1 |
Shared computational principles for language processing in humans and deep language models
|
|
|
|
In: Nat Neurosci (2022)
|
|
BASE
|
|
Show details
|
|
2 |
CausaLM: Causal Model Explanation Through Counterfactual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Model Compression for Domain Adaptation through Causal Effect Estimation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
CausaLM: Causal Model Explanation Through Counterfactual Language Models ...
|
|
|
|
Abstract:
Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the generation of counterfactual examples, which is challenging with existing generation technology. To bridge that gap, we propose CausaLM, a framework for producing causal model explanations using counterfactual language representation models. Our approach is based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem. Concretely, we show that by ... : Our code and data are available at: https://amirfeder.github.io/CausaLM/ Accepted for publication in Computational Linguistics journal ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2005.13407 https://arxiv.org/abs/2005.13407
|
|
BASE
|
|
Hide details
|
|
6 |
Predicting In-game Actions from Interviews of NBA Players ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|