Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction

Qingling Li, Wushao Wen, Jinghui Qin

TL;DR

The paper tackles Aspect Sentiment Triplet Extraction (ASTE) by addressing the limitations of purely word-level table-filling models that miss global sentence context. It introduces Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning (BTF-CCL) together with a Multi-Scale Multi-Granularity CNN (MMCNN) to align sentence- and word-level representations and capture multi-scale semantics. A boundary-based region representation with a contrastive objective and multi-scale features enables robust triplet detection and sentiment classification. Experimental results on four SemEval ASTE benchmarks show state-of-the-art F1 scores, with ablations validating the contributions of CCL and MMCNN.

Abstract

The Aspect Sentiment Triplet Extraction (ASTE) task aims to extract aspect terms, opinion terms, and their corresponding sentiment polarity from a given sentence. It remains one of the most prominent subtasks in fine-grained sentiment analysis. Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner, focusing primarily on word-level interactions while often overlooking sentence-level representations. This limitation hampers the model's ability to capture global contextual information, particularly when dealing with multi-word aspect and opinion terms in complex sentences. To address these issues, we propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations. By constructing positive and negative sample pairs, the model is forced to learn the associations at both the sentence level and the word level. Additionally, a multi-scale, multi-granularity convolutional method is proposed to capture rich semantic information better. Our approach can capture sentence-level contextual information more effectively while maintaining sensitivity to local details. Experimental results show that the proposed method achieves state-of-the-art performance on public benchmarks according to the F1 score.

Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction

TL;DR

The paper tackles Aspect Sentiment Triplet Extraction (ASTE) by addressing the limitations of purely word-level table-filling models that miss global sentence context. It introduces Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning (BTF-CCL) together with a Multi-Scale Multi-Granularity CNN (MMCNN) to align sentence- and word-level representations and capture multi-scale semantics. A boundary-based region representation with a contrastive objective and multi-scale features enables robust triplet detection and sentiment classification. Experimental results on four SemEval ASTE benchmarks show state-of-the-art F1 scores, with ablations validating the contributions of CCL and MMCNN.

Abstract

The Aspect Sentiment Triplet Extraction (ASTE) task aims to extract aspect terms, opinion terms, and their corresponding sentiment polarity from a given sentence. It remains one of the most prominent subtasks in fine-grained sentiment analysis. Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner, focusing primarily on word-level interactions while often overlooking sentence-level representations. This limitation hampers the model's ability to capture global contextual information, particularly when dealing with multi-word aspect and opinion terms in complex sentences. To address these issues, we propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations. By constructing positive and negative sample pairs, the model is forced to learn the associations at both the sentence level and the word level. Additionally, a multi-scale, multi-granularity convolutional method is proposed to capture rich semantic information better. Our approach can capture sentence-level contextual information more effectively while maintaining sensitivity to local details. Experimental results show that the proposed method achieves state-of-the-art performance on public benchmarks according to the F1 score.

Paper Structure

This paper contains 16 sections, 15 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Task Definition
  4. Model Architecture
  5. Representation Leanrning
  6. MMCNN
  7. Global and Local Representation Alignment with Cross-granularity Contrastive Learning
  8. Region Detection and Classification
  9. Training and Decoding
  10. Experiments
  11. Datasets
  12. Implementation Details
  13. Baselines
  14. Main Results
  15. Ablation Study
  16. ...and 1 more sections

Figures (3)

  • Figure 1: An example of ABSA including ATE, OTE, and ASTE. The orange words represent aspects, and the blue ones represent opinions.
  • Figure 2: An example of the aspect and opinion terms marked regions in the 2D table.
  • Figure 3: The overview of BTF-CCL. The sentence is encoded by BERT Encoder, enriched with word-level representations via MMCNN, and then contrastive learning between sentence-level and word-level representations is applied. Finally, triplets are extracted via region detection and classification.