In this paper, we introduce How2, a multimodal collection of instructional videos with English
subtitles and crowdsourced Portuguese translations. We also present integrated sequence …

Current work on multimodal machine translation (MMT) has suggested that the visual
modality is either unnecessary or only marginally beneficial. We posit that this is a …

In this paper, we study abstractive summarization for open-domain videos. Unlike the
traditional text news summarization, the goal is less to" compress" text information but rather …

Unsupervised machine translation (UMT) has recently attracted more attention from
researchers, enabling models to translate when languages lack parallel corpora. However …

Multimodal machine translation involves drawing information from more than one modality,
based on the assumption that the additional modalities will contain useful alternative views …

This paper describes the monomodal and multimodal Neural Machine Translation systems
developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly …

We propose a multimodal neural machine translation (MNMT) method with semantic image
regions called region-attentive multimodal neural machine translation (RA-NMT). Existing …

In the process of globalization, machine translation has undergone a long period of
evolution and development. Although the development level of machine translation has …

While recent changes in Machine Translation state-of-the-art brought translation quality a
step further, it is regularly acknowledged that the standard automatic metrics do not provide …

This paper presents MAST, a new model for Multimodal Abstractive Text Summarization that
utilizes information from all three modalities--text, audio and video--in a multimodal video …