Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Triple GNNs: Introducing Syntactic and Semantic Information for Conversational Aspect-Based Quadruple Sentiment Analysis

Binbin Li, Yuqing Li, Siyu Jia, Bingnan Ma, Yu Ding, Zisen Qi, Xingbang Tan, Menghan Guo, Shenghui Liu

TL;DR

The Triple GNNs network is introduced to enhance DiaAsQ, which employs a Graph Convolutional Network for modeling syntactic dependencies within utterances and a Dual Graph Attention Network to construct interactions between utterances.

Abstract

Conversational Aspect-Based Sentiment Analysis (DiaASQ) aims to detect quadruples \{target, aspect, opinion, sentiment polarity\} from given dialogues. In DiaASQ, elements constituting these quadruples are not necessarily confined to individual sentences but may span across multiple utterances within a dialogue. This necessitates a dual focus on both the syntactic information of individual utterances and the semantic interaction among them. However, previous studies have primarily focused on coarse-grained relationships between utterances, thus overlooking the potential benefits of detailed intra-utterance syntactic information and the granularity of inter-utterance relationships. This paper introduces the Triple GNNs network to enhance DiaAsQ. It employs a Graph Convolutional Network (GCN) for modeling syntactic dependencies within utterances and a Dual Graph Attention Network (DualGATs) to construct interactions between utterances. Experiments on two standard datasets reveal that our model significantly outperforms state-of-the-art baselines. The code is available at \url{https://github.com/nlperi2b/Triple-GNNs-}.

Triple GNNs: Introducing Syntactic and Semantic Information for Conversational Aspect-Based Quadruple Sentiment Analysis

TL;DR

The Triple GNNs network is introduced to enhance DiaAsQ, which employs a Graph Convolutional Network for modeling syntactic dependencies within utterances and a Dual Graph Attention Network to construct interactions between utterances.

Abstract

Conversational Aspect-Based Sentiment Analysis (DiaASQ) aims to detect quadruples \{target, aspect, opinion, sentiment polarity\} from given dialogues. In DiaASQ, elements constituting these quadruples are not necessarily confined to individual sentences but may span across multiple utterances within a dialogue. This necessitates a dual focus on both the syntactic information of individual utterances and the semantic interaction among them. However, previous studies have primarily focused on coarse-grained relationships between utterances, thus overlooking the potential benefits of detailed intra-utterance syntactic information and the granularity of inter-utterance relationships. This paper introduces the Triple GNNs network to enhance DiaAsQ. It employs a Graph Convolutional Network (GCN) for modeling syntactic dependencies within utterances and a Dual Graph Attention Network (DualGATs) to construct interactions between utterances. Experiments on two standard datasets reveal that our model significantly outperforms state-of-the-art baselines. The code is available at \url{https://github.com/nlperi2b/Triple-GNNs-}.
Paper Structure (23 sections, 16 equations, 2 figures, 3 tables)

This paper contains 23 sections, 16 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Aspect-based sentiment analysis
  4. Emotion Recognition in Conversation
  5. Method
  6. Task Formulation
  7. Base Encoding
  8. Single Utterance Encoding
  9. Thread Encoding
  10. Triple GNNs network
  11. Intra-Syntax GCN
  12. Inter-Semantic GATs
  13. Dialogue Quadruple Prediction
  14. Quadruple Decoding
  15. Training Loss
  16. ...and 8 more sections

Figures (2)

  • Figure 1: An illustration of a tree-like dialogue and its corresponding sentiment quadruples. Here, S1 through S4 represent the speakers of the utterances. Arrows indicate reply relations between the utterances.
  • Figure 2: The architecture of our proposed Triple GNNs, which includes four main components: the encoder, a syntactic graph convolution network (Syn-GCN), a dual graph attention network, which includes a speaker-aware GAT (Spk-GAT) and a discourse structure-aware GAT (Str-GAT), and decoding matrices.