Idiap NMT System for WAT 2019 Multimodal Translation Task (D19-52)

Copied to clipboard

Challenge: In the past few decades, multi-modality has received critical attention in translation studies, although the benefit of visual modality in machine translation is still in debate.
Approach: They propose to use the Transformer model and IITB English-Hindi parallel corpus as additional data sources for the evaluation and challenge test sets.
Outcome: The proposed system outperforms systems that consider visual information in the English-Hindi Multi-Modal Translation task.

Similar Papers

NLPRL at WAT2019: Transformer-based Tamil – English Indic Task Neural Machine Translation System (D19-52)

Copied to clipboard

Challenge: a majority of Asians speak low to medium resource languages . lack of resources poses a challenge, which requires innovative solutions .
Approach: They propose a Neural Machine Translation system for Tamil-English Indic Task . they train a system for both Tamil-to-English and English-to Tamil pairs .
Outcome: The proposed system is based on a Transformer-based architecture and is not very innovative, but can be treated as an incremental step in this direction.
CVIT’s submissions to WAT-2019 (D19-52)

Copied to clipboard

Challenge: In this paper, we explore multiway-models for Indian languages.
Approach: They propose to use a Transformer architecture to experiment with multilingual models and methods for low-resource languages.
Outcome: The proposed system is feasible in low-resource languages.
Our Neural Machine Translation Systems for WAT 2019 (D19-52)

Copied to clipboard

Challenge: In the last five years, statistical machine translation is gradually fading out in favor of neural machine translation.
Approach: They describe a novel Neural Machine Translation (NMT) system for the WAT 2019 translation tasks they focus on.
Outcome: The proposed system improves translation accuracy while replacing absolute position representations with relative positions.
UCSYNLP-Lab Machine Translation Systems for WAT 2019 (D19-52)

Copied to clipboard

Challenge: Neural machine translation (NMT) has achieved stateof-the-art performance on various language pairs.
Approach: They describe the UCSYNLP-Lab submission to WAT 2019 for Myanmar-English translation tasks in both directions.
Outcome: The proposed translation system improves the performance of Myanmar-English translation tasks.
English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning (D19-52)

Copied to clipboard

Challenge: Multi-modal translation is an emerging task of the MT community, where visual features of image combine with textual features of parallel source-target text to translate sentences.
Approach: They propose to use convolutional neural net-works and visual geometry to extract image features and attention-based Neural MachineTranslation (NMT) system for translation.
Outcome: The proposed multi-modal translation system improves translation quality and improves the quality of the captions of the images.
NTT Neural Machine Translation Systems at WAT 2019 (D19-52)

Copied to clipboard

Challenge: We submitted two systems for scientific paper subtask and timely disclosure subtask . we evaluated the usefulness of incorporating external data from a wide variety of web pages to improve the translation quality.
Approach: They describe two different translation tasks submitted to WAT 2019 . they submitted scientific paper subtasks and timely disclosure subtask .
Outcome: The proposed system performed better on scientific paper and timely disclosure subtasks.
WAT2019: English-Hindi Translation on Hindi Visual Genome Dataset (D19-52)

Copied to clipboard

Challenge: A multimodal translation is a task of translating a source language to a target language . a parallel text corpus and images are used to represent the contextual details of the text .
Approach: They compare a multimodal approach to a parallel text corpus and image caption generation approach to translate text in English to Hindi as a part of WAT2019 shared task.
Outcome: The proposed approach improves the translation of English to Hindi in three tasks . the proposed system is based on a neural network and can be used in healthcare, government, disaster management, etc.
NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT (D19-52)

Copied to clipboard

Challenge: In this paper, we describe our submissions for the following tasks: English–Tamil translation and Russian–Japanese translation.
Approach: They propose to use multilingual domain adaptation and back-translation to improve translations in Russian–Japanese and English–Tamil.
Outcome: The proposed techniques perform better in Russian–Japanese and English–Tamil translation tasks.
Sarah’s Participation in WAT 2019 (D19-52)

Copied to clipboard

Challenge: Using the Transformer architecture, we trained similar systems across different tasks.
Approach: They presented their results in the 6th Workshop on Asian Translation (WAT) translation task and their submissions to the task.
Outcome: The proposed models perform better on tasks with smaller datasets and with smaller heads on multilingual datasets.
LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019 (D19-52)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) is a promising approach for low resource languages.
Approach: They propose to use both Recurrent Neural Networks & Transformer architectures to train NMT models.
Outcome: The proposed model outperforms Statistical Machine Translation (SMT) techniques on a low resource Hindi-English language pair.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations