1 |
Learning to Explain: Generating Stable Explanations Fast ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.415 Abstract: The importance of explaining the outcome of a machine learning model, especially a black-box model, is widely acknowledged. Recent approaches explain an outcome by identifying the contributions of input features to this outcome. In environments involving large black-box models or complex inputs, this leads to computationally demanding algorithms. Further, these algorithms often suffer from low stability, with explanations varying significantly across similar examples. In this paper, we propose a Learning to Explain (L2E) approach that learns the behaviour of an underlying explanation algorithm simultaneously from all training examples. Once the explanation algorithm is distilled into an explainer network, it can be used to explain new instances. Our experiments on three classification tasks, which compare our approach to six explanation algorithms, show that L2E is between 5 and 7.5×10^4 times faster than these algorithms, while generating ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://underline.io/lecture/25839-learning-to-explain-generating-stable-explanations-fast https://dx.doi.org/10.48448/qw95-9969
|
|
BASE
|
|
Hide details
|
|
3 |
DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Assessing Social License to Operate from the Public Discourse on Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Recognising Agreement and Disagreement between Stances with Reason Comparing Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Catering to your concerns: Automatic generation of personalised security-centric descriptions for Android apps
|
|
|
|
In: ACM Transactions on Cyber-Physical Systems, Vol. 3, no. 4 (Sep 2019), article no. 36 (2019)
|
|
BASE
|
|
Show details
|
|
8 |
Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Cross-Target Stance Classification with Self-Attention Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Catering to Your Concerns: Automatic Generation of Personalised Security-Centric Descriptions for Android Apps ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Evaluating the Usability of a Controlled Language Authoring Assistant
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 147-158 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Query-oriented evidence extraction to support evidence-based medicine practice
|
|
|
|
BASE
|
|
Show details
|
|
14 |
A Corpus for research in text processing for evidence based medicine
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Focused and aggregated search: A perspective from natural language generation
|
|
|
|
In: Information Retrieval (2015)
|
|
BASE
|
|
Show details
|
|
16 |
Focused and aggregated search: A perspective from natural language generation
|
|
|
|
In: Information Retrieval (2015)
|
|
BASE
|
|
Show details
|
|
19 |
Spanning tree approaches for statistical sentence generation
|
|
|
|
BASE
|
|
Show details
|
|
|
|