Related papers: Testing Machine Translation via Referential Transp…
In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source…
Many machine translation models are trained on bilingual corpus, which consist of aligned sentence pairs from two different languages with same semantic. However, there is a qualitative discrepancy between train and test set in bilingual…
The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages. Despite impressive empirical results and an…
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their…
Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for…
Current transformer language models (LM) are large-scale models with billions of parameters. They have been shown to provide high performances on a variety of tasks but are also prone to shortcut learning and bias. Addressing such incorrect…
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),…
Since the 1950s, machine translation (MT) has become one of the important tasks of AI and development, and has experienced several different periods and stages of development, including rule-based methods, statistical methods, and recently…
Literary translation requires balancing target-language fluency with faithfulness to the source. Recent large language models (LLMs) often produce fluent translations, but it remains unclear whether fluency corresponds to semantic…
Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers…
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robustness of neural machine translation systems to numerical text…
In professional settings, translation is guided by communicative goals and client needs, often formalized as specifications. While existing evaluation frameworks acknowledge the importance of such specifications, these specifications are…
Recent research suggests that neural machine translation (MT) in the news domain has reached human-level performance, but for other professional domains, it is far below the level. In this paper, we conduct a fine-grained systematic human…
This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong…
Benchmarks that reflect the diversity and complexity of real-world documents are essential for accurately evaluating Automatic Text Recognition (ATR) systems, especially Vision-Large Language Models (vLLMs). Although recent models…
Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…
Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system,…
This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid…
Large language models have demonstrated parallel and even superior translation performance compared to neural machine translation (NMT) systems. However, existing comparative studies between them mainly rely on automated metrics, raising…
Neural Machine Translation (NMT) is the task of translating a text from one language to another with the use of a trained neural network. Several existing works aim at incorporating external information into NMT models to improve or control…