mlsanityData to 7 Oct 2026

The Role of Explanatory Value in Natural Language Processing

arXiv 2209.06169 ↗First posted 13 Sep 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

A key aim of science is explanation, yet the idea of explaining language phenomena has taken a backseat in mainstream Natural Language Processing (NLP) and many other areas of Artificial Intelligence. I argue that explanation of linguistic behaviour should be a main goal of NLP, and that this is not the same as making NLP models explainable. To illustrate these ideas, some recent models of human language production are compared with each other. I conclude by asking what it would mean for NLP research and institutional policies if our community took explanatory value seriously, while heeding some possible pitfalls.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 75 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

17 of 75 references.

References · 17

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2016Modeling Context in Referring Expressionscited by 1,054
  5. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  6. 2018nocaps: novel object captioning at scalecited by 444
  7. 2021Causal Abstractions of Neural Networkscited by 401
  8. 2016Rationalizing Neural Predictionscited by 281
  9. 2020Evaluation of Text Generation: A Surveycited by 275
  10. 2020Information-Theoretic Probing with Minimum Description Lengthcited by 230
  11. 2020A Survey of Evaluation Metrics Used for NLG Systemscited by 164
  12. 2017Comprehension-guided referring expressionscited by 52
5 more
  1. 2017Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Studycited by 46
  2. 2019When redundancy is useful: A Bayesian approach to 'overinformative' referring expressionscited by 21
  3. 2022Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systemscited by 7
  4. 2019Referring Expression Generation Using Entity Profilescited by 6
  5. 2021What can Neural Referential Form Selectors Learn?cited by 4

Built on by

Not cited yet.