Related papers: Translating away Translationese without Parallel D…

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize the task as a translation between task-specific input text…

Unsupervised text style transfer aims at training a generative model that can alter the style of the input sentence while preserving its content without using any parallel data. In this paper, we employ powerful pre-trained large language…

Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…

End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In…

Direct speech-to-speech translation (S2ST) has gradually become popular as it has many advantages compared with cascade S2ST. However, current research mainly focuses on the accuracy of semantic translation and ignores the speech style…

Simultaneous interpretation, the translation of speech from one language to another in real-time, is an inherently difficult and strenuous task. One of the greatest challenges faced by interpreters is the accurate translation of difficult…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

This study explores the distinctions between neural machine translation (NMT) and human translation (HT) through the lens of translation relations. It benchmarks HT to assess the translation techniques produced by an NMT system and aims to…

Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper…

Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance…

This numeric evaluation of string metric accuracy is based on the following idea: taking the paragraph of text in one language sort all paragraphs of the document in other language by similarity with given paragraph string and consider…

We argue that translation quality alone is not a sufficient metric for measuring knowledge transfer in multilingual neural machine translation. To support this claim, we introduce Representational Transfer Potential (RTP), which measures…

This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge,…

Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences…

Back-translation is a widely used data augmentation technique which leverages target monolingual data. However, its effectiveness has been challenged since automatic metrics such as BLEU only show significant improvements for test examples…

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse…

Machine translation (MT) systems, especially when designed for an industrial setting, are trained with general parallel data derived from the Web. Thus, their style is typically driven by word/structure distribution coming from the average…