UvA-DARE (Digital Academic Repository) A Distributed Inflection Model for Translating into Morphologically Rich Languages

UvA-DARE (Digital Academic Repository) A Distributed Inflection Model for Translating into Morphologically Rich Languages

This work introduces soft tags, which are under-specified representations retaining all possible morphological attributes of a word, and adopts a neural network approach in order to learn distributed representations for the soft tags and their interactions.

A transfer grammar for mapping USR to MRS: Toward multilingual generation

Semantic representation-based multilingual natural language generation (NLG) is still a challenging problem in computational linguistics. In this paper, we present universal semantic representation (USR), a new semantic representation that provides semantics at multiple levels, including the speaker's intention and dis...

Semantic and Syntactic Preserving Parallel Corpus Augmentation for Neural Machine Translation

In the domain of Natural Language Processing (NLP) Parallel text corpora are crucial for training machine translation systems and multilingual NLP applications. They provide the necessary context for learning translation models (e.g., statistical MT or neural MT). In addition, they foster semantic, syntactic, and struc...

Bridging the linguistic divide: recent developments in machine translation for Indian languages

This paper analyses various recent state-of-the-art variants of large language models (LLMs) and neural machine translation (NMT) for Indian languages in comparison to statistical machine translation (SMT) and tackles key questions, such as idiomatic expressions, morphologically complex grammar or the scarceness of par...

Neural Machine Translation for Moor´e, a Low-Resource Language

Efficient Adaptation of English Language Models for Morphologically Rich and Underrepresented Languages: The Case of Arabic

A resource-efficient adaptation of the English-pretrained ModernBERT for Arabic, employing continued pretraining on large Arabic corpora followed by lightweight head-only fine-tuning with a frozen encoder, demonstrating that modern English encoder architectures can be efficiently transferred to Arabic through language-...