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.
Keywords
TreebankComputer scienceParsingArtificial intelligenceIndependence (probability theory)GrammarNatural language processingSimple (philosophy)State (computer science)AlgorithmMathematicsLinguistics
Affiliated Institutions
Related Publications
Fast Exact Inference with a Factored Model for Natural Language Parsing
We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. ...
Learning accurate, compact, and interpretable tree annotation
We present an automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank. Starti...
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. Further progress towards understanding compositionality in tasks...
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural archit...
Parsing Natural Scenes and Natural Language with Recursive Neural Networks
Recursive structure is commonly found in the inputs of different modalities such as natural scene images or natural language sentences. Discovering this recursive structure help...
Publication Info
- Year
- 2003
- Type
- article
- Volume
- 1
- Pages
- 423-430
- Citations
- 3042
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3042
OpenAlex
Cite This
Dan Klein,
Christopher D. Manning
(2003).
Accurate unlexicalized parsing.
, 1
, 423-430.
https://doi.org/10.3115/1075096.1075150
Identifiers
- DOI
- 10.3115/1075096.1075150