Lune

EMNLP Findings2022

Leveraging Only the Category Name for Aspect Detection through Prompt-based Constrained Clustering

Yazheng Li, Pengyun Wang, Yasheng Wang, Yong Dai, Yadao Wang, Lujia Pan, Zenglin Xu

Abstract

Aspect category detection (ACD) aims to automatically identify user-concerned aspects from online reviews, which is of great value for evaluating the fine-grained performance of a product.The most recent solutions tackle this problem via weakly supervised methods, achieving remarkable improvement over unsupervised methods.However, a closer look at these methods reveals that the required human efforts are nontrivial and can sometimes be hard to obtain.In this study, we explore the possibility of minimizing human guidance while improving detection performance, with a deep clustering method that relies merely on the category name of each aspect and a pretrained language model (LM).The LM, combined with prompt techniques, is employed as a knowledge base to automatically generate constraints for clustering, as well as to provide a representation space to perform the clustering.Our method (1) extracts extensive keywords to expand our understanding of each aspect, (2) automatically generates instance-level and concept-level constraints for clustering, and (3) trains the clustering model with the above constraints.We demonstrate the capability of the proposed framework through extensive experiments on four benchmark datasets across nine domains.Our model not only performs noticeably better than existing unsupervised approaches but also considerably surpasses weakly supervised methods that require more human efforts.Our code is available at: https://github.com/ liyazheng/PCCT.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection cites A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection
  • Text Classification Using Label Names Only: A Language Model Self-Training Approach cites Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding
  • Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding cites Text Classification Using Label Names Only: A Language Model Self-Training Approach
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. A Self-enhancement Multitask Framework for Unsupervised Aspect Category DetectionThi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, Tuan-Dung CaoEMNLP 2023 · 3 citations

Builds on6

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  3. Text Classification Using Label Names Only: A Language Model Self-Training ApproachYu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong et al.EMNLP 2020 · 203 citations
  4. Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic EmbeddingJiaxin Huang, Yu Meng, Fang Guo, Heng Ji et al.EMNLP 2020 · 54 citations
  5. A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect DetectionTian Shi, Liuqing Li, Ping Wang, Chandan K. ReddyAAAI 2021 · 44 citations

Related papers

  1. CEIL: A General Classification-Enhanced Iterative Learning Framework for Text ClusteringMingjun Zhao, Mengzhen Wang, Yinglong Ma, Di Niu et al.WWW 2023 · 2 citations
  2. An Uncertainty-Aware Encoder for Aspect DetectionThi-Nhung Nguyen, Kiem-Hieu Nguyen, Young-In Song, Tuan-Dung CaoEMNLP Findings 2021 · 4 citations
  3. Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category DetectionFei Zhao, Yuchen Shen, Zhen Wu, Xinyu DaiEMNLP Findings 2022 · 11 citations
  4. AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment AnalysisSabyasachi Kamila, Walid Magdy, Sourav Dutta, MingXue WangEMNLP 2022 · 5 citations
  5. RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical RulesMiaomiao Li, Jiaqi Zhu, Yang Wang, Yi Yang et al.WWW 2024 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines