mlsanityData to 14 Oct 2026

Multi-Domain Targeted Sentiment Analysis

arXiv 2205.03804 ↗First posted 8 May 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Targeted Sentiment Analysis (TSA) is a central task for generating insights from consumer reviews. Such content is extremely diverse, with sites like Amazon or Yelp containing reviews on products and businesses from many different domains. A real-world TSA system should gracefully handle that diversity. This can be achieved by a multi-domain model -- one that is robust to the domain of the analyzed texts, and performs well on various domains. To address this scenario, we present a multi-domain TSA system based on augmenting a given training set with diverse weak labels from assorted domains. These are obtained through self-training on the Yelp reviews corpus. Extensive experiments with our approach on three evaluation datasets across different domains demonstrate the effectiveness of our solution. We further analyze how restrictions imposed on the available labeled data affect the performance, and compare the proposed method to the costly alternative of manually gathering diverse TSA labeled data. Our results and analysis show that our approach is a promising step towards a practical domain-robust TSA system.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 60 references that are in the map. First posted on arXiv 8 May 2022.

Builds on

24 of 60 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Confidence Regularized Self-Trainingcited by 419
  4. 2020XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generationcited by 222
  5. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  6. 2020The Multilingual Amazon Reviews Corpuscited by 143
  7. 2019Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysiscited by 123
  8. 2021Cycle Self-Training for Domain Adaptationcited by 120
  9. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  10. 2020Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approachcited by 83
  11. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
  12. 2019Exploiting BERT for End-to-End Aspect-based Sentiment Analysiscited by 57
12 more
  1. 2018A Unified Model for Opinion Target Extraction and Target Sentiment Predictioncited by 56
  2. 2021Self-Training with Weak Supervisioncited by 49
  3. 2018Double Embeddings and CNN-based Sequence Labeling for Aspect Extractioncited by 42
  4. 2021Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTacited by 41
  5. 2018Aspect Term Extraction with History Attention and Selective Transformationcited by 37
  6. 2020Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialogcited by 37
  7. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  8. 2020Multilingual Argument Mining: Datasets and Analysiscited by 20
  9. 2018Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classificationcited by 19
  10. 2017Data Selection Strategies for Multi-Domain Sentiment Analysiscited by 11
  11. 2020YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviewscited by 7
  12. 2020Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarioscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Large Language Models in Targeted Sentiment Analysiscited by 3