arXiv 1707.044812017-07-14cs.CL

LIUM-CVC Submissions for WMT17 Multimodal Translation Task

University of Le Mans（勒芒大学）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）

Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz, Joost van de Weijer

备注：: MMT System Description Paper for WMT17

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

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 explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En-De and En-Fr language pairs according to the automatic evaluation metrics METEOR and BLEU.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

LIUM-CVC Submissions for WMT18 Multimodal Translation Task

Le Mans University（勒芒大学）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）

This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previous multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions ranked first for English-French and second for English-German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.

2018-09-01cs.CL

LIUM Machine Translation Systems for WMT17 News Translation Task

University of Le Mans（勒芒大学）

This paper describes LIUM submissions to WMT17 News Translation Task for English-German, English-Turkish, English-Czech and English-Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target monolingual corpora for back-translation. The impact of back-translation quantity and quality is also analyzed for English-Turkish where our post-deadline submission surpassed the best entry by +1.6 BLE…

2017-07-14cs.CL

The MeMAD Submission to the IWSLT 2018 Speech Translation Task

University of Helsinki（赫尔辛基大学）；Aalto University（阿尔托大学）

This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time. All of our systems start by transcribing the audio into text through an automatic speech recognition (ASR) model trained on the TED-LIUM English Speech Recognition Corpus (TED-LIUM). Afterwards, we feed the transcripts into English-German text-ba…

2018-10-24cs.CL

NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems

Laboratoire d’Informatique de l’Université du Maine (LIUM)（曼恩大学计算机实验室（LIUM））

In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. nmtpy decouples the specification of a network from the training and inference utilities to simplify the addition of a new architecture and reduce the amount of boilerplate code to be written. nmtpy has been used for LIUM's top-ranked submissions to WMT Multimodal Machine Translation and News Translation tasks in 2016 and 2017.

2017-06-01cs.CL

ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020

Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；Avignon Université（阿维尼翁大学）；Le Mans Université（勒芒大学）

This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Université), LIG (Université Grenoble Alpes), and LIUM (Le Mans Université). Attention-based encoder-decoder models, trained end-to-end, were used for our submissions to the offline speech translation track. Our contributions focused on data augmentation and ensembling of multiple mode…

2020-05-24cs.CLeess.AS

Does Multimodality Help Human and Machine for Translation and Image Captioning?

LIUM, University of Le Mans（勒芒大学LIUM）；Galatasaray University（加拉塔萨雷大学）；CVC, Universitat Autonoma de Barcelona（巴塞罗那自治大学CVC）

This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate the usefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.

2016-08-16cs.CLcs.LGcs.NE