No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Transferring Word-Formation Networks Between Languages
ResearchGate has not been able to resolve any citations for this publication.
The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements made on several fronts over the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 67 new languages, including 30 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g. missing gender and macron information. We have also amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.
The article presents a semi-automatic method for the construction of word-formation networks focusing particularly on derivation. The proposed approach applies a sequential pattern mining technique to construct useful morphological features in an unsupervised manner. The features take the form of regular expressions and later they are used to feed a machine-learned ranking model. The network is constructed by applying the learned model to sort the lists of possible base words and selecting the most probable ones. This approach, besides relatively small training set and a lexicon, does not require any additional language resources such as a list of vowel and consonant alternations, part-of-speech tags etc. The proposed approach is evaluated on lexeme sets of four languages, namely Polish, Spanish, Czech, and French. The conducted experiments demonstrate the ability of the proposed method to construct linguistically adequate word-formation networks from small training sets. Furthermore, the performed feasibility study shows that the method can further benefit from the interaction with a human language expert within the active learning framework.
The aim of this paper is to open a discussion on harmonization of existing data resources related to derivational morphology. We present a newly assembled collection of eleven harmonized resources named "Universal Derivations" (clearly being inspired by the success story of the Universal Dependencies initiative in treebanking), as well as the harmonization process that brings the individual resources under a unified annotation scheme.
This paper introduces CogNet, a new, large-scale lexical database that provides cognates—words of common origin and meaning—across languages. The database currently contains 3.1 million cognate pairs across 338 languages using 35 writing systems. The paper also describes the automated method by which cognates were computed from publicly available wordnets, with an accuracy evaluated to 94%. Finally, statistics and early insights about the cognate data are presented, hinting at a possible future exploitation of the resource by various fields of lingustics.
The report focuses on existing morphological resources containing derivational word-formation relations. For each resource, the report describes history, licence, format, data structure and some other basic statistics to compare. Therefore, it means the first step to review and harmonize these resources in a similar way as it has already been done with resources of syntactic trees.
A source language sentence is tagged with non-lexical tags, such as part-of-speech tags and is parsed using a lexicalized parser trained in the source language. A target language sentence that is a translation of the source language sentence is tagged with non-lexical labels (e.g., part-of speech tags) and is parsed using a delexicalized parser that has been trained in the source language to produce k-best parses. The best parse is selected based on the parse's alignment with lexicalized parse of the source language sentence. The selected best parse can be used to update the parameter vector of a lexicalized parser for the target language.
Démonette is a derivational morphological network created from information provided by two existing lexical resources, DériF and Morphonette. It features a formal architecture in which words are associated with semantic types and where morphological relations, labelled with concrete and abstract bi-oriented definitions, connect derived words with their base and indirectly related words with each other.
This paper presents the current status of OPUS, a growing language resource of parallel corpora and related tools. The focus in OPUS is to provide freely available data sets in various formats together with basic annotation to be useful for applications in computational linguistics, translation studies and cross-linguistic corpus studies. In this paper, we report about new data sets and their features, additional annotation tools and models provided from the website and essential interfaces and on-line services included in the project.
We present a simple method for transferring dependency parsers from source languages with labeled training data to target languages without labeled training data. We first demonstrate that delexicalized parsers can be directly transferred between languages, producing significantly higher accuracies than unsupervised parsers. We then use a constraint driven learning algorithm where constraints are drawn from parallel corpora to project the final parser. Unlike previous work on projecting syntactic resources, we show that simple methods for introducing multiple source languages can significantly improve the overall quality of the resulting parsers. The projected parsers from our system result in state-of-the-art performance when compared to previously studied unsupervised and projected parsing systems across eight different languages.
Scikit-learn is a Python module integrating a wide range of state-of-the-art
machine learning algorithms for medium-scale supervised and unsupervised
problems. This package focuses on bringing machine learning to non-specialists
using a general-purpose high-level language. Emphasis is put on ease of use,
performance, documentation, and API consistency. It has minimal dependencies
and is distributed under the simplified BSD license, encouraging its use in
both academic and commercial settings. Source code, binaries, and documentation
can be downloaded from http://scikit-learn.sourceforge.net.
In a recent paper, Gale and Church describe an inexpensive method for aligning bitext, based exclusively on sentence lengths [Gale and Church, 1991]. While this method produces surprisingly good results (a success rate around 96%), even better results are required to perform such tasks as the computer-assisted revision of translations. In this paper, we examine some of the weaknesses of Gale and Church's program, and explain how just a small amount of linguistic knowledge would help to overcome these weaknesses. We discuss how cognates provide for a cheap and reasonably reliable source of linguistic knowledge. To illustrate this, we describe a modification to the program in which the criterion is cognates rather than sentence lengths. Finally, we show how better and more efficient results may be obtained by combining the two criteria --- length and "cognateness". Our method can be generalized to accommodate other sources of linguistic knowledge, and experimentation shows that it produc...
There have been a number of recent papers on aligning parallel texts at the sentence level, e.g., Brown et al (1991), Gale and Church (to appear), Isabelle (1992), Kay and Ro .. senschein (to appear), Simard et al (1992), WarwickArmstrong and Russell (1990). On clean inputs, such as the Canadian Hansards, these methods have been very successful (at least 96% correct by sentence). Unfortunately, if the input is noisy (due to OCR and/or unknown markup conventions), then these methods tend to break down because the noise can make it difficult to find paragraph boundaries, let alone sentences. This paper describes a new program, char_align, that aligns texts at the character level rather than at the sentence/paragraph level, based on the cognate approach proposed by Simard et al. 1. Introduction Parallel texts have recently received considerable attention in machine translation (e.g., Brown et al, 1990), bilingual lexicography (e.g., Klavans and Tzoukermann, 1990), and terminology resea...
Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Many popular models to learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for morphologically rich languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skip-gram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram, words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpus quickly. We evaluate the obtained word representations on five different languages, on word similarity and analogy tasks.
Derivational models are still an underresearched area in computational morphology. Even for German, a rather resourcerich language, there is a lack of largecoverage derivational knowledge. This paper describes a rule-based framework for inducing derivational families (i.e., clusters of lemmas in derivational relationships) and its application to create a highcoverage German resource, DErivBase, mapping over 280k lemmas into more than 17k non-singleton clusters. We focus on the rule component and a qualitative and quantitative evaluation. Our approach achieves up to 93% precision and 71% recall. We attribute the high precision to the fact that our rules are based on information from grammar books.
The paper presents a linguistic and computational model aiming at making the morphological structure of the lexicon emerge from the formal and semantic regularities of the words it contains. The model is word-based. The proposed morphological structure consists of (1) binary relations that connect each headword with words that are morphologically related, and especially with the members of its morphological family and its derivational series, and of (2) the analogies that hold between the words. The model has been tested on the lexicon of French using the TLFi machine readable dictionary. Comment: proceedings of the 6th D\'ecembrettes
Universal Dependencies v1: A Multilingual Treebank Collection
- Nivre
Unsupervised Lemmatization as Embeddings-Based Word Clustering
- Rosa
Merging Data Resources for Inflectional and Derivational Morphology in Czech
- Žabokrtský