paper-with-me

Papers

Multimodal Machine Translation with Embedding Prediction

2019-04-01 · NAACL 2019 6 · Tosho Hirasawa, Hayahide Yamagishi, Yukio Matsumura, Mamoru Komachi

Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from a shortage of available training data, resulting in poor performance for translating rare words. In NMT, pretrained word embeddings have been shown to improve NMT of low-resource domains, and a search-based approach is proposed to address the rare word problem. In this study, we effectively combine these two approaches in the context of multimodal NMT and explore how we can take full advantage of pretrained word embeddings to better translate rare words. We report overall performance improvements of 1.24 METEOR and 2.49 BLEU and achieve an improvement of 7.67 F-score for rare word translation.

📄 PDF Abstract BibTeX arXiv:1904.00639

Code (1)

toshohirasawa/nmtpytorch-emb-pred 공식 구현 pytorch

Tasks

Machine TranslationMultimodal Machine TranslationNMTPredictionTranslationWord EmbeddingsWord Translation

Similar Papers 제목 키워드 기반

Debiasing Word Embeddings Improves Multimodal Machine Translation

2019-05-24 · WS 2019 8 · Tosho Hirasawa, Mamoru Komachi

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings …

Machine TranslationMultimodal Machine TranslationNMTTranslation+1

Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation

2017-07-04 · Jean-Benoit Delbrouck, Stéphane Dupont, Omar Seddati

In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English. This is considered as the multimodal…

Dense CaptioningMachine Translationobject-detectionObject Detection+3

Hindi Visual Genome: A Dataset for Multimodal English-to-Hindi Machine Translation

2019-07-21 · Shantipriya Parida, Ondřej Bojar, Satya Ranjan Dash

Visual Genome is a dataset connecting structured image information with English language. We present ``Hindi Visual Genome'', a multimodal dataset consisting of text and images suitable for English-Hindi multimodal machi…

Machine TranslationMultimodal Machine TranslationTranslation

On Leveraging the Visual Modality for Neural Machine Translation

2019-10-07 · WS 2019 10 · Vikas Raunak, Sang Keun Choe, Quanyang Lu, Yi Xu 외

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 …

Machine TranslationMultimodal Machine TranslationNMTSentence+1

Multimodal Quality Estimation for Machine Translation

2020-07-01 · ACL 2020 6 · Shu Okabe, Fr{\'e}d{\'e}ric Blain, Lucia Specia

We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. We compare various multimodality integration and fusion strategies. For both senten…

Machine TranslationSentenceTranslation