# Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training

arXiv: https://arxiv.org/abs/1909.00415 · HTML: https://mlsanity.com/paper/1909.00415/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [Self-Training with Weak Supervision](https://mlsanity.com/paper/2104.05514/) (2021)
- [Co-training Improves Prompt-based Learning for Large Language Models](https://mlsanity.com/paper/2202.00828/) (2022)
- [Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey](https://mlsanity.com/paper/2406.08068/) (2024)
- [Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer](https://mlsanity.com/paper/2109.08024/) (2021)
- [Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction](https://mlsanity.com/paper/2112.09215/) (2021)
- [Interactive Machine Teaching by Labeling Rules and Instances](https://mlsanity.com/paper/2409.05199/) (2024)
- [WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding](https://mlsanity.com/paper/2108.12603/) (2021)
- [SocialVisTUM: An Interactive Visualization Toolkit for Correlated Neural Topic Models on Social Media Opinion Mining](https://mlsanity.com/paper/2110.10575/) (2021)
- [A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection](https://mlsanity.com/paper/2311.09708/) (2023)
- [Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization](https://mlsanity.com/paper/2210.09428/) (2022)

## Abstract (arXiv)

User-generated reviews can be decomposed into fine-grained segments (e.g., sentences, clauses), each evaluating a different aspect of the principal entity (e.g., price, quality, appearance). Automatically detecting these aspects can be useful for both users and downstream opinion mining applications. Current supervised approaches for learning aspect classifiers require many fine-grained aspect labels, which are labor-intensive to obtain. And, unfortunately, unsupervised topic models often fail to capture the aspects of interest. In this work, we consider weakly supervised approaches for training aspect classifiers that only require the user to provide a small set of seed words (i.e., weakly positive indicators) for the aspects of interest. First, we show that current weakly supervised approaches do not effectively leverage the predictive power of seed words for aspect detection. Next, we propose a student-teacher approach that effectively leverages seed words in a bag-of-words classifier (teacher); in turn, we use the teacher to train a second model (student) that is potentially more powerful (e.g., a neural network that uses pre-trained word embeddings). Finally, we show that iterative co-training can be used to cope with noisy seed words, leading to both improved teacher and student models. Our proposed approach consistently outperforms previous weakly supervised approaches (by 14.1 absolute F1 points on average) in six different domains of product reviews and six multilingual datasets of restaurant reviews.