Pith. sign in

REVIEW 2 cited by

Searching for Optimal Subword Tokenization in Cross-domain NER

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.03352 v1 pith:UA3TEVQK 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
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

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

Forward citations

Cited by 2 Pith papers

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

  1. Multi-Granularity Reasoning for Natural Language Inference

    cs.CL 2026-04 conditional novelty 3.5

    Stacking element-wise multi-layer BERT interactions and DenseNet yields modest NLI gains over BERT/RoBERTa baselines on standard benchmarks.

  2. 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.