ترغب بنشر مسار تعليمي؟ اضغط هنا

Post-hoc Interpretability for Neural NLP: A Survey

137   0   0.0 ( 0 )
 نشر من قبل Andreas Madsen
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Natural Language Processing (NLP) models have become increasingly more complex and widespread. With recent developments in neural networks, a growing concern is whether it is responsible to use these models. Concerns such as safety and ethics can be partially addressed by providing explanations. Furthermore, when models do fail, providing explanations is paramount for accountability purposes. To this end, interpretability serves to provide these explanations in terms that are understandable to humans. Central to what is understandable is how explanations are communicated. Therefore, this survey provides a categorization of how recent interpretability methods communicate explanations and discusses the methods in depth. Furthermore, the survey focuses on post-hoc methods, which provide explanations after a model is learned and generally model-agnostic. A common concern for this class of methods is whether they accurately reflect the model. Hence, how these post-hoc methods are evaluated is discussed throughout the paper.



قيم البحث

اقرأ أيضاً

The attention layer in a neural network model provides insights into the models reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the interpretability of at tention weights (Jain & Wallace, 2019; Vig & Belinkov, 2019). Amid such confusion arises the need to understand attention mechanism more systematically. In this work, we attempt to fill this gap by giving a comprehensive explanation which justifies both kinds of observations (i.e., when is attention interpretable and when it is not). Through a series of experiments on diverse NLP tasks, we validate our observations and reinforce our claim of interpretability of attention through manual evaluation.
Post-hoc model-agnostic interpretation methods such as partial dependence plots can be employed to interpret complex machine learning models. While these interpretation methods can be applied regardless of model complexity, they can produce misleadin g and verbose results if the model is too complex, especially w.r.t. feature interactions. To quantify the complexity of arbitrary machine learning models, we propose model-agnostic complexity measures based on functional decomposition: number of features used, interaction strength and main effect complexity. We show that post-hoc interpretation of models that minimize the three measures is more reliable and compact. Furthermore, we demonstrate the application of these measures in a multi-objective optimization approach which simultaneously minimizes loss and complexity.
Today, interpretability of Black-Box Natural Language Processing (NLP) models based on surrogates, like LIME or SHAP, uses word-based sampling to build the explanations. In this paper we explore the use of sentences to tackle NLP interpretability. Wh ile this choice may seem straight forward, we show that, when using complex classifiers like BERT, the word-based approach raises issues not only of computational complexity, but also of an out of distribution sampling, eventually leading to non founded explanations. By using sentences, the altered text remains in-distribution and the dimensionality of the problem is reduced for better fidelity to the black-box at comparable computational complexity.
We review the cost of training large-scale language models, and the drivers of these costs. The intended audience includes engineers and scientists budgeting their model-training experiments, as well as non-practitioners trying to make sense of the e conomics of modern-day Natural Language Processing (NLP).
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves. In recent years, the re is a surge of research on neural network calibration and the majority of the works can be categorized into post-hoc calibration methods, defined as methods that learn an additional function to calibrate an already trained base network. In this work, we intend to understand the post-hoc calibration methods from a theoretical point of view. Especially, it is known that minimizing Negative Log-Likelihood (NLL) will lead to a calibrated network on the training set if the global optimum is attained (Bishop, 1994). Nevertheless, it is not clear learning an additional function in a post-hoc manner would lead to calibration in the theoretical sense. To this end, we prove that even though the base network ($f$) does not lead to the global optimum of NLL, by adding additional layers ($g$) and minimizing NLL by optimizing the parameters of $g$ one can obtain a calibrated network $g circ f$. This not only provides a less stringent condition to obtain a calibrated network but also provides a theoretical justification of post-hoc calibration methods. Our experiments on various image classification benchmarks confirm the theory.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا