SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.10315 · ACL Findings · 2022

Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

Yang Li, Min Zhang, Zhenghua Li, Houquan Zhou

arXiv · PDF · Open in the Atlas

Code that ran

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks. But, in the unsupervised POS tagging task, works utilizing PLMs are few and fail to achieve stateof-the-art (SOTA) performance. The recent SOTA performance is yielded by a Guassian HMM variant proposed by He et al. (2018). However, as a generative model, HMM makes very strong independence assumptions, making it very challenging to incorporate contexualized word representations from PLMs. In this work, we for the first time propose a neural conditional random field autoencoder (CRF-AE) model for unsupervised POS tagging. The discriminative encoder of CRF-AE can straightforwardly incorporate PLM word representations. Moreover, inspired by featurerich HMM, we reintroduce hand-crafted features into the decoder of CRF-AE. Finally, experiments clearly show that our model outperforms previous state-of-the-art models by a large margin on Penn Treebank and multilingual Universal Dependencies treebank v2.0.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.10315")
get_code_for_paper("2203.10315")
have("2203.10315")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.10315.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.10315.svg)](https://syntology.ai/paper/2203.10315)

Connect an agent — have() is free.