Search

Although the Neural Machine Translation (NMT) framework has already been shown effective in large training data scenarios, it is less effective for low-resource conditions. To improve NMT performance in a low-resource setting, we extend the high-quality training data by generating a pseudo bilingual dataset and then filtering out low-quality alignments using a quality estimation based on back-translation. We demonstrate that our approach yields significantly higher BLEU scores than those of a set of baselines.

Neural Machine Translation (NMT) performs training of a neural network employing an encoder-decoder architecture. However, the quality of the neural-based translations predominantly depends on the availability of a large amount of bilingual training dataset. In this paper, we explore the performance of translations predicted by attention-based NMT systems for Spanish to Persian low-resource language pairs. We analyze the errors of NMT systems that occur in the Persian language and provide an in-depth comparison of the performance of the system based on variations in sentence length and size of the training dataset. We evaluate our translation results using BLEU and human evaluation measures based on the adequacy, fluency, and overall rating.

In Spanish ditransitive clauses with Dative Clitic Doubling (DClD), the goal may be doubled by a dative clitic pronoun. Applying a chi-square decomposition analysis to examples with the prototypical ditransitive verb dar “give”, from a corpus of journalistic language characteristic of River Plate Spanish, I show that DClD is disfavoured when the theme is a bare noun, and also that the distinction between bare and non-bare themes is more statistically significant than the distinction between definite and indefinite themes. The relational effect of definiteness on DClD in clauses with the verb dar is accounted for by extending Hopper and Thompson’s (1980) Transitivity Hypothesis to clauses with three arguments.

Modern software development is increasingly collaborative. Open Source Software (OSS) are the bellwether; they support dynamic teams, with tools for code sharing, communication, and issue tracking. The success of an OSS project is reliant on team communication. E.g., in issue discussions, individuals rely on rhetoric to argue their position, but also maintain technical relevancy. Rhetoric and technical language are on opposite ends of a language complexity spectrum: the former is stylistically natural; the latter is terse and concise. Issue discussions embody this duality, as developers use rhetoric to describe technical issues. The style mix in any discussion can define group culture and affect performance, e.g., issue resolution times may be longer if discussion is imprecise. Using GitHub, we studied issue discussions to understand whether project-specific language differences exist, and to what extent users conform to a language norm. We built project-specific and overall GitHub language models to study the effect of perceived language complexity on multiple responses. We find that experienced users conform to project-specific language norms, popular individuals use overall GitHub language rather than project-specific language, and conformance to project-specific language norms reduces issue resolution times. We also provide a tool to calculate project-specific perceived language complexity.

This article argues for a three-way structural characterization of Fijian objects: common nouns can be incorporated or dislocated, but pronouns and proper nouns occur inside the VP as complements. These facts support an analysis of Fijian as a polysynthetic language, since it is a pronominal argument language with incorporated objects. Having complement nominals inside the VP, however, puts Fijian outside the scope of Baker’s (1996) polysynthesis parameter. The distribution of complements in Fijian follows from Hopper and Thompson’s (1980) transitivity hypothesis , since only those nominals with the highest degree of individuation can occur inside the VP.