cites this paper