Using Web-scale N-grams to Improve Base NP Parsing Performance
نویسندگان
چکیده
We use web-scale N-grams in a base NP parser that correctly analyzes 95.4% of the base NPs in natural text. Web-scale data improves performance. That is, there is no data like more data. Performance scales log-linearly with the number of parameters in the model (the number of unique N-grams). The web-scale N-grams are particularly helpful in harder cases, such as NPs that contain conjunctions.
منابع مشابه
Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing
In this paper, we present a novel approach which incorporates the web-derived selectional preferences to improve statistical dependency parsing. Conventional selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This paper extends previous work to wordto-word selectional preferences by using webscale d...
متن کاملWeb-scale Surface and Syntactic n-gram Features for Dependency Parsing
We develop novel firstand second-order features for dependency parsing based on the Google Syntactic Ngrams corpus, a collection of subtree counts of parsed sentences from scanned books. We also extend previous work on surface n-gram features from Web1T to the Google Books corpus and from first-order to second-order, comparing and analysing performance over newswire and web treebanks. Surface a...
متن کاملModeling Common Real-Word Relations Using Triples Extracted from n-Grams
In this paper, we present an approach providing generalized relations for automatic ontology building based on frequent word n-grams. Using publicly available Google n-grams as our data source we can extract relations in form of triples and compute generalized and more abstract models. We propose an algorithm for building abstractions of the extracted triples using WordNet as background knowled...
متن کاملExperiments in Base-NP Chunking and Its Role in Dependency Parsing for Thai
This paper studies the role of base-NP information in dependency parsing for Thai. The baseline performance reveals that the base-NP chunking task for Thai is much more difficult than those of some languages (like English). The results show that the parsing performance can be improved (from 60.30% to 63.74%) with the use of base-NP chunk information, although the best chunker is still far from ...
متن کاملCreating Robust Supervised Classifiers via Web-Scale N-Gram Data
In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude features for the counts of various N-grams, where the counts are obtained from a web-scale auxiliary corpus. We show that including N-gram count features can advance the state-of-the-art accuracy on standard data sets for...
متن کامل