CLLGAug 25, 2020

A simple method for domain adaptation of sentence embeddings

arXiv:2008.11228v1
Originality Incremental advance
AI Analysis

This work addresses the challenge of over-adaptation in domain-specific NLP tasks, offering a more robust solution for practitioners, though it is incremental as it builds on existing embedding methods.

The paper tackles the problem of domain adaptation for pre-trained sentence embeddings by proposing a simple universal method using a Siamese architecture to finetune Google's Universal Sentence Encoder, showing improved results compared to traditional finetuning across various datasets.

Pre-trained sentence embeddings have been shown to be very useful for a variety of NLP tasks. Due to the fact that training such embeddings requires a large amount of data, they are commonly trained on a variety of text data. An adaptation to specific domains could improve results in many cases, but such a finetuning is usually problem-dependent and poses the risk of over-adapting to the data used for adaptation. In this paper, we present a simple universal method for finetuning Google's Universal Sentence Encoder (USE) using a Siamese architecture. We demonstrate how to use this approach for a variety of data sets and present results on different data sets representing similar problems. The approach is also compared to traditional finetuning on these data sets. As a further advantage, the approach can be used for combining data sets with different annotations. We also present an embedding finetuned on all data sets in parallel.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes