Ratnaparkhi, A. (1998), Maximum Entropy Models for Natural Language Ambiguity Resolution, PhD thesis, University of Pennsylvania.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents
Learning Computational Grammars - 3rd Annual Report - Nerbonne (2001) (Correct)
....Other chunk types have not received the same attention as NP chunks. The most complete work is [BVD99] which presents results for NP, VP, PP, ADJP and ADVP chunks. Vee99] works with NP, VP and PP chunks. RM95] have recognized arbitrary chunks but classified every non NP chunk as VP chunk. [Rat98] has recognized arbitrary chunks as part of a parsing task but did not report on the chunking performance. Software and Data The train and test data consist of three columns separated by spaces. Each word has been put on a separate line and there is an empty line after each sentence. The first ....
Adwait Ratnaparkhi, "Maximum Entropy Models for Natural Language Ambiguity Resolution". PhD thesis, University of Pennsylvania, 1998. ftp://ftp.cis.upenn.edu/pub/ircs/tr/98-15/98-15.ps.gz
Exponential Priors for Maximum Entropy Models - Goodman (2003) (2 citations) (Correct)
.... Research Microsoft Corporation One Microsoft Way http: www.research.microsoft.com 1 Introduction Conditional Maximum Entropy (maxent) models have been widely used for a variety of tasks, including language modeling [17] part of speech tagging, prepositional phrase attachment, and parsing [15], word selection for machine translation [2] and finding sentence boundaries [16] They are also sometimes called logistic regression models, maximum likelihood exponential models, log linear models, and are even equivalent to a form of perceptrons single layer neural networks. In particular, ....
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, 1998.
Extending the Coverage of a CCG System - Hockenmaier, Bierner, Baldridge (Correct)
....natural language understanding systems, and a great deal of research has gone into preprocessing techniques to deal with them. Our solution for these issues has been to create a pipeline of preprocessing components which use XML [38] documents in the input output speci cations. Following work by [26], we have built the components themselves using the maximum entropy framework. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those presented in [26] and [28] Other tasks such as paragraph detection or dealing with gures and ....
....use XML [38] documents in the input output speci cations. Following work by [26] we have built the components themselves using the maximum entropy framework. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those presented in [26] and [28] Other tasks such as paragraph detection or dealing with gures and tables have not been implemented as yet, but the existing components have been designed to work with XML documents in a manner which facilitates the incorporation of such additions. With tokenized and sentence detected ....
[Article contains additional citation context not shown here]
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, 1998.
Maximum Entropy Models and Prepositional Phrase Ambiguity - McLauchlan (2001) (Correct)
.... Rooth s approach, this approach does not consider the prepositional noun (N 2 ) The loglinear framework used in this approach also does not necessarily consider interactions between all features, as the maxent framework used in this dissertation does. 2.5.2. 3 Unsupervised Supervised Maxent: Ratnaparkhi 1998 There are two maxent approaches presented in this thesis. The first is unsupervised insofar as there is no manual labour or full parser involved in the extraction of the training data. Instead, the raw text is processed using a tagger and a simple chunker 1 to determine the headwords of noun ....
....achieve very good results using a back off Chapter 2. Previous Work 28 algorithm, but the underlying model maximum likelihood has several shortcomings. Maximum entropy models have several attractive properties, and it seems quite possible to improve on the [Ratnaparkhi et al. 1994] and [Ratnaparkhi, 1998] maxent models. We consider both vanilla and backed off maxent models. Ensemble methods, where a number of classifiers vote on the final prediction, have essentially been untouched in this field except for the Alegre (1999) approach. Chapter 8 considers some methods for creating ensembles of ....
[Article contains additional citation context not shown here]
Ratnaparkhi, A. (1998). Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, PA.
Statistical Parsing of Dutch using Maximum Entropy.. - Mullen, Malouf, van.. (2001) (Correct)
.... over the distribution [6] and building the feature set up by a process of induction to ensure that only maximally representative features are admitted into the model [7] The most commonly employed and computationally inexpensive approach to reducing noise is to use a frequency based feature cuto [14], in which features which occur fewer times in the training data than some predetermined cuto are eliminated. This has shown to be an e ective way to improve results. Because of its simplicity and e ectiveness, it is the approach we have focused on improving on in the present research. Although ....
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, 1998.
Automatic Multi-Lingual Information Extraction - Peng (2001) (Correct)
....should be similar to those of English i.e. Another problem for these languages is also related to segmentation: Part of Speech (POS) tagging. Taking Chinese as an example, although there are many Part of Speech taggers available for English and these taggers are claimed to be language independent [9, 12, 13, 17, 27, 51, 76], there is no publicly available POS tagger for Chinese. The main reason for this is the lack of benchmark data for training and testing. With the recent release of Chinese Treebank [22] we are now able to port the taggers to Chinese. Then with a Chinese segmenter and a POS tagger, we can build ....
....segmentation problems. Information extraction requires many constraints for prediction, including local ones and globe ones. Maximum entropy models has been shown to be good at modeling these constraints in many NLP areas, such as name entity recognition [8] POS and word sense disambiguation [76], parsing [17, 76] attribute grammar [65] language modeling [49, 53, 80] text segmentation [3] word spelling check [72] machine translation [4] text classi cation [63] and information extraction [54] The standard ME method is a supervised approach, which means that we have to label the ....
[Article contains additional citation context not shown here]
Ratnaparkhi, A. Maximum Entropy Models For Natural Language Ambiguity Resolution. Ph.D. thesis, Computer and Information Science Department, University of Pennsylvania, 1998.
Providing Robustness for a CCG System - Hockenmaier, Bierner, Baldridge (Correct)
....XML (World Wide Web Consortium, 1997) provides an elegant means for structuring texts. We have built the components themselves by using maximum entropy probability models. Maximum entropy is a powerful statistical method for estimating decisions by combining diverse pieces of information. Ratnaparkhi (1998) explores the maximum entropy framework with respect to many linguistic problems and demonstrates how tools using it can achieve high accuracy and domain independence. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those ....
....the maximum entropy framework with respect to many linguistic problems and demonstrates how tools using it can achieve high accuracy and domain independence. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those presented in Ratnaparkhi (1998) and Reynar and Ratnaparkhi (1997) Other tasks such as paragraph detection or dealing with figures and tables have not been implemented as yet, 108 but the existing components have been designed to work with XML documents in a manner which permits additions such as these with minimal effort. ....
[Article contains additional citation context not shown here]
Ratnaparkhi, A. (1998). Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D. thesis, University of Pennsylvania.
Providing Robustness for a CCG System - Sy St Em (Correct)
....cations. XML (World Wide Web Consortium, 1997) provides an elegant means for structuring texts. We have built the components themselves by using maximum entropy probability models. Maximum entropy is a powerful statistical method for estimating decisions by combining diverse pieces of information. Ratnaparkhi (1998) explores the maximum entropy framework with respect to many linguistic problems and demonstrates how tools using it can achieve high accuracy and domain independence. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those ....
....the maximum entropy framework with respect to many linguistic problems and demonstrates how tools using it can achieve high accuracy and domain independence. At present, we have built a tokenizer and sentence detector which use maximum entropy models with features based on those presented in Ratnaparkhi (1998) and Reynar and Ratnaparkhi (1997) respectively. Other tasks such as paragraph detection or dealing with gures and tables have not been implemented as yet, but the existing components have been designed to work with XML documents in a manner which permits additions such as these with minimal ....
Ratnaparkhi, A. (1998). Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D. thesis, University of Pennsylvania.
Building a Machine Learning Based Text Understanding System - Soderland (2001) (Correct)
....into that representation. 2 Steps in Text Analysis Our text understanding system has six main steps: 1. Structural analyzer 2. Lexical analyzer 3. Syntactic parser 4. Semantic interpreter 5. Frame builder 6. Coreference resolution The structural analyzer uses a maximum entropy classifier [Ratnaparkhi, 1998] to determine the sentence boundaries after dividing the document into sections based on page layout cues. The lexical analyzer looks up each word of the sentence in a domain specific glossary. This assigns syntactic and semantic features to each word that are used later by the parser and the ....
Adwait Ratnaparkhi. Maximum entropy models for natural language ambiguity resolution. PhD. dissertation, Dept. of Computer and Information Science, University of Pennsylvania, 1998.
Enriching Language Data through Projected Structures - William Lewis Fei (Correct)
No context found.
Ratnaparkhi, A. (1998), Maximum Entropy Models for Natural Language Ambiguity Resolution, PhD thesis, University of Pennsylvania.
Natural Language Processing For - Requirements Engineering.. (Correct)
No context found.
A. Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, Institute for Research in Cognitive Science, University of Pennsylvania, 1998.
Book Title - Book Editors Ios (Correct)
No context found.
Ratnaparkhi, A.: Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, Institute for Research in Cognitive Science, University of Pennsylvania (1998)
Web Text Corpus for Natural Language Processing - Liu, Curran (2006) (Correct)
No context found.
Adwait Ratnaparkhi. 1998. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, PA USA.
NLP-enhanced Content Filtering within the POESIA Project - Mark Hepple Neil (Correct)
No context found.
Ratnaparkhi, A. (1998). Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D. thesis, University of Pennsylvania.
Maximum Expected F-Measure Training of Logistic Regression Models - Jansche (2005) (Correct)
No context found.
Adwait Ratnaparkhi. 1998. Maximum Entropy Models for Natural Language Ambiguity Resolution.
Algorithms for Minimum Risk Chunking - Martin Jansche Center (2005) (Correct)
No context found.
Ratnaparkhi, A.: Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania (1998)
Discriminative Reranking for Natural Language Parsing - Collins, Koo (2000) (35 citations) (Correct)
No context found.
Ratnaparkhi, Adwait. (1998). Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D thesis, University of Pennsylvania.
Exponential Priors for Maximum Entropy Models - Joshua Goodman One (2004) (2 citations) (Correct)
No context found.
Adwait Ratnaparkhi. 1998. Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D. thesis, University of Pennsylvania.
A Weighted Polynomial Information Gain Kernel for.. - Phrase Attachment.. (2003) (Correct)
No context found.
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, PA, 1998.
Automatic Article Restoration - John Lee Spoken (2004) (Correct)
No context found.
Adwait Ratnaparkhi. 1998. Maximum Entropy Models for Natural Language Ambiguity Resolution Ph.D. Thesis, University of Pennsylvania, Philadelphia, PA.
Confidence Estimation for Machine Translation - Blatz, Fitzgerald, Foster.. (2004) (3 citations) (Correct)
No context found.
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, PA, 1998.
Facilitating Treebank Annotation Using a Statistical Parser - Fu-Dong Chiou David (Correct)
No context found.
Adwait Ratnaparkhi. Maximum entropy models for natural language ambiguity resolution. PhD thesis, University of Pennsylvania, 1998.
A Weighted Polynomial Information Gain Kernel for.. - Phrase Attachment.. (2003) (Correct)
No context found.
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, PA, 1998.
Extending DOP1 with the Insertion Operation - Hoogweg (2000) (Correct)
No context found.
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, Philadelphia, 1998.
Mining Subcategorization Information by Using Multiple.. - Marques, Lopes, Coelho (1999) (Correct)
No context found.
Adwait Ratnaparkhi. Maximum Entropy Models for Natural Language Ambiguity Resolution. PhD thesis, University of Pennsylvania, 1998.
First 50 documents
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC