The SIGMORPHON 2016 Shared Task—Morphological Reinflection
Published 1 January 2016Open access
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, Mans Hulden
Citations255
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
The 2016 SIGMORPHON Shared Task was devoted to the problem of morphological reinflection, and introduced morphological datasets for 10 languages with diverse ty-pological characteristics, showing a strong state of the art.
Abstract
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, Mans Hulden. Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology. 2016.
Keywords
Computer Science
Journal of Electronic ImagingPattern Recognition and Machine Learning
21,976 Citations2007Christopher Bishop
Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
arXiv (Cornell University)Neural Machine Translation by Jointly Learning to Align and Translate
14,565 Citations2014Dzmitry Bahdanau
arXiv (Cornell University)Sequence to Sequence Learning with Neural Networks
13,362 Citations2014Ilya Sutskever, Oriol Vinyals +1 more
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
6,616 Citations2014Kyunghyun Cho, Bart van Merriënboer +2 more
It is shown that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase.
TechnometricsPattern Recognition and Machine Learning
4,637 Citations2007Radford M. Neal
This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
Algorithms on strings, trees, and sequences: computer science and computational biology
3,529 Citations1997Dan Gusfield
Communications of the ACMA linear space algorithm for computing maximal common subsequences
1,108 Citations1975D. S. Hirschberg
The problem of finding a longest common subsequence of two strings has been solved in quadratic time and space and an algorithm is presented which will solve this problem in QuadraticTime and in linear space.
Large margin classification using the perceptron algorithm
1,099 Citations1998Yoav Freund, Robert E. Schapire
Computer Speech & LanguageWeighted finite-state transducers in speech recognition
883 Citations2002Mehryar Mohri, Fernando Pereira +1 more
WFSTs provide a common and natural representation for hidden Markov models (HMMs), context-dependency, pronunciation dictionaries, grammars, and alternative recognition outputs, and general transducer operations combine these representations flexibly and efficiently.
Cambridge University Press eBooksStatistical Machine Translation
850 Citations2009Philipp Koehn
This introductory text to statistical machine translation (SMT) provides all of the theories and methods needed to build a statistical machine translator, such as Google Language Tools and Babelfish, and the companion website provides open-source corpora and tool-kits.
The MIT Press eBooksFinite-State Morphology: Inflections and Derivations in a Single Framework Using Dictionaries and Rules
696 Citations1997David Clemenceau
This volume is a practical guide to finite-state theory and the affiliated programming languages lexc and xfst, and readers will learn how to write tokenizers, spelling checkers, and especially morphological analyzer/generators for words in English, French, Finnish, Hungarian and other languages.
Semi-Markov Conditional Random Fields for Information Extraction
617 Citations2004Sunita Sarawagi, William W. Cohen
Intuitively, a semi-CRF on an input sequence x outputs a "segmentation" of x, in which labels are assigned to segments rather than to individual elements of xi, and transitions within a segment can be non-Markovian.
Transactions of the Association for Computational LinguisticsSimple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
593 Citations2016Eliyahu Kiperwasser, Yoav Goldberg
The effectiveness of the BiLSTM approach is demonstrated by applying it to a greedy transition-based parser as well as to a globally optimized graph-basedparser.
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
560 Citations2015Chris Dyer, Miguel Ballesteros +3 more
This work was sponsored in part by the U. S. Army Research Laboratory and the NSF CAREER grant IIS-1054319 and the European Commission.
Lecture notes in computer scienceOpenFst: A General and Efficient Weighted Finite-State Transducer Library
537 Citations2007Cyril Allauzen, Michael Riley +3 more
OpenFst is an open-source library for weighted finite-state transducers (WFSTs) that consists of a C++ template library with efficient WFST representations and over twenty-five operations for constructing, combining, optimizing, and searching them.
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
526 Citations2015Chris Dyer, Miguel Ballesteros +3 more
Morpheme order and semantic scope word formation in the Athapaskan verb
295 Citations2000Keren Rice
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.
eScholarship (California Digital Library)Consonant harmony : long-distance interaction in phonology
177 Citations2010Gunnar Ólafur Hansson
Improving statistical MT through morphological analysis
170 Citations2005Sharon Goldwater, David McClosky
This work shows that using morphological analysis to modify the Czech input can improve a Czech-English machine translation system, and investigates several different methods of incorporating morphological information, and shows that a system that combines these methods yields the best results.
Finnish: An Essential Grammar
163 Citations2002Fred Karlsson
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.
Joint Lemmatization and Morphological Tagging with Lemming
126 Citations2015Thomas Müller, Ryan Cotterell +2 more
LEMMING sets the new state of the art in token-based statistical lemmatization on six languages and reduces the error by 60%, and gives empirical evidence that jointly modeling morphological tags and lemmata is mutually beneficial.
Learning Morphology with Morfette
121 Citations2008Grzegorz Chrupała, Georgiana Dinu +1 more
Morfette is a modular, data-driven, probabilistic system which learns to perform joint morphological tagging and lemmatization from morphologically annotated corpora with high accuracy with no language-specific feature engineering or additional resources.
Blocking of Phrasal Constructions by Lexical Items
106 Citations2007William J. Poser
Blocking is the widely observed phenomenon where the existence of one form prevents the creation and use of another form that would otherwise be expected to occur.
The American Indian QuarterlyThe Navajo Language: A Grammar and Colloquial Dictionary
102 Citations1979Robert W. Young, W. T. W. Morgan
Latent-variable modeling of string transductions with finite-state methods
98 Citations2008Markus Dreyer, Jason Smith +1 more
A conditional loglinear model is presented for string-to-string transduction that employs overlapping features over latent alignment sequences, and which learns latent classes and latent string pair regions from incomplete training data, and it is demonstrated that latent variables can dramatically improve results, even when trained on small data sets.
Finnish: An Essential Grammar
93 Citations2013Fred Karlsson
MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection
89 Citations2016Katharina Kann, Hinrich Schütze
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016 Shared Task on Morphological Reinflection as well as an extended analysis of how different design choices contribute to the final performance.
Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion
87 Citations2008Sittichai Jiampojamarn, Colin Cherry +1 more
The key idea is online discriminative training, which updates parameters according to a comparison of the current system output to the desired output, allowing the model to train all of its components together.
WFST-Based Grapheme-to-Phoneme Conversion: Open Source tools for Alignment, Model-Building and Decoding
87 Citations2012Josef R. Novak, Nobuaki Minematsu +1 more
This paper introduces a new open source, WFST-based toolkit for Grapheme-toPhoneme conversion that is efficient, accurate and currently supports a range of features including EM sequence alignment and several decoding techniques novel in the context of G2P.
Transactions of the Association for Computational LinguisticsModeling Word Forms Using Latent Underlying Morphs and Phonology
77 Citations2015Ryan Cotterell, Nanyun Peng +1 more
It is shown how to recover consistent underlying forms for these morphemes, together with the (stochastic) phonology that maps each concatenation of underlying forms to a surface form of a concatenative language.
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.
Paradigm classification in supervised learning of morphology
67 Citations2015Malin Ahlberg, Markus Forsberg +1 more
This work combines this non-probabilistic strategy of inflection table generalization with a discriminative classifier to permit the reconstruction of complete inflection tables of unseen words and shows that the general method is a viable approach to quickly creating highaccuracy morphological resources.
A Language-Independent Feature Schema for Inflectional Morphology
63 Citations2015John Sylak-Glassman, Christo Kirov +2 more
This schema is used to universalize data extracted from Wiktionary via a robust multidimensional table parsing algorithm and feature mapping algorithms, yielding 883,965 instantiated paradigms in 352 languages.
Inflection Generation as Discriminative String Transduction
62 Citations2015Garrett Nicolai, Colin Cherry +1 more
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.
Weighting Finite-State Transductions With Neural Context
60 Citations2016Pushpendre Rastogi, Ryan Cotterell +1 more
This work proposes to keep the traditional architecture, which uses a finite-state transducer to score all possible output strings , but to augment the scoring function with the help of recurrent networks, and combines these learned features with the transducers to define a probability distribution over aligned output strings, in the form of a weighted flnites-state automaton.
Graphical models over multiple strings
42 Citations2009Markus Dreyer, Jason Eisner
A Markov Random Field is proposed in which each factor (potential function) is a weighted finite-state machine, typically a transducer that evaluates the relationship between just two of the strings.
Automatic Extraction of Morphological Lexicons from Morphologically Annotated Corpora
37 Citations2013Ramy Eskander, Nizar Habash +1 more
A method for automatically learning inflectional classes and associated lemmas from morphologically annotated corpora using a core languageindependent algorithm, which can be optimized for specific languages.
Improving Sequence to Sequence Learning for Morphological Inflection Generation: The BIU-MIT Systems for the SIGMORPHON 2016 Shared Task for Morphological Reinflection
37 Citations2016Roee Aharoni, Yoav Goldberg +1 more
The reported results for the proposed models over the ten languages in the shared task bring this submission to the second/third place (depending on the language) on all three sub-tasks out of eight participating teams, while training only on the Restricted category data.
Automatic learning of language model structure
37 Citations2004Kevin Duh, Katrin Kirchhoff
This paper presents an entirely data-driven model selection procedure based on genetic search, which is shown to outperform both knowledge-based and random selection procedures on two different language modeling tasks (Arabic and Turkish).
Stochastic Contextual Edit Distance and Probabilistic FSTs
31 Citations2014Ryan Cotterell, Nanyun Peng +1 more
This work shows how to construct and train a probabilistic finite-state transducer that computes stochastic contextual edit distance and model typos found in social media text to illustrate the improvement from conditioning on context.
Communications in computer and information scienceA Universal Feature Schema for Rich Morphological Annotation and Fine-Grained Cross-Lingual Part-of-Speech Tagging
25 Citations2015John Sylak-Glassman, Christo Kirov +3 more
A universal morphological feature schema is presented, which is a set of features that represent the finest distinctions in meaning that are expressed by inflectional morphology across languages, and is used to assess the effectiveness of cross-linguistic projection of a multilingual consensus of these fine-grained morphological features.
A Computational Grammar and Lexicon for Maltese
23 Citations2013John J. Camilleri
This thesis contributes two computational resources for Maltese: a grammar and an online full-form lexicon, which uses the smart paradigms from the morphological part of the grammar to automatically produce some 4 million inflection forms and extend the collection into a full- form computational lexicon.
Morphological reinflection with convolutional neural networks
17 Citations2016Robert Östling
The method performs reasonably well on all the languages of the SIGMORPHON 2016 shared task, and using only convolution achieves surprisingly good results in this task, surpassing the accuracy of the encoder-decoder model for several languages.
Using longest common subsequence and character models to predict word forms
15 Citations2016Alexey Sorokin
This paper uses the method of longest common subsequence to extract abstract paradigms from given pairs of basic and inflected word forms, as well as suffix and prefix features to predict this paradigm automatically, using combination of affix feature-based and character ngram models.
Noise-Aware Character Alignment for Bootstrapping Statistical Machine Transliteration from Bilingual Corpora
14 Citations2013Katsuhito Sudoh, Shinsuke Mori +1 more
A novel noise-aware character alignment method for bootstrapping statistical machine transliteration from automatically extracted phrase pairs is proposed, an extension of a Bayesian many-to-many aligned method for distinguishing nontransliteration (noise) parts in phrase pairs.
Morphological Reinflection via Discriminative String Transduction
14 Citations2016Garrett Nicolai, Bradley Hauer +2 more
The results show that the methods of Nicolai et al. (2015) perform well on typologically diverse languages and language-specific heuristics and errors.
EHU at the SIGMORPHON 2016 Shared Task. A Simple Proposal: Grapheme-to-Phoneme for Inflection
10 Citations2016Iñaki Alegria, Izaskun Etxeberria
The results show that a very simple method can indeed improve upon some baselines, but does not reach the accuracies of the best systems in the task.
The Columbia University - New York University Abu Dhabi SIGMORPHON 2016 Morphological Reinflection Shared Task Submission
8 Citations2016Dima Taji, Ramy Eskander +2 more
Evaluating Sequence Alignment for Learning Inflectional Morphology
4 Citations2016David King
Results indicate a strong preference for simpler, concatenative morphological systems in CRF-based sequence alignment models for learning natural language morphology.