paper-with-me

Papers

Joining Hands: Exploiting Monolingual Treebanks for Parsing of Code-mixing Data

2017-03-31 · EACL 2017 4 · Irshad Ahmad Bhat, Riyaz Ahmad Bhat, Manish Shrivastava, Dipti Misra Sharma

In this paper, we propose efficient and less resource-intensive strategies for parsing of code-mixed data. These strategies are not constrained by in-domain annotations, rather they leverage pre-existing monolingual annotated resources for training. We show that these methods can produce significantly better results as compared to an informed baseline. Besides, we also present a data set of 450 Hindi and English code-mixed tweets of Hindi multilingual speakers for evaluation. The data set is manually annotated with Universal Dependencies.

📄 PDF Abstract BibTeX arXiv:1703.10772

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning

2016-06-03 · Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain syntactic knowledge that is potential to benefit ea…

Dependency ParsingMulti-Task Learning

A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks

2016-12-01 · COLING 2016 12 · Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain common syntactic knowledge that is potential to ben…

Dependency ParsingInformation RetrievalMulti-Task Learning

German and English Treebanks and Lexica for Tree-Adjoining Grammars

2012-05-01 · LREC 2012 5 · Miriam Kaeshammer, Vera Demberg

We present a treebank and lexicon for German and English, which have been developed for PLTAG parsing. PLTAG is a psycholinguistically motivated, incremental version of tree-adjoining grammar (TAG). The resources are how…

Language ModellingTAG

Cross-lingual Universal Dependency Parsing Only from One Monolingual Treebank

2020-12-24 · Kailai Sun, Zuchao Li, Hai Zhao

Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we …

Cross-Lingual TransferDependency ParsingDomain AdaptationLanguage Modeling+2

Exploiting Multiple Treebanks for Parsing with Quasi-synchronous Grammars

2012-07-01 · ACL 2012 7 · Zhenghua Li, Ting Liu, Wanxiang Che
Information Retrieval