arXiv cs.CL· Muhammad Imran, Carlos G\'omez-Rodr\'iguez·· 11 小时前AI 评分18
用多任务学习句法增强做极性分类：Contrastive-MTL 在 11 个数据集上 10 个超越基线
Polarity Classification with Multitask Learning Syntax Augmentation
AI 导读
研究提出两种将句法知识融入神经情感分析的多任务学习策略：Standard-MTL 用共享编码器加两个任务头联合学习依存句法与极性分类，Contrastive-MTL 则通过对比辅助目标和句法偏置注意力池化提供隐式句法引导。
正文 · 原文
Abstract:Sentiment Analysis (SA) is a fundamental NLP task concerned with the identification and categorization of subjective information in text. While lexicon-based methods offer transparency, they often struggle with linguistic phenomena such as negation and intensification. Syntactic parsing has been integrated into SA pipelines to address this, but conventional parsers introduce significant computational overhead. Recent work shows that reformulating dependency parsing as a Sequence Labeling (SEL) task can improve efficiency. We propose and compare two strategies for integrating syntactic knowledge into a neural sentiment analysis model under unified Multi-Task Learning (MTL). The first, Standard-MTL, jointly learns dependency parsing (via sequence labeling) and sentiment polarity classification using a shared encoder with two task-specific heads. The second, Contrastive-MTL, provides implicit syntactic guidance through a contrastive auxiliary objective and a syntax-biased attention pooling mechanism, without requiring explicit label prediction. Both rely on syntactic annotations during training and eliminate need for hand-crafted compositional rules or external parsing at inference. We evaluate eleven datasets spanning seven languages---the MARC corpus (English, Spanish, French, German) and seven datasets from SemEval-2022 Task 10 (English, Spanish, Norwegian, Basque, Catalan)---using four established SEL encodings. With the relative encoding, Contrastive-MTL outperforms a syntax-naive baseline on 10 of 11 datasets and surpasses the external rule-based pipeline (SELSP) that parses at inference on all six datasets where the latter applies, while being 1.5--9$\times$ faster at evaluation. Standard-MTL is more dataset- and encoding-dependent. These results show implicit syntactic supervision during training can match or exceed explicit parsing at inference without computational overhead.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.08323 [cs.CL] |
| (or arXiv:2611.08323v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08323 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Muhammad Imran [view email]
[v1]
Thu, 5 Nov 2026 17:19:09 UTC (1,896 KB)
来源：arXiv cs.CL · arxiv.org