Papers › Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa

Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa

11 Apr 2021NAACL 2021 4arXiv:2104.04986archive 2025-07-28

Junqi Dai, Hang Yan, Tianxiang Sun, PengFei Liu, Xipeng Qiu

Aspect-based Sentiment Analysis (ABSA), aiming at predicting the polarities for aspects, is a fine-grained task in the field of sentiment analysis. Previous work showed syntactic information, e.g. dependency trees, can effectively improve the ABSA performance. Recently, pre-trained models (PTMs) also have shown their effectiveness on ABSA. Therefore, the question naturally arises whether PTMs contain sufficient syntactic information for ABSA so that we can obtain a good ABSA model only based on PTMs. In this paper, we firstly compare the induced trees from PTMs and the dependency parsing trees on several popular models for the ABSA task, showing that the induced tree from fine-tuned RoBERTa (FT-RoBERTa) outperforms the parser-provided tree. The further analysis experiments reveal that the FT-RoBERTa Induced Tree is more sentiment-word-oriented and could benefit the ABSA task. The experiments also show that the pure RoBERTa-based model can outperform or approximate to the previous SOTA performances on six datasets across four languages since it implicitly incorporates the task-oriented syntactic information.

PaperPDFConference PDFCode

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

Code

ROGERDJQ/RoBERTaABSA officialmentioned in papermentioned 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-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Dependency ParsingSentiment Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RoBERTa+MLP Laptop (Acc) 83.78 #7 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RoBERTa+MLP Mean Acc (Restaurant + Laptop) 85.58 #7 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 RoBERTa+MLP Restaurant (Acc) 87.37 #7 of 48 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

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionRoBERTaSoftmaxWeight DecayWordPiece

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