Lune

ACL Findings2023

Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation

Guoxin Yu, Lemao Liu, Haiyun Jiang, Shuming Shi, Xiang Ao

Abstract

In this paper, we aim to adapt the idea of retrieval-based neural approaches to the Aspect Sentiment Triplet Extraction (ASTE) task. Different from previous studies retrieving semantic similar neighbors, the ASTE task has its specialized challenges when adapting, i.e., the purpose includes predicting the sentiment polarity and it is usually aspect-dependent. Semantic similar neighbors with different polarities will be infeasible even counterproductive. To tackle this issue, we propose a retrieval-based neural ASTE approach, named RLI (Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation), which exploits the label information of neighbors. Given an aspect-opinion term pair, we retrieve semantic similar triplets from the training corpus and interpolate their label information into the augmented representation of the target pair. The retriever is jointly trained with the whole ASTE framework, and neighbors with both similar semantics and sentiments can be recalled with the aid of this distant supervision. In addition, we design a simple yet effective pre-train method for the retriever that implicitly encodes the label similarities. Extensive experiments and analysis on two widely-used benchmarks show that the proposed model establishes a new state-of-the-art on ASTE.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Grid Tagging Scheme for End-to-End Fine-grained Opinion Extraction cites Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis
  • Position-Aware Tagging for Aspect Sentiment Triplet Extraction cites Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis
  • A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis cites Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. EFSA: Towards Event-Level Financial Sentiment AnalysisTianyu Chen, Yiming Zhang, Guoxin Yu, Dapeng Zhang et al.ACL 2024 · 4 citations

Builds on14

  1. Generalization through Memorization: Nearest Neighbor Language ModelsUrvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer et al.ICLR 2020 · 1,038 citations
  2. Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment AnalysisHaiyun Peng, Lu Xu, Lidong Bing, Fei Huang et al.AAAI 2020 · 494 citations
  3. Position-Aware Tagging for Aspect Sentiment Triplet ExtractionLu Xu, Hao Li, Wei Lu, Lidong BingEMNLP 2020 · 264 citations
  4. Grid Tagging Scheme for End-to-End Fine-grained Opinion ExtractionZhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan et al.EMNLP Findings 2020 · 253 citations
  5. A Joint Training Dual-MRC Framework for Aspect Based Sentiment AnalysisYue Mao, Yi Shen, Chao Yu, Longjun CaiAAAI 2021 · 243 citations

Related papers

  1. ASTE-Transformer: Modelling Dependencies in Aspect-Sentiment Triplet ExtractionIwo Naglik, Mateusz LangoEMNLP Findings 2024 · 4 citations
  2. STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet ExtractionShuo Liang, Wei Wei, Xian-Ling Mao, Yuanyuan Fu et al.AAAI 2023 · 54 citations
  3. Dual-Channel Span for Aspect Sentiment Triplet ExtractionPan Li, Ping Li, Kai ZhangEMNLP 2023 · 11 citations
  4. Learning Cooperative Interactions for Multi-Overlap Aspect Sentiment Triplet ExtractionShiman Zhao, Wei Chen, Tengjiao WangEMNLP Findings 2022 · 7 citations
  5. Refine, Align, and Aggregate: Multi-view Linguistic Features Enhancement for Aspect Sentiment Triplet ExtractionGuixin Su, Mingmin Wu, Zhongqiang Huang, Yongcheng Zhang et al.ACL Findings 2024 · 16 citations
Dusk over the sea between two cliffs drawn in fine vertical lines