Fill it up: Exploiting partial dependency annotations in a minimum spanning tree parser

2016-11-26 · Liang Sun, Jason Mielens, Jason Baldridge

Unsupervised models of dependency parsing typically require large amounts of clean, unlabeled data plus gold-standard part-of-speech tags. Adding indirect supervision (e.g. language universals and rules) can help, but we show that obtaining small amounts of direct supervision - here, partial dependency annotations - provides a strong balance between zero and full supervision. We adapt the unsupervised ConvexMST dependency parser to learn from partial dependencies expressed in the Graph Fragment Language. With less than 24 hours of total annotation, we obtain 7% and 17% absolute improvement in unlabeled dependency scores for English and Spanish, respectively, compared to the same parser using only universal grammar constraints.

📄 PDF Abstract BibTeX arXiv:1611.08765

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency Parsing

Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations

2020-12-01 · COLING 2020 8 · Yash Kankanampati, Joseph Le Roux, Nadi Tomeh, Dima Taji 외

In this paper we present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations which is the case in Arabic, with the availability of CATiB and UD t…

ARC Dependency Parsing

Exploiting Partial Annotations with EM Training

2012-06-01 · WS 2012 6 · Dirk Hovy, Eduard Hovy

A gentle tutorial and a structured reformulation of Bock's algorithm for minimum directed spanning trees

2026-03-29 · Yuxi Wang, Jungyeul Park arxiv

This paper presents a gentle tutorial and a structured reformulation of Bock's 1971 Algol procedure for constructing minimum directed spanning trees. Our aim is to make the original algorithm readable and reproducible fo…

Dependency Parsing

Validation Issues induced by an Automatic Pre-Annotation Mechanism in the Building of Non-projective Dependency Treebanks

2014-05-01 · LREC 2014 5 · Oph{\'e}lie Lacroix, Denis B{\'e}chet

In order to build large dependency treebanks using the CDG Lab, a grammar-based dependency treebank development tool, an annotator usually has to fill a selection form before parsing. This step is usually necessary becau…

Dependency Parsing Form

Dependency Parsing with Partial Annotations: An Empirical Comparison

2017-11-01 · IJCNLP 2017 11 · Yue Zhang, Zhenghua Li, Jun Lang, Qingrong Xia 외

This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA). The first approach is based on a forest-based training objective for two CRF parsers, i.e., a biaffin…

Active Learning Dependency Parsing