Inflection Generation as Discriminative String Transduction
Published 1 January 2015Open access
Garrett Nicolai, Colin Cherry, Grzegorz Kondrak
Citations62
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Results of experiments demonstrate that the approach to morphological inflection generation as discriminative string transduction improves the state of the art in terms of predicting inflected word-forms.
Abstract
We approach the task of morphological inflection generation as discriminative string transduction.Our supervised system learns to generate word-forms from lemmas accompanied by morphological tags, and refines them by referring to the other forms within a paradigm.Results of experiments on six diverse languages with varying amounts of training data demonstrate that our approach improves the state of the art in terms of predicting inflected word-forms.
Keywords
Computer Science
LIBLINEAR: A Library for Large Linear Classification
6,625 Citations2008Rong-En Fan, Kai‐Wei Chang +3 more
Optimizing search engines using clickthrough data
3,898 Citations2002Thorsten Joachims
The goal of this paper is to develop a method that utilizes clickthrough data for training, namely the query-log of the search engine in connection with the log of links the users clicked on in the presented ranking.
Online large-margin training of dependency parsers
816 Citations2005Ryan McDonald, Koby Crammer +1 more
An effective training algorithm for linearly-scored dependency parsers that implements online large-margin multi-class training on top of efficient parsing techniques for dependency trees is presented.
Text, speech and language technologyThe Prague Dependency Treebank
406 Citations2003Alena Böhmová, Jan Hajič +2 more
Inspired by the Penn Treebank, the most widely used syntactically annotated corpus of English, this work decided to develop a similarly sized corpus of Czech with a rich annotation scheme.
Optimizing search engines using clickthrough data
395 Citations2002Thorsten Joachims
Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion
186 Citations2007Sittichai Jiampojamarn, Grzegorz Kondrak +1 more
This work presents a novel technique of training with many-to-many alignments of letters and phonemes, and applies an HMM method in conjunction with a local classification model to predict a global phoneme sequence given a word.
North American Chapter of the Association for Computational LinguisticsImprovements in Phrase-Based Statistical Machine Translation
186 Citations2004Richard Zens, Hermann Ney
A highly efficient monotone search algorithm with a complexity linear in the input sentence length is described and translated results for three tasks: Verbmobil, Xerox and the Canadian Hansards are presented.
Supervised Learning of Complete Morphological Paradigms
136 Citations2013Greg Durrett, John DeNero
This work describes a supervised approach to predicting the set of all inflected forms of a lexical item that automatically acquires the orthographic transformation rules of morphological paradigms from labeled examples, and then learns the contexts in which those transformations apply using a discriminative sequence model.
Semi-supervised learning of morphological paradigms and lexicons
129 Citations2014Mans Hulden, Markus Forsberg +1 more
A semi-supervised approach to the problem of paradigm induction from inflection tables, representing the resulting paradigms in an abstract form that can be used by linguists for the rapid creation of lexical resources.
Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model
76 Citations2011Markus Dreyer, Jason Eisner
An inference algorithm is presented that organizes observed words (tokens) into structured inflectional paradigms (types) and naturally predicts the spelling of unobserved forms that are missing from these paradigm, and discovers inflectionAL principles (grammar) that generalize to wholly unobserved words.
National Research Council Canada (Government of Canada)Integrating Joint n-gram Features into a Discriminative Training Framework
58 Citations2010Sittichai Jiampojamarn, Colin Cherry +1 more
This work includes joint n-gram features inside a state-of-the-art discriminative sequence model for letter-to-phoneme and transliteration transduction and results indicate an improvement in overall performance.
A global model for joint lemmatization and part-of-speech prediction
42 Citations2009Kristina Toutanova, Colin Cherry
This work uses only morphological lexicons and unlabeled data to learn a partially-supervised part-of-speech tagger and a lemmatizer which are combined using features on a dynamically linked dependency structure of words.
Conference of the European Chapter of the Association for Computational LinguisticsModeling Inflection and Word-Formation in SMT
40 Citations2012Alexander Fraser, Marion Weller +2 more
It is shown that improved modeling of inflection and wordformation leads to improved SMT, especially when translating into morphologically rich languages.
Combining Morpheme-based Machine Translation with Post-processing Morpheme Prediction
35 Citations2011Ann Clifton, Anoop Sarkar
This paper proposes a novel combination of post-processing morphology prediction with morpheme-based translation, and shows that its methods outperform previously proposed ones and provide the best known results on the English-Finnish Europarl translation task.