2020

Unsupervised Morphological Paradigm Completion

Jin, Huiming, Cai, Liwei, Peng, Yihui et al.

Understand

We propose the task of unsupervised morphological paradigm completion.

Given only raw text and a lemma list, the task consists of generating the morphological paradigms, i.e., all inflected forms, of the lemmas.
From a natural language processing (NLP) perspective, this is a challenging unsupervised task, and high-performing systems have the potential to improve tools for low-resource languages or to assist linguistic annotators.
From a cognitive science perspective, this can shed light on how children acquire morphological knowledge.

Built on

The child’s learning of English morphology
Jean Berko. 1958 · 1958
Earlier work this paper cites.
Brown corpus
W Nelson Francis and Henry Kucera. 1964 · 1964
Earlier work this paper cites.
Inflectional morphology: A theoretical study based on aspects of Latin verb conjugation , volume 6
Peter Hugoe Matthews and PH Matthews. 1972 · 1972
Earlier work this paper cites.
Word formation in generative grammar
Mark Aronoff. 1976 · 1976
Earlier work this paper cites.
Opyt strukturnogo opisanija archinskogo jazyka. T. I. leksika. fonetika. T. II. taksonomicheskaja grammatika
Aleksandr E. Kibrik. 1977 · 1977
Earlier work this paper cites.
An algorithm to solve the m × n m\times n assignment problem in expected time O {O} ( m n log ⁡ n ) (mn\log n)
Richard M Karp. 1980 · 1980
Earlier work this paper cites.
Longman dictionary of contemporary English
Della Summers and Adam Gadsby. 1995 · 1995
Earlier work this paper cites.
The Bible as a parallel corpus: Annotating the ‘book of 2000 tongues’
Philip Resnik, Mari Broman Olsen, and Mona Diab. 1999 · 2000
Earlier work this paper cites.
Minimally supervised morphological analysis by multimodal alignment
David Yarowsky and Richard Wicentowski. 2000 · 2000
Earlier work this paper cites.
Unsupervised learning of the morphology of a natural language
John Goldsmith. 2001 · 2001
Earlier work this paper cites.
Unsupervised segmentation of words using prior distributions of morph length and frequency
Mathias Creutz. 2003 · 2003
Earlier work this paper cites.
One-shot neural cross-lingual transfer for paradigm completion
Katharina Kann, Ryan Cotterell, and Hinrich Schütze. 2017 · 2003
Earlier work this paper cites.
Analysis of morph-based speech recognition and the modeling of out-of-vocabulary words across languages
Mathias Creutz, Teemu Hirsimäki, Mikko Kurimo, Antti Puurula, Janne Pylkkönen, Vesa Siivola, Matti Varjokallio, Ebru Arisoy, Murat Saraçlar, and Andreas Stolcke. 2007 · 2007
Earlier work this paper cites.
Unsupervised models for morpheme segmentation and morphology learning
Mathias Creutz and Krista Lagus. 2007 · 2007
Earlier work this paper cites.
Towards a machine-learning architecture for lexical functional grammar parsing
Grzegorz Chrupała. 2008 · 2008
Earlier work this paper cites.
Unsupervised multilingual learning for morphological segmentation
Benjamin Snyder and Regina Barzilay. 2008 · 2008
Earlier work this paper cites.
Discovering morphological paradigms from plain text using a Dirichlet process mixture model
Markus Dreyer and Jason Eisner. 2011 · 2011
Earlier work this paper cites.

Similar

Unsupervised learning of morphology
Harald Hammarström and Lars Borin. 2011 · 2011
Cited alongside, same era.
Polish: A comprehensive grammar
Iwona Sadowska. 2012 · 2012
Cited alongside, same era.
Supervised learning of complete morphological paradigms
Greg Durrett and John DeNero. 2013 · 2013
Cited alongside, same era.
Semi-supervised learning of morphological paradigms and lexicons
Mans Hulden, Markus Forsberg, and Malin Ahlberg. 2014 · 2014
Cited alongside, same era.
Morphological segmentation for keyword spotting
Karthik Narasimhan, Damianos Karakos, Richard Schwartz, Stavros Tsakalidis, and Regina Barzilay. 2014 · 2014
Cited alongside, same era.
Morphological inflection generation with hard monotonic attention
Roee Aharoni and Yoav Goldberg. 2017 · 2015
Cited alongside, same era.
Paradigm classification in supervised learning of morphology
Malin Ahlberg, Markus Forsberg, and Mans Hulden. 2015 · 2015
Cited alongside, same era.
Neural machine translation by jointly learning to align and translate
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015 · 2015
Cited alongside, same era.
An unsupervised method for uncovering morphological chains
Karthik Narasimhan, Regina Barzilay, and Tommi Jaakkola. 2015 · 2015
Cited alongside, same era.
Inflection generation as discriminative string transduction
Garrett Nicolai, Colin Cherry, and Grzegorz Kondrak. 2015 · 2015
Cited alongside, same era.
A graph-based lattice dependency parser for joint morphological segmentation and syntactic analysis
Wolfgang Seeker and Özlem Çetinoğlu. 2015 · 2015
Cited alongside, same era.
Unsupervised morphology induction using word embeddings
Radu Soricut and Franz Och. 2015 · 2015
Cited alongside, same era.

Then

CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2017 · 2017
Later among the works it cites.
Exploring cross-lingual transfer of morphological knowledge in sequence-to-sequence models
Huiming Jin and Katharina Kann. 2017 · 2017
Later among the works it cites.
Align and copy: UZH at SIGMORPHON 2017 shared task for morphological reinflection
Peter Makarov, Tatiana Ruzsics, and Simon Clematide. 2017 · 2017
Later among the works it cites.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Later among the works it cites.
Multi-space variational encoder-decoders for semi-supervised labeled sequence transduction
Chunting Zhou and Graham Neubig. 2017 · 2017
Later among the works it cites.
The CoNLL–SIGMORPHON 2018 shared task: Universal morphological reinflection
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Arya D. McCarthy, Katharina Kann, Sebastian Mielke, Garrett Nicolai, Miikka Silfverberg, David Yarowsky, Jason Eisner, and Mans Hulden. 2018 · 2018
Later among the works it cites.
Neural transductive learning and beyond: Morphological generation in the minimal-resource setting
Katharina Kann and Hinrich Schütze. 2018 · 2018
Later among the works it cites.
UniMorph 2.0: Universal morphology
Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sebastian Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2018 · 2018
Later among the works it cites.
Imitation learning for neural morphological string transduction
Peter Makarov and Simon Clematide. 2018a · 2018
Later among the works it cites.
Unsupervised morphology learning with statistical paradigms
Hongzhi Xu, Mitchell Marcus, Charles Yang, and Lyle Ungar. 2018 · 2018
Later among the works it cites.
Pushing the limits of low-resource morphological inflection
Antonios Anastasopoulos and Graham Neubig. 2019 · 2019
Later among the works it cites.
The FLORES evaluation datasets for low-resource machine translation: Nepali–English and Sinhala–English
Francisco Guzmán, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, and Marc’Aurelio Ranzato. 2019 · 2019
Later among the works it cites.
The SIGMORPHON 2019 shared task: Morphological analysis in context and cross-lingual transfer for inflection
Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sebastian J. Mielke, Jeffrey Heinz, Ryan Cotterell, and Mans Hulden. 2019 · 2019
Later among the works it cites.
The paradigm discovery problem
Alexander Erdmann, Micha Elsner, Shijie Wu, Ryan Cotterell, and Nizar Habash. 2020 · 2020
Closest in time.
SkinAugment: Auto-encoding speaker conversions for automatic speech translation
A. D. McCarthy, L. Puzon, and J. Pino. 2020 · 2020
Closest in time.
The Johns Hopkins University Bible Corpus: 1600+ tongues for typological exploration
Arya D. McCarthy, Rachel Wicks, Dylan Lewis, Aaron Mueller, Winston Wu, Oliver Adams, Garrett Nicolai, Matt Post, and David Yarowsky. 2020 · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…