Papers › An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

17 Jun 2019ACL 2019 7arXiv:1906.06906archive 2025-07-28

Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks simultaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learning common features for the different tasks, IMN introduces a message passing architecture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets.

PaperPDFConference PDFCode

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

Code

lixin4ever/E2E-TBSA officialmentioned in papermentioned on GitHub report
ruidan/IMN-E2E-ABSA officialmentioned in papermentioned on GitHubtfApache-2.0 report
lixin4ever/BERT-E2E-ABSA mentioned on GitHubpytorchApache-2.0 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 Term Extraction and Sentiment ClassificationAspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Multi-Task LearningSentenceSentiment AnalysisTerm Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect Term Extraction and Sentiment Classification SemEval IMN-BERT Avg F1 64.23 #6 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval IMN-BERT Laptop 2014 (F1) 61.73 #6 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval IMN-BERT Restaurant 2014 (F1) 70.72 #6 of 6 Archive leaderboard report
Aspect Term Extraction and Sentiment Classification SemEval IMN-BERT Restaurant 2015 (F1) 60.22 #6 of 6 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval 2014 Task 4 Laptop IMN F1 58.37 #7 of 9 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval 2014 Task 4 Subtask 1+2 IMN F1 58.37 #9 of 10 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 IMN Laptop (Acc) 75.36 #21 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 IMN Mean Acc (Restaurant + Laptop) 79.63 #21 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 IMN Restaurant (Acc) 83.89 #21 of 48 Archive leaderboard report
Sentiment Analysis SemEval 2014 Task 4 Subtask 1+2 IMN F1 58.37 #7 of 8 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.

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