Semi-supervised Domain Adaptation for Dependency Parsing
During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data. However, unsupervised approaches make limited progress so far due to the intrinsic difficulty of both domain adaptation and parsing. This paper tackles the semi-supervised domain adaptation problem for Chinese dependency parsing, based on two newly-annotated large-scale domain-aware datasets. We propose a simple domain embedding approach to merge the source- and target-domain training data, which is shown to be more effective than both direct corpus concatenation and multi-task learning. In order to utilize unlabeled target-domain data, we employ the recent contextualized word representations and show that a simple fine-tuning procedure can further boost cross-domain parsing accuracy by large margin.
Code (1)
Tasks
Chinese Dependency ParsingDependency ParsingDomain AdaptationMulti-Task LearningSemi-supervised Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Semi-Supervised Methods for Out-of-Domain Dependency Parsing
Dependency parsing is one of the important natural language processing tasks that assigns syntactic trees to texts. Due to the wider availability of dependency corpora and improved parsing and machine learning techniques…
Dependency ParsingAdapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing
One of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, but there is so …
Dependency ParsingDiscourse Parsing半监督跨领域语义依存分析技术研究(Semi-supervised Domain Adaptation for Semantic Dependency Parsing)
近年来,尽管深度学习给语义依存分析带来了长足的进步,但由于语义依存分析数据标注代价非常高昂,并且在单领域上性能较好的依存分析器迁移到其他领域时,其性能会大幅度下降。因此为了使其走向实用,就必须解决领域适应问题。本文提出一个新的基于对抗学习的领域适应依存分析模型,我们提出了基于对抗学习的共享双编码器结构,并引入领域私有辅助任务和正交约束,同时也探究了多种预训练模型在跨领域依存分析任务上的效果和性能。
Dependency ParsingDomain AdaptationSemantic Dependency ParsingSemi-supervised Domain AdaptationSemi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
Supervised parsing models have achieved impressive results on in-domain texts. However, their performances drop drastically on out-of-domain texts due to the data distribution shift. The shared-private model has shown it…
Dependency ParsingDomain AdaptationSemi-supervised Domain AdaptationNeural Network based Deep Transfer Learning for Cross-domain Dependency Parsing
In this paper, we describe the details of the neural dependency parser sub-mitted by our team to the NLPCC 2019 Shared Task of Semi-supervised do-main adaptation subtask on Cross-domain Dependency Parsing. Our system is …
Dependency ParsingTransfer Learning