Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis (2404.06063v2)

Published 9 Apr 2024 in cs.CL, cs.AI, and cs.LG

Abstract: Few-Shot Aspect-Based Sentiment Analysis (FSABSA) is an indispensable and highly challenging task in natural language processing. However, methods based on Pre-trained LLMs (PLMs) struggle to accommodate multiple sub-tasks, and methods based on Generative Pre-trained Transformers (GPTs) perform poorly. To address the above issues, the paper designs a Heuristic-enhanced Candidates Selection (HCS) strategy and further proposes All in One (AiO) model based on it. The model works in a two-stage, which simultaneously accommodates the accuracy of PLMs and the generalization capability of GPTs. Specifically, in the first stage, a backbone model based on PLMs generates rough heuristic candidates for the input sentence. In the second stage, AiO leverages LLMs' contextual learning capabilities to generate precise predictions. The study conducted comprehensive comparative and ablation experiments on five benchmark datasets. The experimental results demonstrate that the proposed model can better adapt to multiple sub-tasks, and also outperforms the methods that directly utilize GPTs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33, NeurIPS, December 6-12, 2020, Vol. 33. Curran Associates Inc., Vancouver, BC, Canada, 1877–1901. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
  2. Sanjiv Ranjan Das and Mike Y. Chen. 2001. Yahoo! For Amazon: Sentiment Parsing from Small Talk on the Web. In EFA 2001 Barcelona Meetings, Available at SSRN, EFA, August 5, 2001. Elsevier, Bangkok, Thailand, 45. https://doi.org/10.2139/ssrn.276189
  3. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT. ACL, Minneapolis, MN, USA, 4171–4186. https://doi.org/10.18653/V1/N19-1423
  4. Multitask-Based Cluster Transmission for Few-Shot Text Classification. In Knowledge Science, Engineering and Management - 16th International Conference, KSEM, Vol. 14117. Springer, Guangzhou, China, 66–77. https://doi.org/10.1007/978-3-031-40283-8_7
  5. GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models. arXiv:2303.10130 [econ.GN]
  6. Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational NAACL-HLT. ACL, Minneapolis, MN, USA, 2509–2518. https://doi.org/10.18653/V1/N19-1259
  7. Target-oriented opinion words extraction with target-fused neural sequence labeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). ACL, Minneapolis, MN, USA, 2509–2518. https://doi.org/10.18653/v1/n19-1259
  8. Few-Shot Relational Triple Extraction with Perspective Transfer Network. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, CIKM. ACM, Atlanta, GA, USA, 488–498. https://doi.org/10.1145/3511808.3557323
  9. Beyond the Stars: Improving Rating Predictions using Review Text Content. In 12th International Workshop on the Web and Databases, WebDB, June 28. ACM, Providence, Rhode Island, USA, 1–6. http://webdb09.cse.buffalo.edu/papers/Paper9/WebDB.pdf
  10. Effective Attention Modeling for Aspect-Level Sentiment Classification. In Proceedings of the 27th International Conference on Computational Linguistics, COLING, August 20-26, 2018. ACL, Santa Fe, New Mexico, USA, 1121–1131.
  11. Attention-enabled gated spiking neural P model for aspect-level sentiment classification. Neural Networks 157 (2023), 437–443. https://doi.org/10.1016/j.neunet.2022.11.006
  12. Aspect Sentiment Triplet Extraction Using Reinforcement Learning. In The 30th ACM International Conference on Information and Knowledge Management, CIKM, November 1 - 5, 2021. ACM, Virtual Event, Queensland, Australia, 3603–3607. https://doi.org/10.1145/3459637.3482058
  13. A semantically enhanced dual encoder for aspect sentiment triplet extraction. Neurocomputing 562 (2023), 126917. https://doi.org/10.1016/J.NEUCOM.2023.126917
  14. Aspect-level sentiment classification via location enhanced aspect-merged graph convolutional networks. The Journal of Supercomputing 79, 9 (2023), 9666–9691. https://doi.org/10.1007/S11227-022-05002-4
  15. A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP, November 3-7, 2019. ACL, Hong Kong, China, 6279–6284. https://doi.org/10.18653/V1/D19-1654
  16. Gated Relational Encoder-Decoder Model for Target-Oriented Opinion Word Extraction. IEEE Access 10 (2022), 130507–130517. https://doi.org/10.1109/ACCESS.2022.3228835
  17. FABSA: An aspect-based sentiment analysis dataset of user reviews. Neurocomputing 562 (2023), 126867. https://doi.org/10.1016/j.neucom.2023.126867
  18. A Better Choice: Entire-space Datasets for Aspect Sentiment Triplet Extraction. arXiv:2212.09052 [cs.CL]
  19. STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI, February 7-14, 2023. AAAI Press, Washington, DC, USA, 13174–13182. https://doi.org/10.1609/aaai.v37i11.26547
  20. Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP, September 17-21, 2015. ACL, Lisbon, Portugal, 1433–1443. https://doi.org/10.18653/V1/D15-1168
  21. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Comput. Surv. 55, 9 (2023), 195:1–195:35. https://doi.org/10.1145/3560815
  22. Pair-wise aspect and opinion terms extraction as graph parsing via a novel mutually-aware interaction mechanism. Neurocomputing 493 (2022), 268–280. https://doi.org/10.1016/j.neucom.2022.04.064
  23. Mining product reputations on the Web. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD, July 23-26, 2002. ACM, Edmonton, Alberta, Canada, 341–349. https://doi.org/10.1145/775047.775098
  24. OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]
  25. Bo Pang and Lillian Lee. 2008. Opinion Mining and Sentiment Analysis. Foundations and Trends® in Information Retrieval 2 (2008), 1–135. https://doi.org/10.1561/1500000011
  26. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. In The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI). AAAI Press, New York, NY, USA, 8600–8607. https://doi.org/10.1609/aaai.v34i05.6383
  27. SemEval-2016 Task 5: Aspect Based Sentiment Analysis. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval@NAACL-HLT). ACL, San Diego, CA, USA, 19–30. https://doi.org/10.18653/v1/s16-1002
  28. SemEval-2015 Task 12: Aspect Based Sentiment Analysis. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval@NAACL-HLT). ACL, Denver, Colorado, USA, 486–495. https://doi.org/10.18653/v1/s15-2082
  29. SemEval-2014 Task 4: Aspect Based Sentiment Analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval@COLING). ACL, Dublin, Ireland, 27–35. https://doi.org/10.3115/v1/s14-2004
  30. Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, June 17-24, 2023. IEEE, Vancouver, BC, Canada, 14974–14983. https://doi.org/10.1109/CVPR52729.2023.01438
  31. ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation. arXiv:2107.02137 [cs.CL]
  32. Aspect Level Sentiment Classification with Deep Memory Network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP, November 1-4, 2016. ACL, Austin, Texas, USA, 214–224. https://doi.org/10.18653/V1/D16-1021
  33. A Weak Supervision Approach for Few-Shot Aspect Based Sentiment. arXiv:2305.11979 [cs.CL]
  34. Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, WASSA@ACL, July 14, 2023. ACL, Toronto, Canada, 19–27. https://doi.org/10.18653/V1/2023.WASSA-1.3
  35. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, NIPS, December 4-9, 2017. ACM, Long Beach, CA, USA, 5998–6008.
  36. Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction. In Findings of the Association for Computational Linguistics, EMNLP, November, 2020. ACL, Online, 2576–2585. https://doi.org/10.18653/v1/2020.findings-emnlp.234
  37. Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI, February 7-12, 2020. AAAI Press, New York, NY, USA, 9298–9305. https://doi.org/10.1609/AAAI.V34I05.6469
  38. Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), The 11th International Joint Conference on Natural Language Processing (IJCNLP). ACL, Online, 4755–4766. https://doi.org/10.18653/v1/2021.acl-long.367
  39. Position-Aware Tagging for Aspect Sentiment Triplet Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP, November 16-20, 2020. ACL, Online, 2339–2349. https://doi.org/10.18653/v1/2020.emnlp-main.183
  40. An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022, February 22 - March 1, 2022. AAAI Press, Online, 3081–3089. https://doi.org/10.1609/AAAI.V36I3.20215
  41. Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI, 9-15 July 2016. IJCAI/AAAI Press, New York, NY, USA, 2979–2985.
  42. Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, EMNLP, The 9th International Joint Conference on Natural Language Processing, IJCNLP, November 3-7, 2019. ACL, Hong Kong, China, 4567–4577. https://doi.org/10.18653/V1/D19-1464
  43. A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges. IEEE Transactions on Knowledge and Data Engineering 35, 11 (2023), 11019–11038. https://doi.org/10.1109/TKDE.2022.3230975
  44. Detecting Dependency-Related Sentiment Features for Aspect-Level Sentiment Classification. IEEE Transactions on Affective Computing 14, 1 (2023), 196–210. https://doi.org/10.1109/TAFFC.2021.3063259
  45. Synchronously tracking entities and relations in a syntax-aware parallel architecture for aspect-opinion pair extraction. Applied Intelligence 52, 13 (2022), 15210–15225. https://doi.org/10.1007/s10489-022-03286-w
  46. ChatAgri: Exploring potentials of ChatGPT on cross-linguistic agricultural text classification. Neurocomputing 557 (2023), 126708. https://doi.org/10.1016/J.NEUCOM.2023.126708
  47. A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT. arXiv:2302.09419 [cs.AI]

Summary

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