Effective self-training for parsing
2006
615 citations
Abstract
We present a simple, but surprisingly effective, method of self-training a twophase parser-reranker system using readily available unlabeled data.We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker.Our improved model achieves an f -score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing.Finally, we provide some analysis to better understand the phenomenon.
Keywords
ParsingComputer scienceBootstrapping (finance)Discriminative modelArtificial intelligenceNatural language processingBottom-up parsingTraining setSimple (philosophy)Top-down parsingMachine learningMathematics
Affiliated Institutions
Related Publications
Self-training PCFG grammars with latent annotations across languages
We investigate the effectiveness of self-training PCFG grammars with latent annotations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared...
DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms ...
Enriching Word Vectors with Subword Information
Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore ...
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Human ability to understand language is general, flexible, and robust. In contrast, most NLU models above the word level are designed for a specific task and struggle with out-o...
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning...
Publication Info
- Year
- 2006
- Type
- article
- Pages
- 152-159
- Citations
- 615
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
615
OpenAlex
Cite This
David McClosky,
Eugene Charniak,
Mark Johnson
(2006).
Effective self-training for parsing.
, 152-159.
https://doi.org/10.3115/1220835.1220855
Identifiers
- DOI
- 10.3115/1220835.1220855