Kun Xu, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu, Zhao Zhang, Guang-Yuan Hao, Linlin Li, Yuyang Zhang, Baojun Wang
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.
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause excessive matching noise and problems of frequent updates. In this paper, we propose DyLex, a plug-in lexicon incorporation approach for BERT based sequence labeling tasks. Instead of leveraging embeddings of words in the lexicon as in conventional methods, we adopt word-agnostic tag embeddings to avoid re-training the representation while updating the lexicon. Moreover, we employ an effective supervised lexical knowledge denoising method to smooth out matching noise. Finally, we introduce a col-wise attention based knowledge fusion mechanism to guarantee the pluggability of the proposed framework. Experiments on ten datasets of three tasks show that the proposed framework achieves new SOTA, even with very large scale lexicons 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.08818")
get_code_for_paper("2109.08818")
have("2109.08818")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.08818.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.08818)
Connect an agent — have() is free.