United States

Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop SEAL-Shap, an efficient source valuation framework for quantifying the usefulness of the sources (e.g., domains/languages) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.

NAACL 2021

Evaluating the Values of Sources in Transfer Learning

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

technical paper

ENTRUST: Argument Reframing with Language Models and Entailment

Hurdles to Progress in Long-form Question Answering

An Empirical Study on Neural Keyphrase Generation

A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation

Paragraph-level Simplification of Medical Texts

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

Factual Probing Is [MASK]: Learning vs. Learning to Recall

Evaluating Saliency Methods for Neural Language Models

Contextualized Perturbation for Textual Adversarial Attack

DirectProbe: Studying Representations without Classifiers

https://d3smihljt9218e.cloudfront.net/transcript/13659/subtitle/5b7c5ff8f657255616f1595eb3602f2a.vtt

English (automatic)

Evaluating the Values of Sources in Transfer Learning

Downloads

Next from NAACL 2021

ENTRUST: Argument Reframing with Language Models and Entailment

Similar lecture

Finding Concept-specific Biases in Form--Meaning Associations

VIDEO LIBRARY

EVENTS

COMPANY

RESOURCES