Papers › A Unified Generative Framework for Aspect-Based Sentiment Analysis

A Unified Generative Framework for Aspect-Based Sentiment Analysis

8 Jun 2021ACL 2021 5arXiv:2106.04300archive 2025-07-28

Hang Yan, Junqi Dai, Tuo ji, Xipeng Qiu, Zheng Zhang

Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which leads to various complicated ABSA models while hard to solve these subtasks in a unified framework. In this paper, we redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexes, which converts all ABSA subtasks into a unified generative formulation. Based on the unified formulation, we exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an end-to-end framework. Extensive experiments on four ABSA datasets for seven subtasks demonstrate that our framework achieves substantial performance gain and provides a real unified end-to-end solution for the whole ABSA subtasks, which could benefit multiple tasks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yhcc/BARTABSA officialmentioned in papermentioned on GitHubpytorch report
ROGERDJQ/RoBERTaABSA mentioned on GitHubpytorch report
sherlock-jerry/ssa-semeval mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect Sentiment Triplet ExtractionAspect Term Extraction and Sentiment ClassificationAspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Aspect-oriented Opinion ExtractionSentiment Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect Sentiment Triplet Extraction ASTE-Data-V2 BARTABSA F1 67.62 #10 of 11 Archive leaderboard report
Aspect Sentiment Triplet Extraction MuseASTE BARTABSA F1 0.249 #2 of 4 Archive leaderboard report
Aspect Sentiment Triplet Extraction SemEval BARTABSA F1 72.46 #1 of 4 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval BARTABSA Avg F1 69.18 #2 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval BARTABSA Laptop 2014 (F1) 67.37 #2 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval BARTABSA Restaurant 2014 (F1) 73.56 #2 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval BARTABSA Restaurant 2015 (F1) 66.61 #2 of 6 Archive leaderboard report
Aspect-oriented Opinion Extraction SemEval-2014 Task-4 BARTABSA Laptop 2014 (F1) 80.55 #1 of 5 Archive leaderboard report
Aspect-oriented Opinion Extraction SemEval-2014 Task-4 BARTABSA Restaurant 2014 (F1) 85.38 #1 of 5 Archive leaderboard report
Aspect-oriented Opinion Extraction SemEval-2014 Task-4 BARTABSA Restaurant 2015 (F1) 80.52 #1 of 5 Archive leaderboard report
Aspect-oriented Opinion Extraction SemEval-2014 Task-4 BARTABSA Restaurant 2016 (F1) 87.92 #1 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionBARTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections