Related papers: The Impact of Text Presentation on Translator Perf…

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in…

Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale,…

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…

Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management. Despite their ubiquity, existing large language model based approaches typically treat tables as plain text,…

Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time…

Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle…

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…

Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because relevant information is often distributed across multiple sheets with heterogeneous schemas,…

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as information retrieval or text summarization. In this work, we…

Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel…

As strong machine translation (MT) systems are increasingly based on large language models (LLMs), reliable quality benchmarking requires methods that capture their ability to leverage extended context. This study compares two commercial MT…

Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task. We empirically test this claim with alternative evaluation protocols,…

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

Interpreters facilitate multi-lingual meetings but the affordable set of languages is often smaller than what is needed. Automatic simultaneous speech translation can extend the set of provided languages. We investigate if such an automatic…

Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…

Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…

Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT)…