Contrastive Explanations of Text Classifiers as a Service

Malandri, Lorenzo; Mercorio, Fabio; Mezzanzanica, Mario; Nobani, Navid; Seveso, Andrea

doi:10.18653/v1/2022.naacl-demo.6

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other related approaches enable global (rather than local) explainability (Malandri et al, 2022), or explanation interfaces for non-transformers models on non-NLP tasks (Agarwal et al, 2022). Other approaches study model behavior at the subgroup level (Wang et al, 2021;Goel et al, 2021;Pastor et al, 2021a,b), focusing more on model evaluation and robustness rather than its interpretation.…”

Section: Related Workmentioning

confidence: 99%

ferret: a Framework for Benchmarking Explainers on Transformers

Attanasio,

Pastor,

Di Bonaventura

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrati

View full text Add to dashboard Cite

As Transformers are increasingly relied upon to solve complex NLP problems, there is an increased need for their decisions to be humanly interpretable. While several explainable AI (XAI) techniques for interpreting the outputs of transformer-based models have been proposed, there is still a lack of easy access to using and comparing them. We introduce ferret, a Python library to simplify the use and comparisons of XAI methods on transformer-based classifiers. With ferret, users can visualize and compare transformers-based models output explanations using state-of-the-art XAI methods on any freetext or existing XAI corpora. Moreover, users can also evaluate ad-hoc XAI metrics to select the most faithful and plausible explanations. To align with the recently consolidated process of sharing and using transformers-based models from Hugging Face, ferret interfaces directly with its Python library. In this paper, we showcase ferret to benchmark XAI methods used on transformers for sentiment analysis and hate speech detection. We show how specific methods provide consistently better explanations and are preferable in the context of transformer models.

show abstract

Section: Related Workmentioning

confidence: 99%

ferret: a Framework for Benchmarking Explainers on Transformers

Attanasio,

Pastor,

Di Bonaventura

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrati

View full text Add to dashboard Cite

show abstract

“…Other related approaches enable global (rather than local) explainability (Malandri et al, 2022), or explanation interfaces for non-transformers models on non-NLP tasks (Agarwal et al, 2022). Other approaches study model behavior at the subgroup level Pastor et al, 2021a,b), focusing more on model evaluation and robustness rather than its interpretation.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

2023

View full text Add to dashboard Cite

Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, lowresource settings such as new and emerging domains would especially benefit from reliable question answering systems. Furthermore, multilingual and cross-lingual resources in emergent domains are scarce, leading to few or no such systems. In this paper, we demonstrate a cross-lingual open-retrieval question answering system for the emergent domain of COVID-19. Our system adopts a corpus of scientific articles to ensure that retrieved documents are reliable. To address the scarcity of cross-lingual training data in emergent domains, we present a method utilizing automatic translation, alignment, and filtering to produce English-to-all datasets. We show that a deep semantic retriever greatly benefits from training on our English-to-all data and significantly outperforms a BM25 baseline in the cross-lingual setting. We illustrate the capabilities of our system with examples and release all code necessary to train and deploy such a system 1 .

show abstract

Contrastive Explanations of Text Classifiers as a Service

Cited by 2 publications

References 13 publications

ferret: a Framework for Benchmarking Explainers on Transformers

ferret: a Framework for Benchmarking Explainers on Transformers

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

Contact Info

Product

Resources

About