Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials (2402.19076v1)

Published 29 Feb 2024 in cs.CL

Abstract: In recent years, LLMs have achieved state-of-the-art performance across various NLP tasks. However, investigations have shown that these models tend to rely on shortcut features, leading to inaccurate predictions and causing the models to be unreliable at generalization to out-of-distribution (OOD) samples. For instance, in the context of relation extraction (RE), we would expect a model to identify the same relation independently of the entities involved in it. For example, consider the sentence "Leonardo da Vinci painted the Mona Lisa" expressing the created(Leonardo_da_Vinci, Mona_Lisa) relation. If we substiute "Leonardo da Vinci" with "Barack Obama", then the sentence still expresses the created relation. A robust model is supposed to detect the same relation in both cases. In this work, we describe several semantically-motivated strategies to generate adversarial examples by replacing entity mentions and investigate how state-of-the-art RE models perform under pressure. Our analyses show that the performance of these models significantly deteriorates on the modified datasets (avg. of -48.5% in F1), which indicates that these models rely to a great extent on shortcuts, such as surface forms (or patterns therein) of entities, without making full use of the information present in the sentences.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Matching the blanks: Distributional similarity for relation learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
  2. Yonatan Belinkov and Yonatan Bisk. 2018. Synthetic and natural noise both break neural machine translation. In International Conference on Learning Representations.
  3. John Blitzer. 2008. Domain Adaptation of Natural Language Processing Systems. Ph.D. thesis.
  4. Robust neural machine translation with doubly adversarial inputs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
  5. Towards interpreting and mitigating shortcut learning behavior of NLU models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  6. HotFlip: White-box adversarial examples for text classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
  7. Using punctuation as an adversarial attack on deep learning-based NLP systems: An empirical study. In Findings of the Association for Computational Linguistics: EACL 2023.
  8. Piotr Gaiński and Klaudia Bałazy. 2023. Step by step loss goes very far: Multi-step quantization for adversarial text attacks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics.
  9. Explaining and harnessing adversarial examples. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  10. A survey of adversarial defences and robustness in nlp.
  11. Marti A. Hearst. 1992. Automatic acquisition of hyponyms from large text corpora. In COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics.
  12. Deceiving google’s perspective api built for detecting toxic comments. arXiv preprint arXiv:1702.08138.
  13. Unified semantic typing with meaningful label inference. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  14. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2).
  15. Robin Jia and Percy Liang. 2017. Adversarial examples for evaluating reading comprehension systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.
  16. How can we know when language models know? on the calibration of language models for question answering. Transactions of the Association for Computational Linguistics, 9:962–977.
  17. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8.
  18. Divyansh Kaushik and Zachary C. Lipton. 2018. How much reading does reading comprehension require? a critical investigation of popular benchmarks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
  19. Understanding neural networks through representation erasure.
  20. On robustness and bias analysis of bert-based relation extraction. In Knowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction.
  21. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55:1 – 35.
  22. Summarization as indirect supervision for relation extraction. In EMNLP - Findings.
  23. Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3428–3448. Association for Computational Linguistics.
  24. TextAttack: A framework for adversarial attacks, data augmentation, and adversarial training in NLP. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.
  25. Crafting adversarial input sequences for recurrent neural networks. In MILCOM 2016 - 2016 IEEE Military Communications Conference.
  26. Language models as knowledge bases? ArXiv, abs/1909.01066.
  27. Semantically equivalent adversarial rules for debugging NLP models. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
  28. Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
  29. Oscar Sainz and German Rigau. 2021. Ask2Transformers: Zero-shot domain labelling with pretrained language models. In Proceedings of the 11th Global Wordnet Conference.
  30. Towards debiasing fact verification models. 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), pages 3419–3425. Association for Computational Linguistics.
  31. Masked language modeling and the distributional hypothesis: Order word matters pre-training for little. arXiv preprint arXiv:2104.06644.
  32. Intriguing properties of neural networks. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings.
  33. The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.
  34. Universal adversarial triggers for attacking and analyzing NLP. 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).
  35. Shanchan Wu and Yifan He. 2019. Enriching pre-trained language model with entity information for relation classification. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management.
  36. Jincheng Xu and Qingfeng Du. 2020. Texttricker: Loss-based and gradient-based adversarial attacks on text classification models. Eng. Appl. Artif. Intell., 92:103641.
  37. LUKE: Deep contextualized entity representations with entity-aware self-attention. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
  38. Searching for a search method: Benchmarking search algorithms for generating NLP adversarial examples. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP.
  39. Bridge the gap between cv and nlp! a gradient-based textual adversarial attack framework.
  40. Position-aware attention and supervised data improve slot filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.
  41. Wenxuan Zhou and Muhao Chen. 2022. An improved baseline for sentence-level relation extraction. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Gennaro Nolano (3 papers)
  2. Moritz Blum (6 papers)
  3. Basil Ell (3 papers)
  4. Philipp Cimiano (25 papers)

Summary

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

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