Related papers: eSCAPE: a Large-scale Synthetic Corpus for Automat…

Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood…

Most prior work on exemplar-based syntactically controlled paraphrase generation relies on automatically-constructed large-scale paraphrase datasets, which are costly to create. We sidestep this prerequisite by adapting models from prior…

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both…

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE). Note that high-quality instruction data is the vital key for enhancing…

Current Machine Translation systems achieve very good results on a growing variety of language pairs and data sets. However, it is now well known that they produce fluent translation outputs that often can contain important meaning errors.…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Automatic Speech Recognition (ASR) and text Machine Translation…

A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT…

We introduce Mistake Attribution (MATT), a new task for fine-grained understanding of human mistakes in egocentric videos. While prior work detects whether a mistake occurs, MATT attributes the mistake to what part of the instruction is…

Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…

End-to-end automatic speech translation (AST) relies on data that combines audio inputs with text translation outputs. Previous work used existing large parallel corpora of transcriptions and translations in a knowledge distillation (KD)…

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…

Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM have shown state-of-the-art…

We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-grained prosody transfer between any pair of seen speakers.…

An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this `split…

This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results…

Parallel data are an important part of a reliable Statistical Machine Translation (SMT) system. The more of these data are available, the better the quality of the SMT system. However, for some language pairs such as Persian-English,…

Lecture transcript translation helps learners understand online courses, however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel…