Maximum entropy models for natural language ambiguity resolution

By Adwait Ratnaparkhi, Mitchell P. Marcus. 1998

Subfields: Natural Language Processing, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Probabilistic & Bayesian Methods

Citations in the corpus

Introduction to the CoNLL-2000 Shared Task Chunking (2000, background): “Ratnaparkhi (1998) has recognized arbitrary chunks as part of a parsing task but did not report on the chunking performance.”
Syntactic Processing Using the Generalized Perceptron and Beam Search (2011, methodology): “The term global feature vector is used by Collins (2002) to distinguish between feature counts for whole sequences and the local feature vectors in maximum entropy tagging models, which are boolean-valued vectors containing the indicator features for one element in the sequence (Ratnaparkhi 1998).”
English SLT and MT system description for the IWSLT 2013 evaluation (2013, methodology): “We used LoPar [42] to obtain morphological analysis and POS annotation of German and MXPOST [43], a maximum entropy model for English POS tags.”
Sentence Level Discourse Parsing using Syntactic and Lexical Information (2003, methodology): “The problem of sentence segmentation has been studied extensively, and tools such as those described by Palmer and Hearst (1997) and Ratnaparkhi (1998) can handle it well.”
Trainable Methods for Surface Natural Language Generation (2000, background): “For example, the set of attribute-value pairs { $cityfr = New York City, $city-to = Seattle , $time-dep = 6 a.m., $date-dep = Wednesday } represent the meaning of the noun phrase “a flight to Seattle that departs from New York City at 6 a.m. on Wednesday”.”
An evaluation of statistical spam filtering techniques (2004, methodology): “1996] is a generalpurpose machine-learning framework that has been successfully applied to a wide range of text processing tasks such as statistical language modeling [Rosenfeld 1996], language ambiguity resolution [Ratnaparkhi 1998], and text categorization [Nigam et al.”
Discriminative Reranking for Natural Language Parsing (2000, methodology): “…Roukos, and Ward 1994; Berger, Della Pietra, and Della Pietra 1996; Della Pietra, Della Pietra, and Lafferty 1997; Papineni, Roukos, and Ward 1997, 1998) require several full passes over the training set for each round of feature selection, suggesting that at least for the parsing data, the…”
Recommender systems based on user reviews: the state of the art (2015, methodology): “The companion context is also obtained from reviews using a hybrid classifier that first identifies related features via rule-based methods and then uses the features to train a Maximum Entropy (MaxEnt) classifier (Ratnaparkhi 1998).”
Maximum Entropy Markov Models for Information Extraction and Segmentation (2000, background): “…with considerable success to many natural language tasks, including language modeling for speech recognition (Rosenfeld, 1994; Chen & Rosenfeld, 1999), segmentation of newswire stories (Beeferman et al., 1999), part-of-speech tagging, prepositional phrase attachment and parsing (Ratnaparkhi, 1998).”
CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank (2007, methodology): “Statistical parsing on the Penn Treebank has made great progress by focusing on the machine-learning or algorithmic aspects (Magerman 1994; Ratnaparkhi 1998; Collins 1999; Charniak 2000; Henderson 2004; McDonald, Crammer, and Pereira 2005).”
IXA pipeline: Efficient and Ready to Use Multilingual NLP tools (2014, methodology): “• Maximum Entropy models based on Ratnaparkhi’s approach (1996; 1998) optimized using Generalised Iterative Scaling.”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, methodology): “We used LoPar (Schmid, 2000) to obtain morphological analysis and POS annotation of German and MXPOST (Ratnaparkhi, 1998), a maximum entropy model for English POS tags.”
Chinese Word Segmentation as Character Tagging (2003, unknown): “We then briefly describe the maximum entropy model, which has been successfully applied to POS tagging as well as parsing [Ratnaparkhi, 1996; Ratnaparkhi, 1998].”
Controlled user evaluations of information visualization interfaces for text retrieval: Literature review and meta-analysis (2008, unknown): “ensure that . The aj’s are called model parameters, with aj corresponding to the weight for the feature function fj. The model parameters can be found by an iterative algorithm called generalized iterative scaling (GIS; Darroch & Ratcliff, 1972; Ratnaparkhi, 1996b ).”