.png){kind=icon}
返回
Deep Contextualized Self-training for Low Resource Dependency Parsing
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00294.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, which is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser's output when applied to unlabeled data, and integrates these models with the base parser through a gating mechanism. We conduct experiments across multiple languages, both in low resource in-domain and in cross-domain setups, and demonstrate that DCST substantially outperforms traditional self-training as well as recent semi-supervised training methods.(1)
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
Two Highly Conserved Cysteine Residues in HPV16 L2 Form an Intramolecular Disulfide Bond and Are Critical for Infectivity in Human Keratinocytes.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏Cobalt and Copper Composite Oxides as Efficient Catalysts for Preferential Oxidation of CO in H2-Rich Stream钴和铜复合氧化物作为H2-Rich流中CO优先氧化的有效催化剂
PREAI
分享收藏
查看更多内容