Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

Abstract

Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i.e., the part-of-speech tags and dependency relations). As an important aspect of exploring characteristics of language comprehension, adaptive graph representations have played an essential role in recent years. To this end, in the paper, we aim to explore the possibility of learning invariant semantic features from graph-like structures in CDSC. Specifically, we present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs. More specifically, we first raise a POS-Transformer module to extract sequential semantic features from the word sequences as well as the part-of-speech tags. Then, we design a Hybrid Graph Attention (HGAT) module to generate syntax-based semantic features by considering the transferable dependency relations. Finally, we devise an Integrated aDaptive Strategy (IDS) to guide the joint learning process of both modules. Extensive experiments on four public datasets indicate that GAST achieves comparable effectiveness to a range of state-of-the-art models.

Towards Distribution-shift Robust Text Classification of Emotional Content

“…PADA (Ben-David et al, 2022) generates domain-related features and adds them to the text to enable the model to adapt to different domains. Other studies refer to specific tasks such as moral value classification (Liscio et al, 2022) and sentiment analysis (Fu and Liu, 2022;Zhang et al, 2022a;Li et al, 2022;Luo et al, 2022;Liu and Zhao, 2022). Despite not considering the model generalization across datasets, and being often application-specific, these methods do not make any assessment with zero-shot learning nor consider building upon them to improve OOD performance.…”