Accurate Unlexicalized Parsing
Dan Klein,Christopher D. Manning +1 more
- 07 Jul 2003
- pp 423-430
TL;DR: It is demonstrated that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar.
read more
Abstract: We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar. Indeed, its performance of 86.36% (LP/LR F1) is better than that of early lexicalized PCFG models, and surprisingly close to the current state-of-the-art. This result has potential uses beyond establishing a strong lower bound on the maximum possible accuracy of unlexicalized models: an unlexicalized PCFG is much more compact, easier to replicate, and easier to interpret than more complex lexical models, and the parsing algorithms are simpler, more widely understood, of lower asymptotic complexity, and easier to optimize.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Automated extraction of bio-entity relationships from literature
Jinfeng Zhang
- 20 Aug 2013
TL;DR: In this paper, a graph theoretic algorithm is used to extract information from text based on natural language processing (NLP) and graph theory for extracting protein-protein relationships in biomedical literature, such as proteins, genes, pathways, diseases and drugs.
21
•Dissertation
Schema-agnostic queries for large-schema databases: A distributional semantics approach
André Freitas
- 01 May 2015
TL;DR: This work aims at proposing a complementary semantic model for databases, based on distributional semantic models, which provides a complementary perspective to the formal perspective of database semantics, which supports semantic approximation as a first-class database operation.
21
Building an English-Vietnamese Bilingual Corpus for Machine Translation
Quoc Hung Ngo,Werner Winiwarter +1 more
- 13 Nov 2012
TL;DR: This paper presents research on building an English-Vietnamese parallel corpus, which is constructed for building a Vietnamese-English machine translation system, and describes the specification of collecting data for the corpus, linguistic tagging, bilingual annotation, and the tools specially developed for the manual annotation.
21
Better Binarization for the CKY Parsing
Xinying Song,Shilin Ding,Chin-Yew Lin +2 more
- 25 Oct 2008
TL;DR: Experimental results not only show that different binarizations have great impacts on parsing efficiency, but also confirm that the learnt binarization outperforms other existing methods.
21
•Journal Article
The Multimedia-Based Learning System Improved Cognitive Skills and Motivation of Disabled Children with a Very High Rate.
TL;DR: A multimedia-based learning system to teach children with intellectual disabilities (ID) the basic living and science concepts is proposed and has shown a considerable improvement in the learning process and allowed the children with ID to improve their cognitive skills and become more proactive in the classroom.
21
References
Aspects of the Theory of Syntax
Ann S. Ferebee,Noam Chomsky +1 more
TL;DR: Methodological preliminaries of generative grammars as theories of linguistic competence; theory of performance; organization of a generative grammar; justification of grammar; descriptive and explanatory theories; evaluation procedures; linguistic theory and language learning.
12.5K
The Mental representation of grammatical relations
TL;DR: In this article, twelve articles are grouped into three sections, as follows: "I. Syntactic Representation: " Lexical-Functional Grammar: A Formal Theory for Grammatical Representation (R. Kaplan and J. Bresnan); Control and Complementation (J.Bresnan).
Head-Driven Statistical Models for Natural Language Parsing
TL;DR: Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree.
•Proceedings Article
A maximum-entropy-inspired parser
Eugene Charniak
- 29 Apr 2000
TL;DR: A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
1.8K
Statistical Decision-Tree Models for Parsing
David M. Magerman
- 26 Jun 1995
TL;DR: SPATTER as discussed by the authors is 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, which is based on the following premises: (1) grammars are too complex and detailed to develop manually for most interesting domains; parsing models must rely heavily on lexical and contextual information to analyze sentences accurately; and existing n-gram modeling techniques are inadequate for parsing models.
659