arXiv Computation and Language
Polarity Classification with Multitask Learning Syntax Augmentation
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Aug 27
KESA: A Knowledge Enhanced Approach For Sentiment Analysis
The paper introduces KESA, a knowledge‑enhanced approach for sentence‑level sentiment analysis that incorporates sentiment knowledge through two auxiliary tasks: sentiment word cloze and conditional sentiment prediction. These tasks use prior sentiment polarity to guide the selection of sentiment words and the prediction of overall sentiment, respectively, and explore label combination methods to unify multiple label types. Experiments show that KESA consistently outperforms pre‑trained models and complements existing knowledge‑enhanced post‑training methods.
arXiv AI
Aug 21
Contrastive Mixed Prompt Learning for Incomplete Multimodal Sentiment Analysis with Unseen Modality Combination
arXiv:2608. 20019v1 Announce Type: new Abstract: Incomplete multimodal sentiment analysis has garnered significant attention in recent years.
arXiv Machine Learning
Oct 19
Dependency Reasoning for Aspect Sentiment Quadruple Prediction
The paper introduces DRIFT, a method that linearizes dependency parse trees and injects them into large language model prompts to improve Aspect Sentiment Quadruple Prediction (ASQP). By providing explicit relational context, DRIFT enables the model to reason over aspect‑opinion dependencies rather than relying on token proximity. Experiments on SemEval Rest15, Rest16, and ACOS show that DRIFT outperforms other generative ASQP methods, achieving 54.47% and 64.10% F1 on Rest15 and Rest16, and demonstrating consistent gains across short- and medium‑distance aspect‑opinion configurations, while also revealing that exact‑match metrics underestimate semantically correct predictions.
arXiv Computation and Language
Oct 9
Structured Sentiment Analysis Using Sequence Labeling as Dependency Graph Parsing
The paper presents a method for structured sentiment analysis that constructs a fine‑grained sentiment graph with nodes for sentiment holders, targets, and expressions, and arcs for their relationships. It reframes the task as dependency graph parsing and solves it via sequence labeling, using linearized graph encodings to assign a label to each word. Experiments on seven datasets across five languages demonstrate that this approach achieves performance competitive with more complex single‑model methods.
arXiv Computation and Language
2d ago
Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages
The paper proposes using multilingual sentiment lexicons to steer language models for sentiment control, especially in low-resource languages. It finds that aggregated multilingual lexicons outperform English-derived steering vectors for mid- and low-resource languages, while monolingual lexicons are still best for languages the model was pre-trained on. The study also explains how representational density, pre-training priors, and architectural biases affect steering effectiveness, noting that large English vectors can cause linguistic collapse in low-resource settings but this is mitigated by norm-dampening in multilingual aggregation.
arXiv Computation and Language
Sep 1
Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
arXiv:2608.30425v1 Announce Type: new Abstract: Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source language with annotated data to a target language, enabling fine...