Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

About

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method.

Zheng Li, Xin Li, Ying Wei, Lidong Bing, Yu Zhang, Qiang Yang• 2019

Related benchmarks

TaskDatasetResultRank
Unified Aspect-Based Sentiment AnalysisCross-domain ABSA Transfer Pairs S, R, L, D domains
Micro-F1 (S -> R)41.03
11
Aspect Term ExtractionCross-domain ABSA S, R, L, D domains (Transfer Pairs)
Micro-F1 (S -> R)52.05
10
Showing 2 of 2 rows

Other info

Follow for update