arXiv Computation and Language

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 Machine Learning

2d ago

Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction

The paper presents a method for robust multimodal sentiment analysis that handles incomplete or noisy modalities. It introduces a completeness estimation technique to measure how much sentiment-relevant information remains in partial data, guiding the reconstruction of missing semantics. A joint training strategy stabilizes multi-task learning for sentiment prediction and completeness estimation, and experiments on three benchmark datasets show improved semantic reconstruction and sentiment accuracy.

By Han-Jun Choi, Byunggill Joe, Saim Shin, Jin Yea Jang

nlp multimodal benchmarks

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.

By Kaixin Xu, NaiJin Liu, Yulin Kang, Tangyue Jin, Zixuan Yu, Wenxi Zhao, Yibei Liu, Qianle Zhang, Yangyang Wu, Mengying Zhu, Meng Xi

nlp multimodal benchmarks

arXiv AI

Aug 26

SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

SenseShift is an encoder-based framework that enables fine‑grained, sentence‑level sentiment control in text generation. It uses bidirectional attention, quantized sentiment signals, and iterative mask infilling to generate local sentences conditioned on target sentiment intensity. Experiments on story and review generation show that SenseShift delivers stronger sentiment controllability while preserving text quality and robustness to out‑of‑domain inputs compared to larger decoder‑based baselines.

By Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl

llms efficiency

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...

By Jakub \v{S}m\'{i}d, Pavel P\v{r}ib\'{a}\v{n}, Pavel Kr\'{a}l

nlp benchmarks

arXiv AI

Jun 30

Do We Still Need Fine Tuning? Turkish Sentiment Analysis in the Era of Large Language Model

arXiv:2606. 29614v1 Announce Type: cross Abstract: This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models.

By Sercan Karaka\c{s}, Yusuf \c{S}im\c{s}ek

llms nlp fine-tuning

arXiv AI

Jul 14

Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization

arXiv:2607. 10825v1 Announce Type: cross Abstract: Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns.

By Fabrizio Marozzo, Stefano Iannicelli

llms nlp

arXiv AI

Jun 2

DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis

arXiv:2606. 01323v1 Announce Type: cross Abstract: Aspect-Based Sentiment Analysis (ABSA) encompasses seven distinct subtasks, each focusing on different extracted elements.

By Shu Long, Yanglei Gan, Xuchuan Zhou

diffusion nlp robotics

arXiv Machine Learning

Jun 9

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation

arXiv:2604. 12277v2 Announce Type: replace Abstract: Pretrained text encoders are prone to shortcut learning, relying on token-label correlations that fail once the distribution shifts in deployment.

By Jiayi Li, Shijie Tang, G\"un Kaynar, Shiyi Du, Carl Kingsford

safety

arXiv Computation and Language

Aug 25

HelaBERT: Enhancing Sinhala Language Understanding with Dual Pooling Classification Head

arXiv:2608.22922v1 Announce Type: new Abstract: We present HelaBERT, a family of two BERT-based masked language models pre-trained from scratch on approximately 1 billion tokens of Sinhala text sourc...

By Thisen Ekanayake, Nisansa de Silva

llms nlp

arXiv Computation and Language

Sep 1

REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation

arXiv:2608.30627v1 Announce Type: new Abstract: As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token pred...

By Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang

benchmarks

arXiv AI

Jul 9

Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts

arXiv:2607. 06611v1 Announce Type: cross Abstract: Automatically recognizing the sentiment, positive or negative, from speech is a challenging task, requiring both the analysis of vocal inflections and the interpretation of uttered words.

By Andrei-George Durdun, Victor Constantinescu, Radu Tudor Ionescu

llms nlp efficiency multimodal benchmarks

Hugging Face Trending Papers

Jun 22

Learning Moral Diversity: Modelling Individual Perspectives in Moral Classification of Texts

Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators' labels into a single "ground truth", overlooking the inherent subjectivity of the task.

llms nlp

Related stories