Applied morphological processing of English

By Guido Minnen, John A. Carroll, Darren Pearce. Natural Language Engineering, 2001

391 citations recorded by the source corpus.

We describe two newly developed computational tools for morphological processing: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser. The tools are fast, being based on finite-state techniques, have wide coverage, incorporating data from various corpora and machine readable dictionaries, and are robust, in that they are able to deal effectively with unknown words. The tools are freely available. We evaluate the accuracy and speed of both tools and discuss a number of practical applications in which they have been put to use.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e979925b15861153a0e9ce8ace39a28d319e613d

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

English-to-Czech Factored Machine Translation (2007, methodology): “5 The Czech part of the corpus was tagged and lemmatized using the tool by Hajič and Hladká (1998), the English part was tagged MXPOST (Ratnaparkhi, 1996) and lemmatized using the Morpha tool (Minnen et al., 2001).”
Subtlex-UK: A New and Improved Word Frequency Database for British English (2014, methodology): “The lemmatization is based on an algorithm developed by Minnen, Carroll, and Pearce (2001).”
The Second Release of the RASP System (2006, background): “The type and token error rate of the current system is less than 0.07% (Minnen, Carroll and Pearce, 2001).”
Vector Space Models of Lexical Meaning (2015, background): “Another standard practice is to lemmatise the sentence (Minnen et al., 2001) so that the direct object of scored, for example, would be equated with the direct object of score or scores (i.e. each of these three word-grammatical relation pairs would correspond to the same basis vector).”
An Exploration of Discourse-Based Sentence Spaces for Compositional Distributional Semantics (2015, methodology): “To train the noun vectors and verb tensors we used an October 2013 download of Wikipedia articles, which was tokenised using the Stanford NLP tools, 2 lemmatised with the Morpha lemmatiser (Minnen et al., 2001), and parsed with the C&C parser (Clark and Curran, 2007).”
The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity (2014, methodology): “It is the last component in the pipeline of the C&C tools (Curran et al., 2007), comprising a tokenizer, POS-tagger, lemmatizer (Minnen et al., 2001), and a robust parser for CCG (Steed-man, 2001).”
A Natural Proof System for Natural Language (2017, methodology): “In contrast to Morpha (Minnen et al., 2001), used in C&C, EasyCCG uses a less accurate morphological analyzer.”
Robust Accurate Statistical Annotation of General Text (2002, background): “The type and token error rate of the current system is less than 0.07%, and the system is able to process more than 200K words per second on standard hardware (Minnen, Carroll and Pearce, 2001).”
From distributional to semantic similarity (2004, background): “morpha has wide coverage – nearly 100% against the CELEX lexical database (Minnen et al., 2001) – and is very efficient, analysing over 80 000 words per second (Minnen et al.”
Learning to recognize features of valid textual entailments (2006, background): “The nodes in the final graph are then annotated with their associated word, part-of-speech (given by the parser), lemma (given by a finite-state transducer described by Minnen et al. (2001)) and named-entity tag.”
Deriving a Large-Scale Taxonomy from Wikipedia (2007, background): “This is because the size of the induced taxonomy is very large – up to 105,418 generated isa semantic links – and also to avoid any bias in the evaluation method.”
Question classification with log-linear models (2006, methodology): “The most important features are the words of the question which have been lemmatised using the Sussex morphological analyser [ 17 ].”
SimpleNLG: A Realisation Engine for Practical Applications (2009, methodology): “Morphological rules, a re-implementation of those in MORPHG (Minnen et al., 2001), cover the full range of English inflection, including regular and irregular forms1.”