Predicting the Success of Domain Adaptation in Text Similarity

TL;DR

This paper investigates how to predict the success of domain adaptation in text similarity tasks by modeling factors influencing adaptation outcomes and selecting optimal source domains using descriptive features and similarity metrics.

Contribution

It introduces a predictive framework for assessing domain adaptation success and source domain selection based on domain features and similarity measures.

Findings

Certain domains show predictable adaptation success

Cross-domain similarity metrics are effective predictors

Some domains remain challenging to predict accurately

Abstract

Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain adaptation. This paper models adaptation success and selection of the most suitable source domains among several candidates in text similarity. We use descriptive domain information and cross-domain similarity metrics as predictive features. While mostly positive, the results also point to some domains where adaptation success was difficult to predict.