pith. sign in

arxiv: 2206.03352 · v1 · pith:UA3TEVQKnew · submitted 2022-06-07 · 💻 cs.CL · cs.AI

Searching for Optimal Subword Tokenization in Cross-domain NER

classification 💻 cs.CL cs.AI
keywords inputcross-domaindistributionapproachapproachesdirldistributionsdomain
0
0 comments X
read the original abstract

Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into similar feature distributions. However, these approaches ignore the direct alignment of input word distributions between domains, which is a vital factor in word-level classification tasks such as cross-domain NER. In this work, we shed new light on cross-domain NER by introducing a subword-level solution, X-Piece, for input word-level distribution shift in NER. Specifically, we re-tokenize the input words of the source domain to approach the target subword distribution, which is formulated and solved as an optimal transport problem. As this approach focuses on the input level, it can also be combined with previous DIRL methods for further improvement. Experimental results show the effectiveness of the proposed method based on BERT-tagger on four benchmark NER datasets. Also, the proposed method is proved to benefit DIRL methods such as DANN.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization

    cs.CL 2026-04 unverdicted novelty 3.0

    The paper claims a selective fine-tuning method that identifies and freezes core parameters to mitigate catastrophic forgetting in LLMs while improving domain adaptation, shown in experiments with GPT-J and LLaMA-3.