Wei Wu, Xin Zhou, Tao Gui, Ruotian Ma, Di Liang, Sirui Wang, Xuanting Chen, Yiding Tan, J ##lian Kat ##arina Dec ##hy, Julian Lil ##iana Kathy, Julian Liliana, Katarina Jlian, and 1 more
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.03352")
get_code_for_paper("2206.03352")
have("2206.03352")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2206.03352.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2206.03352)
Connect an agent — have() is free.