Related papers: ForMaT: Dataset for Visually-Grounded Multilingual…
This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text…
Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with…
Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In…
Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstrated on image representations. Recent works aiming at…
Language barriers in scientific documents hinder the diffusion and development of science and technologies. However, prior efforts in translating such documents largely overlooked the information in layouts. To bridge the gap, we introduce…
In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a…
Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…
This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, Hausa, Swahili, Yor\`ub\'a, and Zulu. The dataset comprises 334 health and 271 information…
Multimodal machine translation (MMT) is a challenging task that seeks to improve translation quality by incorporating visual information. However, recent studies have indicated that the visual information provided by existing MMT datasets…
Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this…
A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint…
Recent research in the field of multimodal machine translation (MMT) has indicated that the visual modality is either dispensable or offers only marginal advantages. However, most of these conclusions are drawn from the analysis of…
Leveraging the visual modality effectively for Neural Machine Translation (NMT) remains an open problem in computational linguistics. Recently, Caglayan et al. posit that the observed gains are limited mainly due to the very simple, short,…
Image Translation (IT) holds immense potential across diverse domains, enabling the translation of textual content within images into various languages. However, existing datasets often suffer from limitations in scale, diversity, and…
The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large…
Neural Machine Translation (NMT) models are typically trained on datasets with limited exposure to Scientific, Technical and Educational domains. Translation models thus, in general, struggle with tasks that involve scientific understanding…
In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results in three research domains: (i) Building clean, web-mined…
Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…
Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat translation). Although the dataset-specific models have achieved…
Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework…