Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection (2407.20673v1)

Published 30 Jul 2024 in cs.CL and cs.AI

Abstract: Multi-label few-shot aspect category detection aims at identifying multiple aspect categories from sentences with a limited number of training instances. The representation of sentences and categories is a key issue in this task. Most of current methods extract keywords for the sentence representations and the category representations. Sentences often contain many category-independent words, which leads to suboptimal performance of keyword-based methods. Instead of directly extracting keywords, we propose a label-guided prompt method to represent sentences and categories. To be specific, we design label-specific prompts to represent sentences by combining crucial contextual and semantic information. Further, the label is introduced into a prompt to obtain category descriptions by utilizing a LLM. This kind of category descriptions contain the characteristics of the aspect categories, guiding the construction of discriminative category prototypes. Experimental results on two public datasets show that our method outperforms current state-of-the-art methods with a 3.86% - 4.75% improvement in the Macro-F1 score.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. Infinite mixture prototypes for few-shot learning. In ICML, pages 232–241, 2019.
  2. Language models are few-shot learners. In NeurIPS, pages 1877–1901, 2020.
  3. Large-scale multi-label text classification on eu legislation. arXiv preprint arXiv:1906.02192, 2019.
  4. Hybrid attention-based prototypical networks for noisy few-shot relation classification. In AAAI, pages 6407–6414, 2019.
  5. SimCSE: Simple contrastive learning of sentence embeddings. In EMNLP, pages 6894–6910, 2021.
  6. Mncn: A multilingual ngram-based convolutional network for aspect category detection in online reviews. In AAAI, pages 6441–6448, 2019.
  7. PPT: Pre-trained prompt tuning for few-shot learning. In ACL, pages 8410–8423, 2022.
  8. Implicit feature identification via co-occurrence association rule mining. In CICLing, pages 393–404, 2011.
  9. Few-shot learning for multi-label intent detection. In AAAI, pages 13036–13044, 2021.
  10. Multi-label few-shot learning for aspect category detection. In ACL-IJCNLP, pages 6330–6340, 2021.
  11. A challenge dataset and effective models for aspect-based sentiment analysis. In EMNLP-IJCNLP, pages 6280–6285, 2019.
  12. Promptbert: Improving bert sentence embeddings with prompts. In EMNLP, pages 8826–8837, 2022.
  13. PromptBERT: Improving BERT sentence embeddings with prompts. In EMNLP, pages 8826–8837, 2022.
  14. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT, pages 4171–4186, 2019.
  15. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691, 2021.
  16. On the sentence embeddings from pre-trained language models. In EMNLP, pages 9119–9130, 2020.
  17. Label-enhanced prototypical network with contrastive learning for multi-label few-shot aspect category detection. In SIGKDD, pages 1079–1087, 2022.
  18. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  19. Aspect category detection via topic-attention network. arXiv preprint arXiv:1901.01183, 2019.
  20. Semeval-2016 task 5: Aspect based sentiment analysis. In SemEval, pages 19–30, 2016.
  21. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In EMNLP-IJCNLP, pages 3982–3992, 2019.
  22. Few-shot and zero-shot multi-label learning for structured label spaces. In EMNLP, pages 3132–3142, 2018.
  23. Supervised and unsupervised aspect category detection for sentiment analysis with co-occurrence data. IEEE transactions on cybernetics, 48(4):1263–1275, 2017.
  24. Prototypical networks for few-shot learning. In NeurIPS, pages 4080–4090, 2017.
  25. Whitening sentence representations for better semantics and faster retrieval. arXiv preprint arXiv:2103.15316, 2021.
  26. Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 9(86):2579–2605, 2008.
  27. Few-shot multi-label aspect category detection utilizing prototypical network with sentence-level weighting and label augmentation. In DEXA, pages 363–377, 2023.
  28. Label-driven denoising framework for multi-label few-shot aspect category detection. arXiv preprint arXiv:2210.04220, 2022.
  29. Learning few-shot sample-set operations for noisy multi-label aspect category detection. In IJCAI, pages 5306–5313, 2023.
  30. Multi-attention meta learning for few-shot fine-grained image recognition. In IJCAI, pages 1090–1096, 2020.
  31. Attribute-guided feature learning for few-shot image recognition. IEEE Transactions on Multimedia, 23:1200–1209, 2020.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now