paper-with-me

Papers

A framework for (under)specifying dependency syntax without overloading annotators

2013-06-10 · WS 2013 8 · Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge

We introduce a framework for lightweight dependency syntax annotation. Our formalism builds upon the typical representation for unlabeled dependencies, permitting a simple notation and annotation workflow. Moreover, the formalism encourages annotators to underspecify parts of the syntax if doing so would streamline the annotation process. We demonstrate the efficacy of this annotation on three languages and develop algorithms to evaluate and compare underspecified annotations.

📄 PDF Abstract BibTeX arXiv:1306.2091

Code (1)

brendano/gfl_syntax 공식 구현

Similar Papers 제목 키워드 기반

Specifying Treebanks, Outsourcing Parsebanks: FinnTreeBank 3

2012-05-01 · LREC 2012 5 · Atro Voutilainen, Kristiina Muhonen, Tanja Purtonen, Krister Lind{\'e}n

Corpus-based treebank annotation is known to result in incomplete coverage of mid- and low-frequency linguistic constructions: the linguistic representation and corpus annotation quality are sometimes suboptimal. Large d…

Descriptive

Source Dependency-Aware Transformer with Supervised Self-Attention

2019-09-05 · Chengyi Wang, Shuangzhi Wu, Shujie Liu

Recently, Transformer has achieved the state-of-the-art performance on many machine translation tasks. However, without syntax knowledge explicitly considered in the encoder, incorrect context information that violates t…

Machine TranslationTranslation

FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction

2024-03-04 · XUDONG ZHU, Zhao Kang, Bei Hui

Document-level Relation Extraction (DocRE) aims to identify relation labels between entities within a single document. It requires handling several sentences and reasoning over them. State-of-the-art DocRE methods use a …

Document-level Relation ExtractionRelationRelation ExtractionSentence

A Structured Syntax-Semantics Interface for English-AMR Alignment

2018-06-01 · NAACL 2018 6 · Ida Szubert, Adam Lopez, Nathan Schneider

Abstract Meaning Representation (AMR) annotations are often assumed to closely mirror dependency syntax, but AMR explicitly does not require this, and the assumption has never been tested. To test it, we devise an expres…

Abstract Meaning RepresentationAMR Parsing

Is syntax structure modeling worth? Leveraging pattern-driven modeling to enable affordable sentiment dependency learning

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Is structure information modeling really worth in Aspect-based sentiment classification (ABSC)? Recent popular works tend to exploit syntactic information guiding sentiment dependency parsing, i.e., structure-based senti…

Dependency ParsingSentiment AnalysisSentiment ClassificationSentiment Dependency Learning