1,720,982 research outputs found
Prompting Large Language Models for Idiomatic Translation
Large Language Models (LLMs) have demonstrated impressive performance in translating content across different languages and genres. Yet, their potential in the creative aspects of machine translation has not been fully explored. In this paper, we seek to identify the strengths and weaknesses inherent in different LLMs when applied to one of the most prominent features of creative works: the translation of idiomatic expressions. We present an overview of their performance in the EN→IT language pair, a context characterized by an evident lack of bilingual data tailored for idiomatic translation. Lastly, we investigate the impact of prompt design on the quality of machine translation, drawing on recent findings which indicate a substantial variation in the performance of LLMs depending on the prompts utilized
Simplified or not simplified? The different guises of mediated English at the European Parliament
In this article we describe a framework for the corpus-based comparative investigation of interpreting and translation, illustrating it through a study of simplification across different modes of language production and across different language pairs. We rely on EPTIC, a corpus featuring plenary speeches at the European Parliament in their interpreted and translated versions, aligned to each other and to their source texts in EnglishItalian and EnglishFrench. Aiming to shed light on lexical simplification in different mediation modes, we compare interpretations and translations to each other and to comparable original speeches and their edited written versions. Specifically, we compare lexical features (lexical density, type-token ratio, core vocabulary and list head coverage) in interpreting and translation into English from French and Italian, both in a monolingual comparable perspective and an intermodal perspective. Our results do not unconditionally support the simplification hypothesis: lexical simplification is observed in mediated English, but is found to be greater when the source language is French, and in interpretations rather than translations. We conclude that this feature is contingent on both the mediation mode and the source languages involved, and that the influence of the latter seems to be stronger than that of the former
Word-formation in original and translated English: source language influence on the use of un- and less
This article aims to assess whether the word-formation features of translated language, as opposed to original language, are source language (SL)-dependent or translation-related. To do so, we analyze the use of the -less and un- negative affixes in original English and in English translated from four SL: French, Italian, Dutch and German. Findings based on the Europarl corpus show that the use of -less and un- in translated English is partially SL-dependent
Going Beyond Counting First Authors in Author Co-citation Analysis
The present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Enriching the phraseological coverage of high-frequency adverbs in English-French bilingual dictionaries
The Complementary Contribution of Comparable and Parallel Corpora to Crosslinguistic Studies
- …
