Related papers: Multiple References with Meaningful Variations Imp…
Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT),…
Paraphrases, the rewordings of the same semantic meaning, are useful for improving generalization and translation. However, prior works only explore paraphrases at the word or phrase level, not at the sentence or corpus level. Unlike…
We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional diverse references can provide…
Most Sign Language Translation (SLT) corpora pair each signed utterance with a single written-language reference, despite the highly non-isomorphic relationship between sign and spoken languages, where multiple translations can be equally…
The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on…
Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. When used in place of original references, the paraphrased versions produce metric…
Literary translation is a culturally significant task, but it is bottlenecked by the small number of qualified literary translators relative to the many untranslated works published around the world. Machine translation (MT) holds potential…
Recent studies in prompting large language model (LLM) for document-level machine translation (DMT) primarily focus on the inter-sentence context by flatting the source document into a long sequence. This approach relies solely on the…
Simultaneous machine translation (SiMT) generates translation while reading the whole source sentence. However, existing SiMT models are typically trained using the same reference disregarding the varying amounts of available source…
Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…
Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though…
Large Language Models (LLMs) have demonstrated significant capabilities in machine translation. However, their translation quality is sometimes questioned, as the generated outputs may deviate from expressions typically used by native…
One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models…
This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…
Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel…
The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors…
Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates that the human references should be of very high quality. However, there are no…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate…
Metaphorical expressions are difficult linguistic phenomena, challenging diverse Natural Language Processing tasks. Previous works showed that paraphrasing a metaphor as its literal counterpart can help machines better process metaphors on…