Towards a Multi-Representational Treebank

Published 1 November 2008Open access

Fei Xia, Owen Rambow, Rajesh Bhatt, Martha Palmer, Dipti Misra Sharma

Citations34

TL;DR

This paper shows that high-quality DS-to-PS conversion is possible if the conversion process is performed at the designing stage of treebank construction to ensure that all information the authors wish to represent in PS is provided in DS.

Abstract

Computational, descriptive, and theoretical linguistics use both phrase\n(PS) structure and dependency structure (DS) to represent syntax. We believe\nthat the next-generation treebank should be multi-representational, designed\nfor both representations with an automatic conversion. In this paper,\nwe highlight the assumptions made by existing PS-to-DS and DS-to-PS conversion\nalgorithms and show the limitations of these algorithms. We then\npropose a new DS-to-PS conversion algorithm that outperforms existing algorithms\nand allows more flexibility. Our experiments and error analysis\nshow that high-quality DS-to-PS conversion is possible if the conversion process\nis performed at the designing stage of treebank construction to ensure\nthat all information we wish to represent in PS is provided in DS.

Keywords

Computer Science

Building a Large Annotated Corpus of English: The Penn Treebank

7,528 Citations1993Mitchell P. Marcus

Non-projective dependency parsing using spanning tree algorithms

857 Citations2005Ryan McDonald, Fernando Pereira +2 more

Using this representation, the parsing algorithm of Eisner (1996) is sufficient for searching over all projective trees in O(n3) time and is extended naturally to non-projective parsing using Chu-Liu-Edmonds (Chu and Liu, 1965; Edmonds, 1967) MST algorithm, yielding an O( n2) parsing algorithm.

View PDF

Statistical decision-tree models for parsing

533 Citations1995David M. Magerman

SPATTER is described, a statistical parser based on decision-tree learning techniques which constructs a complete parse for every sentence and achieves accuracy rates far better than any published result.

View PDF

MaltParser: A Data-Driven Parser-Generator for Dependency Parsing

466 Citations2006Joakim Nivre, Johan Hall +1 more

MaltParser supports several parsing algorithms and learning algorithms, and allows user-defined feature models, consisting of arbitrary combinations of lexical features, part-of-speech features and dependency features, for dependency parsing.

RECERCAT (Consorci de Serveis Universitaris de Catalunya)Simple Semi-supervised Dependency Parsing

444 Citations2008Terry Koo, Xavier Carreras +1 more

This work focuses on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus, and shows that the cluster-based features yield substantial gains in performance across a wide range of conditions.

View PDF

Converting dependency structures to phrase structures

114 Citations2001Fei Xia, Martha Palmer

This work not only provides ways to convert Treebanks from one type of representation to the other, but also clarifies the differences in representational coverage of the two approaches.

View PDF

Lecture notes in computer scienceThe Current Status of the Prague Dependency Treebank

18 Citations2001Eva Hajičová, Jan Hajič +5 more

The Prague Dependency Treebank project is conceived of as a many-layered scenario, both from the point of view of the stratal annotation scheme, from the division-of-labor points of view, and with regard to the level of detail captured at the highest, tectogrammatical layer.