Zobrazeno 1 - 10
of 170
pro vyhledávání: '"Ebert, Sebastian"'
Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases an input salience method, which highlights the most important parts of the input, may reveal problematic reasoning.
Externí odkaz:
http://arxiv.org/abs/2211.05485
Feature attribution a.k.a. input salience methods which assign an importance score to a feature are abundant but may produce surprisingly different results for the same model on the same input. While differences are expected if disparate definitions
Externí odkaz:
http://arxiv.org/abs/2111.07367
Recently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP). A central research topic has been the investigation of search algorithms and search constraints, accompanied by benchmark algorith
Externí odkaz:
http://arxiv.org/abs/2109.07926
Gorman and Bedrick (2019) argued for using random splits rather than standard splits in NLP experiments. We argue that random splits, like standard splits, lead to overly optimistic performance estimates. We can also split data in biased or adversari
Externí odkaz:
http://arxiv.org/abs/2005.00636
Publikováno v:
In Journal of Economic Behavior and Organization November 2023 215:292-306
Embeddings are generic representations that are useful for many NLP tasks. In this paper, we introduce DENSIFIER, a method that learns an orthogonal transformation of the embedding space that focuses the information relevant for a task in an ultraden
Externí odkaz:
http://arxiv.org/abs/1602.07572
Understanding open-domain text is one of the primary challenges in natural language processing (NLP). Machine comprehension benchmarks evaluate the system's ability to understand text based on the text content only. In this work, we investigate machi
Externí odkaz:
http://arxiv.org/abs/1602.04341
Publikováno v:
In Journal of Economic Theory September 2020 189