The 2016 SIGMORPHON Shared Task was devoted to the problem of morphological reinflection. It introduced morphological datasets for 10 languages with diverse typological characteristics. The shared task drew submissions from 9 teams representing 11 institutions reflecting a variety of approaches to addressing supervised learning of reinflection. For the simplest task, inflection generation from lemmas, the best system averaged 95.56% exact-match accuracy across all languages, ranging from Maltese (88.99%) to Hungarian (99.30%). With the relatively large training datasets provided, recurrent neural network architectures consistently performed best-in fact, there was a significant margin between neural and non-neural approaches. The best neural approach, averaged over all tasks and languages, outperformed the best nonneural one by 13.76% absolute; on individual tasks and languages the gap in accuracy sometimes exceeded 60%. Overall, the results show a strong state of the art, and serve as encouragement for future shared tasks that explore morphological analysis and generation with varying degrees of supervision.
The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation required systems to be trained and tested in each of 52 typologically diverse languages. In sub-task 1, submitted systems were asked to predict a specific inflected form of a given lemma. In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by predicting all of the remaining inflected forms. Both sub-tasks included high, medium, and low-resource conditions. Sub-task 1 received 24 system submissions, while sub-task 2 received 3 system submissions. Following the success of neural sequence-to-sequence models in the SIGMORPHON 2016 shared task, all but one of the submissions included a neural component. The results show that high performance can be achieved with small training datasets, so long as models have appropriate inductive bias or make use of additional unlabeled data or synthetic data. However, different biasing and data augmentation resulted in non-identical sets of inflected forms being predicted correctly, suggesting that there is room for future improvement.
This paper presents a universal morphological feature schema that represents the finest distinctions in meaning that are expressed by overt, affixal inflectional morphology across languages. 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. These data are shown to be effective for training morphological analyzers, yielding significant accuracy gains when applied to Durrett and DeNero's (2013) paradigm learning framework.
Many of the world's languages contain an abundance of inflected forms for each lexeme. A major task in processing such languages is predicting these inflected forms. We develop a novel statistical model for the problem, drawing on graphical modeling techniques and recent advances in deep learning. We derive a Metropolis-Hastings algorithm to jointly decode the model. Our Bayesian network draws inspiration from principal parts morphological analysis. We demonstrate improvements on 5 languages.
The post-velar consonants (uvulars, pharyngeals/epiglottals, glottals) have been argued to form an innate and universal phonological natural class (e.g. by McCarthy 1994). Under this hypothesis, languages should have an equal likelihood of showing evidence for the guttural natural class regardless of which post-velar consonants are present in each language. However, typological evidence from P-base (Mielke, 2008) shows that languages with pharyngeal consonants are significantly more likely to show such evidence than languages with just uvulars and glottals. This paper argues that the reason that languages with pharyngeals are more likely to show evidence of the guttural natural class is that pharyngeals are able to pull other consonants into phonologically patterning with them for both articulatory and acoustic reasons. The epilaryngeal constriction used in pharyngeal consonants facilitates articulatory links with uvulars and glottals. The acoustic effects of pharyngeals and uvulars on adjacent vowels are also similar, providing another means for these segments to pattern together phonologically. A preliminary analysis in Optimality Theory of the effects of post-velars on vowels is proposed in which markedness constraints refer to similarity scales that relate post-velar consonants to vowels. The guttural natural class, rather than being innate, emerges from phonological patterns with phonetic underpinnings.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.