CASA: Conversational Aspect Sentiment Analysis for Dialogue Understanding

Dialogue understanding has always been a bottleneck for many conversational tasks, such as dialogue response generation and conversational question answering. To expedite the progress in this area, we introduce the task of conversational aspect sentiment analysis (CASA) that can provide useful fine-grained sentiment information for dialogue understanding and planning. Overall, this task extends the standard aspect-based sentiment analysis to the conversational scenario with several major adaptations. To aid the training and evaluation of data-driven methods, we annotate 3,000 chit-chat dialogues (27,198 sentences) with fine-grained sentiment information, including all sentiment expressions, their polarities and the corresponding target mentions. We also annotate an out-of-domain test set of 200 dialogues for robustness evaluation. Besides, we develop multiple baselines based on either pretrained BERT or self-attention for preliminary study. Experimental results show that our BERT-based model has strong performances for both in-domain and out-of-domain datasets, and thorough analysis indicates several potential directions for further improvements.

• Publication year

  2022

• Venue

  Journal of Artificial Intelligence Research

• Publication date

  2022-02-09

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1613/jair.1.12802
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Conversational Semantic Role Labeling

  2021cited by this paper
• NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation

  2021cited by this paper
• Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction

  2021cited by this paper
• Dialogue-Based Relation Extraction

  2020cited by this paper
• Revisiting Pre-Trained Models for Chinese Natural Language Processing

  2020cited by this paper
• Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence

  2019cited by this paper
• Affect-Driven Dialog Generation

  2019cited by this paper
• DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction

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

  2019cited by this paper
• Proactive Human-Machine Conversation with Explicit Conversation Goal

  2019influential reference
• A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction

  2019cited by this paper
• Learning to Select Knowledge for Response Generation in Dialog Systems

  2019cited by this paper
• AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

  2019influential reference
• A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis

  2019cited by this paper
• BERT for Coreference Resolution: Baselines and Analysis

  2019influential reference
• Cross-Domain Generalization of Neural Constituency Parsers

  2019cited by this paper
• Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots

  2018cited by this paper
• Wizard of Wikipedia: Knowledge-Powered Conversational agents

  2018cited by this paper
• A Unified Model for Opinion Target Extraction and Target Sentiment Prediction

  2018cited by this paper
• An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss

  2018cited by this paper
• Multilingual Constituency Parsing with Self-Attention and Pre-Training

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

  2018cited by this paper
• Augmenting End-to-End Dialogue Systems With Commonsense Knowledge

  2018cited by this paper
• Recurrent Attention Network on Memory for Aspect Sentiment Analysis

  2017cited by this paper
• Attention is All you Need

  2017influential reference
• Hierarchical Recurrent Attention Network for Response Generation

  2017cited by this paper
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

  2017cited by this paper
• Adversarial Examples for Evaluating Reading Comprehension Systems

  2017cited by this paper
• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

  2017cited by this paper
• Chinese Zero Pronoun Resolution with Deep Memory Network

  2017influential reference
• Affective Neural Response Generation

  2017cited by this paper
• Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms

  2017cited by this paper
• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

  2016cited by this paper
• SemEval-2016 Task 5: Aspect Based Sentiment Analysis

  2016cited by this paper
• A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis

  2016cited by this paper
• Coherent Dialogue with Attention-Based Language Models

  2016cited by this paper
• Topic Aware Neural Response Generation

  2016cited by this paper
• SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods

  2016cited by this paper
• SQuAD: 100,000+ Questions for Machine Comprehension of Text

  2016cited by this paper
• Attention-based LSTM for Aspect-level Sentiment Classification

  2016cited by this paper
• Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

  2015cited by this paper
• A Diversity-Promoting Objective Function for Neural Conversation Models

  2015cited by this paper
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

  2015cited by this paper
• A Neural Conversational Model

  2015cited by this paper
• PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis

  2015cited by this paper
• Creating a Fine-Grained Corpus for Chinese Sentiment Analysis

  2015cited by this paper
• SemEval-2014 Task 4: Aspect Based Sentiment Analysis

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification

  2014cited by this paper
• Latent Dirichlet Allocation

  2009cited by this paper
• Targeting Sentiment Expressions through Supervised Ranking of Linguistic Configurations

  2009cited by this paper
• The Penn Chinese TreeBank: Phrase structure annotation of a large corpus

  2005cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper

• PLiTS-Net: A PLM-Conditioned Liquid Thread Network for Social Media Sentiment Analysis

  2026cites this paper
• A unified review of aspect sentiment triplet extraction methods in aspect-based sentiment analysis

  2025cites this paper
• EmoBERTa–CNN: Hybrid Deep Learning Approach Capturing Global Semantics and Local Features for Enhanced Emotion Recognition in Conversational Settings

  2025cites this paper
• Система анализа тональности текста на телугу на основе нового пассивно-агрессивного классификатора с нечетким взвешиванием

  2024cites this paper
• Hierarchical graph fusion network and a new argumentative dataset for multiparty dialogue discourse parsing

  2024cites this paper
• Exploring aspect-based sentiment quadruple extraction with implicit aspects, opinions, and ChatGPT: a comprehensive survey

  2024cites this paper
• ChatASU: Evoking LLM’s Reflexion to Truly Understand Aspect Sentiment in Dialogues

  2024cites this paper
• Social Orientation: A New Feature for Dialogue Analysis

  2024cites this paper
• Unveiling Sarcasm in Hindi: Cutting-Edge Deep Learning Framework for Sarcasm Detection

  2024cites this paper
• The Importance of Context for Sentiment Analysis in Dialogues

  2023cites this paper
• Aspect-based automated evaluation of dialogues

  2023cites this paper
• Domain Adaptation for Conversational Query Production with the RAG Model Feedback

  2023cites this paper
• Semantic-based Pre-training for Dialogue Understanding

  2022cites this paper
• DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

  2022cites this paper
• An opposition-based differential evolution clustering algorithm for emotional preference and migratory behavior optimization

  2022cites this paper
• RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

  2021cites this paper
• SENTIMENT ANALYSIS FRAMEWORK FOR TELUGU TEXT BASED ON NOVEL CONTRIVED PASSIVE AGGRESSIVE WITH FUZZY WEIGHTING CLASSIFIER (CPSC-FWC)

  year unknowncites this paper