Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning (2403.07342v2)

Published 12 Mar 2024 in cs.CL and cs.AI

Abstract: Aspect Sentiment Triplet Extraction (ASTE) is a burgeoning subtask of fine-grained sentiment analysis, aiming to extract structured sentiment triplets from unstructured textual data. Existing approaches to ASTE often complicate the task with additional structures or external data. In this research, we propose a novel tagging scheme and employ a contrastive learning approach to mitigate these challenges. The proposed approach demonstrates comparable or superior performance in comparison to state-of-the-art techniques, while featuring a more compact design and reduced computational overhead. Notably, even in the era of LLMs, our method exhibits superior efficacy compared to GPT 3.5 and GPT 4 in a few-shot learning scenarios. This study also provides valuable insights for the advancement of ASTE techniques within the paradigm of LLMs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2974–2985.
  2. Bidirectional machine reading comprehension for aspect sentiment triplet extraction. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 12666–12674.
  3. Semantic and syntactic enhanced aspect sentiment triplet extraction. arXiv preprint arXiv:2106.03315.
  4. Hongliang Dai and Yangqiu Song. 2019. Neural aspect and opinion term extraction with mined rules as weak supervision. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5268–5277.
  5. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  6. Inheriting the wisdom of predecessors: A multiplex cascade framework for unified aspect-based sentiment analysis. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI, pages 4096–4103.
  7. Simcse: Simple contrastive learning of sentence embeddings. In 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, pages 6894–6910. Association for Computational Linguistics (ACL).
  8. Declutr: Deep contrastive learning for unsupervised textual representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 879–895.
  9. Dimensionality reduction by learning an invariant mapping. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), volume 2, pages 1735–1742. IEEE.
  10. Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415.
  11. Roger A Horn. 1990. The hadamard product. In Proc. Symp. Appl. Math, volume 40, pages 87–169.
  12. A survey on contrastive self-supervised learning. Technologies, 9(1).
  13. Seeking common but distinguishing difference, a joint aspect-based sentiment analysis model. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3910–3922.
  14. Contrastive representation learning: A framework and review. Ieee Access, 8:193907–193934.
  15. Dual graph convolutional networks integrating affective knowledge and position information for aspect sentiment triplet extraction. Frontiers in Neurorobotics, 17.
  16. Stage: span tagging and greedy inference scheme for aspect sentiment triplet extraction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 13174–13182.
  17. Learning to remove: Towards isotropic pre-trained bert embedding. In Artificial Neural Networks and Machine Learning–ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part V 30, pages 448–459. Springer.
  18. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988.
  19. A robustly optimized bmrc for aspect sentiment triplet extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 272–278.
  20. Andrzej Maćkiewicz and Waldemar Ratajczak. 1993. Principal components analysis (pca). Computers & Geosciences, 19(3):303–342.
  21. A joint training dual-mrc framework for aspect based sentiment analysis. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 13543–13551.
  22. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 8600–8607.
  23. Novel cinnamic acid derivatives as antioxidant and anticancer agents: Design, synthesis and modeling studies. Molecules, 19(7):9655–9674.
  24. Semeval-2015 task 12: Aspect based sentiment analysis. In Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015), pages 486–495.
  25. Semeval-2016 task 5: Aspect based sentiment analysis. In ProWorkshop on Semantic Evaluation (SemEval-2016), pages 19–30. Association for Computational Linguistics.
  26. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823.
  27. A contrastive cross-channel data augmentation framework for aspect-based sentiment analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6691–6704.
  28. Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning, pages 9929–9939. PMLR.
  29. Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pages 3316–3322.
  30. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, pages 38–45.
  31. Hallucination improves the performance of unsupervised visual representation learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16132–16143.
  32. Grid tagging scheme for aspect-oriented fine-grained opinion extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2576–2585.
  33. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466.
  34. Position-aware tagging for aspect sentiment triplet extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2339–2349.
  35. A unified generative framework for aspect-based sentiment analysis. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2416–2429.
  36. A pairing enhancement approach for aspect sentiment triplet extraction. arXiv preprint arXiv:2306.10042.
  37. Contrastive triple extraction with generative transformer. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 14257–14265.
  38. Com-mrc: A context-masked machine reading comprehension framework for aspect sentiment triplet extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3230–3241.
  39. A multi-task learning framework for opinion triplet extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 819–828.
  40. Supporting clustering with contrastive learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5419–5430.
  41. Boundary-driven table-filling for aspect sentiment triplet extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6485–6498.
  42. A multi-task shared cascade learning for aspect sentiment triplet extraction using bert-mrc. Cognitive Computation, pages 1–18.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Qiao Sun (21 papers)
  2. Liujia Yang (3 papers)
  3. Minghao Ma (3 papers)
  4. Nanyang Ye (26 papers)
  5. Qinying Gu (14 papers)

Summary

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

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