nach oben

Erschienen in:

2021 | OriginalPaper | Buchkapitel

Cross-Domain Transfer of Generative Explanations Using Text-to-Text Models

verfasst von : Karl Fredrik Erliksson, Anders Arpteg, Mihhail Matskin, Amir H. Payberah

Erschienen in: Natural Language Processing and Information Systems

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Deep learning models based on the Transformers architecture have achieved impressive state-of-the-art results and even surpassed human-level performance across various natural language processing tasks. However, these models remain opaque and hard to explain due to their vast complexity and size. This limits adoption in highly-regulated domains like medicine and finance, and often there is a lack of trust from non-expert end-users. In this paper, we show that by teaching a model to generate explanations alongside its predictions on a large annotated dataset, we can transfer this capability to a low-resource task in another domain. Our proposed three-step training procedure improves explanation quality by up to 7% and avoids sacrificing classification performance on the downstream task, while at the same time reducing the need for human annotations.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel NumER: A Fine-Grained Numeral Entity Recognition Dataset

Nächstes Kapitel Virus Causes Flu: Identifying Causality in the Biomedical Domain Using an Ensemble Approach with Target-Specific Semantic Embeddings

Code available at https://github.com/Peltarion/explainability_transfer.

Since all seq2seq models considered in this work have publicly released checkpoints from language model pre-training, this is used as starting point for step 2 in Fig. 1.

We use the dataset versions distributed through the ERASER benchmark [10].

The hyperparameter settings for the different models and training phases are available in the public code repository.

Bastings, J., et al.: Interpretable neural predictions with differentiable binary variables. In: ACL (2019)

Bowman, S.R., et al.: A large annotated corpus for learning natural language inference. In: EMNLP (2015)

Brunner, G., et al.: On identifiability in transformers. In: ICLR (2019)

Camburu, O., et al.: e-SNLI: natural language inference with natural language explanations. In: NeurIPS (2018)

Chen, C., et al.: This looks like that: Deep learning for interpretable image recognition. In: NeurIPS (2019)

Clark, K., et al.: What does BERT look at? An analysis of BERT’S attention. In: ACL Blackbox NLP Workshop (2019)

Common Crawl. https://www.commoncrawl.org

Danilevsky, M., et al.: A survey of the state of explainable AI for natural language processing. In: AACL-IJCNLP (2020)

Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)

10.

DeYoung, J., et al.: ERASER: a benchmark to evaluate rationalized NLP models. In: ACL (2020)

11.

Doshi-Velez, F., et al.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)

12.

Ehsan, U., et al.: Rationalization: a neural machine translation approach to generating natural language explanations. In: AIES (2018)

13.

EU: General Data Prodection Regulation (GDPR): Recital 71 (2018). https://www.privacy-regulation.eu/en/r71.htm

14.

Guidotti, R., et al.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1–42 (2018)CrossRef

15.

He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)

16.

Hendricks, L.A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., Darrell, T.: Generating visual explanations. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 3–19. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_1CrossRef

17.

Jacovi, A., et al.: Towards faithfully interpretable NLP systems: how should we define and evaluate faithfulness? In: ACL (2020)

18.

Jain, S., et al.: An analysis of attention over clinical notes for predictive tasks. In: Clinical NLP (2019)

19.

Jain, S., et al.: Attention is not explanation. In: NAACL (2019)

20.

Khashabi, D., et al.: Looking beyond the surface: a challenge set for reading comprehension over multiple sentences. In: NAACL (2018)

21.

Kim, B., et al.: The Bayesian case model: a generative approach for case-based reasoning and prototype classification. In: NIPS (2014)

22.

Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 577–593. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_35CrossRef

23.

Kovaleva, O., et al.: Revealing the dark secrets of BERT. In: NeurIPS (2019)

24.

Lehman, E., et al.: Inferring which medical treatments work from reports of clinical trials. In: NAACL (2019)

25.

Lei, T., et al.: Rationalizing neural predictions. In: EMNLP (2016)

26.

Letham, B., et al.: Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model. Ann. Appl. Stat. 9, 1350–1371 (2015)MathSciNetCrossRef

27.

Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL (2020)

28.

Lin, C.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)

29.

Lundberg, S., et al.: A unified approach to interpreting model predictions. In: NIPS (2017)

30.

Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)MathSciNetCrossRef

31.

Mullenbach, J., et al.: Explainable prediction of medical codes from clinical text. In: NAACL (2018)

32.

Narang, S., et al.: WT5?! Training text-to-text models to explain their predictions. arXiv preprint arXiv:2004.14546 (2020)

33.

Papineni, K., et al.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)

34.

Paranjape, B., et al.: An information bottleneck approach for controlling conciseness in rationale extraction. In: EMNLP (2020)

35.

Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR (2020)

36.

Rajani, N., et al.: Explain yourself! Leveraging language models for commonsense reasoning. In: ACL (2019)

37.

Ribeiro, M., et al.: Why should i trust you? Explaining the predictions of any classifier. In: KDD (2016)

38.

Serrano, S., et al.: Is attention interpretable? In: ACL (2019)

39.

Sundararajan, M.: Axiomatic attribution for deep networks. In: ICML (2017)

40.

Thorne, J., et al.: FEVER: a large-scale dataset for fact extraction and verification. In: NAACL (2018)

41.

Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)

42.

Wadden, D., et al.: Fact or fiction: verifying scientific claims. In: EMNLP (2020)

43.

Wang, A., et al.: Superglue: a stickier benchmark for general-purpose language understanding systems. In: NeurIPS (2019)

44.

Wiegreffe, S., et al.: Attention is not not explanation. In: EMNLP-IJCNLP (2019)

45.

Wiegreffe, S., et al.: Measuring association between labels and free-text rationales. arXiv preprint arXiv:2010.12762 (2020)

46.

Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 (2020)

Titel: Cross-Domain Transfer of Generative Explanations Using Text-to-Text Models
verfasst von: Karl Fredrik Erliksson
Anders Arpteg
Mihhail Matskin
Amir H. Payberah
Verlag: Springer International Publishing
Buch: Natural Language Processing and Information Systems
Print ISBN: 978-3-030-80598-2

Electronic ISBN: 978-3-030-80599-9

Copyright-Jahr: 2021
DOI: https://doi.org/10.1007/978-3-030-80599-9_8

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner