Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContrastive Explanations for Model Interpretability
تفسيرات تناقض لتفسير النموذج
131
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توضيحات تناقض توضيح سبب حدوث حدث قد حدث على عكس آخر.إنهم بطبيعتهم بديهية للبشر لكل من الإنتاج والفهم.نقترح طريقة لإنتاج تفسيرات صغيرة في الفضاء الكامن، من خلال إسقاط تمثيل الإدخال، بحيث يتم التقاط الميزات التي تفرق إلا عن قرارات محتملة.يسمح التعديل لدينا بسلوك نموذجي للنظر في التفكير المتعرج فقط، والكشف عن جوانب المدخلات مفيدة لقرارات ومعاكضة معينة.يمكن أن تجيب تفسيراتنا الصنع للإجابة على أي تسمية، ومعها الملصق البدائل، هي ميزة إدخال معينة مفيدة.نحن ننتج تفسيرات صغيرة عبر كل من إسناد مفهوم مجردة رفيع المستوى ومستوى المدخلات / المدخلات منخفضة المستوى لإسناد معايير تصنيف NLP.توضح نتائجنا قدرة التفسيرات على نطاق واسع لتوفير إمكانية الترجمة الترجمة الفورية للقرارات النموذجية.
Contrastive explanations clarify why an event occurred in contrast to another. They are inherently intuitive to humans to both produce and comprehend. We propose a method to produce contrastive explanations in the latent space, via a projection of the input representation, such that only the features that differentiate two potential decisions are captured. Our modification allows model behavior to consider only contrastive reasoning, and uncover which aspects of the input are useful for and against particular decisions. Our contrastive explanations can additionally answer for which label, and against which alternative label, is a given input feature useful. We produce contrastive explanations via both high-level abstract concept attribution and low-level input token/span attribution for two NLP classification benchmarks. Our findings demonstrate the ability of label-contrastive explanations to provide fine-grained interpretability of model decisions.
References used
https://aclanthology.org/
rate research
Read More
Ideally, people who navigate together in a complex indoor space share a mental model that facilitates explanation. This paper reports on a robot control system whose cognitive world model is based on spatial affordances that generalize over its perce
ptual data. Given a target, the control system formulates multiple plans, each with a model-relevant metric, and selects among them. As a result, it can provide readily understandable natural language about the robot's intentions and confidence, and generate diverse, contrastive explanations that reference the acquired spatial model. Empirical results in large, complex environments demonstrate the robot's ability to provide human-friendly explanations in natural language.
In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank
-- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive exp
lanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.
Although neural models have shown strong performance in datasets such as SNLI, they lack the ability to generalize out-of-distribution (OOD). In this work, we formulate a few-shot learning setup and examine the effects of natural language explanation
s on OOD generalization. We leverage the templates in the HANS dataset and construct templated natural language explanations for each template. Although generated explanations show competitive BLEU scores against ground truth explanations, they fail to improve prediction performance. We further show that generated explanations often hallucinate information and miss key elements that indicate the label.
Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the
need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
