Incremental Parsing with the Perceptron Algorithm
Michael Collins,Brian Roark +1 more
- pp 111-118
Reads0
Chats0
TLDR
It is demonstrated that training a perceptron model to combine with the generative model during search provides a 2.1 percent F-measure improvement over the Generative model alone, to 88.8 percent.Abstract:
This paper describes an incremental parsing approach where parameters are estimated using a variant of the perceptron algorithm. A beam-search algorithm is used during both training and decoding phases of the method. The perceptron approach was implemented with the same feature set as that of an existing generative model (Roark, 2001a), and experimental results show that it gives competitive performance to the generative model on parsing the Penn treebank. We demonstrate that training a perceptron model to combine with the generative model during search provides a 2.1 percent F-measure improvement over the generative model alone, to 88.8 percent.read more
Citations
More filters
Proceedings ArticleDOI
Moses: Open Source Toolkit for Statistical Machine Translation
Philipp Koehn,Hieu Hoang,Alexandra Birch,Chris Callison-Burch,Marcello Federico,Nicola Bertoldi,Brooke Cowan,Wade Shen,C. Corbett Moran,Richard Zens,Chris Dyer,Ondrej Bojar,Alexandra Elena Constantin,Evan Herbst +13 more
TL;DR: An open-source toolkit for statistical machine translation whose novel contributions are support for linguistically motivated factors, confusion network decoding, and efficient data formats for translation models and language models.
Proceedings Article
Scheduled sampling for sequence prediction with recurrent Neural networks
TL;DR: This work proposes a curriculum learning strategy to gently change the training process from a fully guided scheme using the true previous token, towards a less guided scheme which mostly uses the generated token instead.
Proceedings ArticleDOI
Online Large-Margin Training of Dependency Parsers
TL;DR: An effective training algorithm for linearly-scored dependency parsers that implements online large-margin multi-class training on top of efficient parsing techniques for dependency trees is presented.
Proceedings Article
Grammar as a foreign language
TL;DR: The domain agnostic attention-enhanced sequence-to-sequence model achieves state-of-the-art results on the most widely used syntactic constituency parsing dataset, when trained on a large synthetic corpus that was annotated using existing parsers.
Proceedings Article
Online Learning of Approximate Dependency Parsing Algorithms.
Ryan McDonald,Fernando Pereira +1 more
TL;DR: This paper extends the maximum spanning tree dependency parsing framework to incorporate higher-order feature representations and allow dependency structures with multiple parents per word, and shows that those extensions can make the MST framework computationally intractable, but that the intractability can be circumvented with new approximate parsing algorithms.
References
More filters
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Proceedings ArticleDOI
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms
TL;DR: Experimental results on part-of-speech tagging and base noun phrase chunking are given, in both cases showing improvements over results for a maximum-entropy tagger.
Journal ArticleDOI
An efficient boosting algorithm for combining preferences
TL;DR: This work describes and analyze an efficient algorithm called RankBoost for combining preferences based on the boosting approach to machine learning, and gives theoretical results describing the algorithm's behavior both on the training data, and on new test data not seen during training.
Proceedings Article
An Efficient Boosting Algorithm for Combining Preferences
TL;DR: RankBoost as discussed by the authors is an algorithm for combining preferences based on the boosting approach to machine learning, which can be applied to several applications, such as that of combining the results of different search engines, or the "collaborative filtering" problem of ranking movies for a user based on movie rankings provided by other users.