We present a novel supervised word alignment method based on cross-language span
prediction. We first formalize a word alignment problem as a collection of independent …

Most existing word alignment methods rely on manual alignment datasets or parallel
corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we …

Parallel texts represent a very valuable resource in many applications of natural language
processing. The fundamental step in creating parallel corpus is the alignment. Sentence …

Although a machine translation model trained with a large in-domain parallel corpus
achieves remarkable results, it still works poorly when no in-domain data are available. This …

The multilingual parallel corpus is an important resource for many applications of natural
language processing (NLP). For machine translation, the size and quality of the training …

The problem of hallucination and omission, a long-standing problem in machine translation
(MT), is more pronounced when a large language model (LLM) is used in MT because an …

Cross-lingual annotation projection is a practical method for improving performance on low
resource structured prediction tasks. An important step in annotation projection is obtaining …

This paper seeks to leverage translations of Ancient Greek texts to enhance the performance
of automatic word sense disambiguation (WSD). Satisfactory WSD in Ancient Greek is …

Bilingual corpus is an important resource for many applications of natural language
processing (NLP). About low-resource language pairs, it is more necessary to build them …

Doğal dil işleme, yapay zekânın ve dil biliminin gelişimiyle son yıllarda önem kazandı. Çeviri
şirketlerinin yapmış olduğu,“Türkçe'den İngilizce'ye-İngilizce'den Türkçe'ye” birebir çevirileri …