A Maximum Entropy Model for Part-Of-Speech Tagging

By Adwait Ratnaparkhi. 1996

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

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, background): “For instance, Ratnaparkhi (1996) 15.”
Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003, methodology): “For example, in the left-to-right CMM shown in ﬁgure 1(a), That is, the replicated structure is a local model P ( t 0 | t − 1 , w 0 ) .”
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms (2002, methodology): “For both methods, we tried the algorithms with feature count cut-o s set at 0 and 5 (i.e., we ran experiments with all features in training data included, or with all features occurring 5 times or more included { (Ratnaparkhi 96) uses a count cut-o of 5).”
A theory of learning from different domains (2010, background): “In general, labeled data for tasks like part-of-speech tagging (Ratnaparkhi 1996), parsing (Collins 1999), information extraction (Bikel et al. 1997), and sentiment analysis (Pang et al. 2002) are drawn from a limited set of document types and genres in a given language due to availability, cost,…”
A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering (2016, methodology): “For each annotation, we use a pretrained maximum-entropy parser [25, 21] from the Natural Language Toolkit (NLTK) [2] to tag all words in the annotation with their part-of-speech (POS).”
Domain Adaptation with Structural Correspondence Learning (2006, methodology): “Discriminative tag-gers and chunkers have been the state-of-the-art for more than a decade (Ratnaparkhi, 1996; Sha and Pereira, 2003).”
Head-Driven Statistical Models for Natural Language Parsing (2003, methodology): “Words in test data that have not been seen in training are deterministically assigned the POS tag that is assigned by the tagger described in Ratnaparkhi (1996).”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, background): “The work of maximum entropy classiﬁer (Ratnaparkhi, 1996) and Maximum entropy Markov models (MEMMs) (McCallum et al., 2000) fall in this category.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “An alternative, discriminative model (known to the nlp community at least since Ratnaparkhi, 1996) is logistic regression (Maximum Entropy).”
Discriminative Training of a Neural Network Statistical Parser (2004, background): “However, the fact that the DGSSN uses a large-vocabulary tagger (Ratnaparkhi, 1996) as a preprocessing stage may compensate for its smaller vocabulary.”
Three Generative, Lexicalised Models for Statistical Parsing (1997, methodology): “For unknown words, the output from the tagger described in (Ratnaparkhi 96) is used as the single possible tag for that word.”
Shallow Parsing with Conditional Random Fields (2003, background): “The sequential classi(cid:2)cation approach can handle many correlated features, as demonstrated in work on maximum-entropy (McCallum et al., 2000; Ratnaparkhi, 1996) and a variety of other linear classi(cid:2)ers, including winnow (Punyakanok and Roth, 2001), AdaBoost (Ab-ney et al., 1999), and…”
Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing (2019, background): “, 1993) is the de facto data set used to train many of the POS taggers (Brill, 1994; Ratnaparkhi, 1996; Toutanova and Manning, 2000; Toutanova et al., 2003) and”
Syntactic Phrase Reordering for English-to-Arabic Statistical Machine Translation (2009, methodology): “We then proceed to split the data into smaller sentences and tag them using Ratnaparkhi’s Maximum Entropy Tagger (Ratnaparkhi, 1996).”
Inducing History Representations for Broad Coverage Statistical Parsing (2003, methodology): “We used a publicly available tagger (Ratnaparkhi, 1996) to provide the tags used in these experiments, rather than the handcorrected tags which come with the corpus.”
Ensemble of feature sets and classification algorithms for sentiment classification (2011, methodology): “MXPOST is a POS tagger based on maximum entropy which was introduced in [33].”