Applying Co-Training Methods to Statistical Parsing
نویسنده
چکیده
We propose a novel Co-Training method for statistical parsing. The algorithm takes as input a small corpus (9695 sentences) annotated with parse trees, a dictionary of possible lexicalized structures for each word in the training set and a large pool of unlabeled text. The algorithm iteratively labels the entire data set with parse trees. Using empirical results based on parsing the Wall Street Journal corpus we show that training a statistical parser on the combined labeled and unlabeled data strongly outperforms training only on the labeled data.
منابع مشابه
Corrected Co-training for Statistical Parsers
Corrected co-training (Pierce & Cardie, 2001) and the closely related co-testing (Muslea et al., 2000) are active learning methods which exploit redundant views to reduce the cost of manually creating labeled training data. We extend these methods to statistical parsing algorithms for natural language. Because creating complex parse structures by hand is significantly more timeconsuming than se...
متن کاملWeakly supervised training for parsing Mandarin broadcast transcripts
We present a systematic investigation of applying weakly supervised co-training approaches to improve parsing performance for parsing Mandarin broadcast news (BN) and broadcast conversation (BC) transcripts, by iteratively retraining two competitive Chinese parsers from a small set of treebanked data and a large set of unlabeled data. We compare co-training to self-training, and our results sho...
متن کاملFourth Workshop on Statistical Parsing of Morphologically Rich Languages
We present a number of semi-supervised parsing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semisupervised learning in the form of self-tra...
متن کاملLearning Structured Classifiers for Statistical Dependency Parsing
My research is focused on developing machine learning algorithms for inferring dependency parsers from language data. By investigating several approaches I have developed a unifying perspective that allows me to share advances between both probabilistic and non-probabilistic methods. First, I describe a generative technique that uses a strictly lexicalised parsing model, where all the parameter...
متن کاملExample Selection for Bootstrapping Statistical Parsers
This paper investigates bootstrapping for statistical parsers to reduce their reliance on manually annotated training data. We consider both a mostly-unsupervised approach, co-training, in which two parsers are iteratively re-trained on each other’s output; and a semi-supervised approach, corrected co-training, in which a human corrects each parser’s output before adding it to the training data...
متن کامل