Cascaded Grammatical Relation Assignment
arXiv (Cornell University)Published 2 June 1999Open access
Sabine Buchholz, Jorn Veenstra, Walter Daelemans
Citations74
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
In this paper we discuss cascaded Memory-Based grammatical relations assignment. In the first stages of the cascade, we find chunks of several types (NP,VP,ADJP,ADVP,PP) and label them with their adverbial function (e.g. local, temporal). In the last stage, we assign grammatical relations to pairs of chunks. We studied the effect of adding several levels to this cascaded classifier and we found that even the less performing chunkers enhanced the performance of the relation finder.
Keywords
Computer Science
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Text, speech and language technologyText Chunking Using Transformation-Based Learning
1,257 Citations1999Lance Ramshaw, Mitchell P. Marcus
This work has shown that the transformation-based learning approach can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive “baseNP” chunks.
Studies in linguistics and philosophyParsing By Chunks
878 Citations1991Steven Abney
The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Three generative, lexicalised models for statistical parsing
749 Citations1997Michael Collins
A new statistical parsing model is proposed, which is a generative model of lexicalised context-free grammar and extended to include a probabilistic treatment of both subcategorisation and wh-movement.
Representing text chunks
449 Citations1999Erik F. Tjong Kim Sang, Jorn Veenstra
It is shown that the the data representation choice has a minor influence on chunking performance, however, equipped with the most suitable data representation, the memory-based learning chunker was able to improve the best published chunking results for a standard data set.
arXiv (Cornell University)MBT: A Memory-Based Part of Speech Tagger-Generator
259 Citations1996Walter Daelemans, Jakub Zavrel +2 more
Machine LearningForgetting Exceptions is Harmful in Language Learning
228 Citations1999Walter Daelemans, Antal van den Bosch +1 more
It is shown that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy, and that decision-tree learning often performs worse than memory-based learning.
arXiv (Cornell University)A Linear Observed Time Statistical Parser Based on Maximum Entropy\n Models
145 Citations1997Adwait Ratnaparkhi
arXiv (Cornell University)Memory-Based Shallow Parsing
118 Citations1999Walter Daelemans, Sabine Buchholz +1 more
A memory-based approach to learning shallow natural language patterns
81 Citations1998Shlomo Argamon, Ido Dagan +1 more
A novel memory-based learning method that recognizes shallow patterns in new text based on a bracketed training corpus that enables easy porting to new domains and to sub-language patterns for information extraction.
Light parsing as finite state filtering
65 Citations1999Gregory Grefenstette
A light parsing system using recently created finite state operators for grouping adjacent syntactically related units, and extracting non-ad jacent n-ary grammatical relations is described.
Fast NP Chunking using Memory-Based learning techniques
47 Citations1998Jorn Veenstra
A fast decision tree variant of MBL (IGTree) is applied to fast NP chunking on the dataset described in (Ramshaw and Marcus, 1995), which consists of roughly 50,000 test and 200,000 train items.
Automation of treebank annotation
34 Citations1998Thorsten Brants, Wojciech Skut
This paper describes applications of stochastic and symbolic NLP methods to treebank annotation and focuses on the automation of tree bank annotation, the comparison of conflicting annotations for the same sentence and the automatic detection of inconsistencies.
Distinguishing complements from adjuncts using memory-based learning
20 Citations1998Sabine Buchholz, Brandon Keller
Memory-based learning experiments for the task of distinguishing complements from adjuncts are presented and it is shown that whereas at the level of constituents, PPs are most diicult to classify, at thelevel of frames it is the ditransitive frame that has the highest error rate.
Medical Entomology and ZoologyCorpus-based parsing and sublanguage studies
20 Citations1998Ralph Grishman, Satoshi Sekine
A corpus-based parser and sublanguage techniques were developed to improve the parser's accuracy, including in particular two methods for incorporating lexical information, and some promising cases were found where the parser was able to correct recognition errors.