Neural conditional language generation models achieve the state-of-the-a...
Scene Text Recognition (STR) models have achieved high performance in re...
Despite recent progress in video and language representation learning, t...
We present Burst2Vec, our multi-task learning approach to predict emotio...
Recent efforts within the AI community have yielded impressive results
t...
Recently, there has been a surge in research in multimodal machine
trans...
Understanding toxicity in user conversations is undoubtedly an important...
In traditional Visual Question Generation (VQG), most images have multip...
Current Machine Translation (MT) systems achieve very good results on a
...
Sentence-level Quality estimation (QE) of machine translation is
traditi...
The societal issue of digital hostility has previously attracted a lot o...
Recent Quality Estimation (QE) models based on multilingual pre-trained
...
Quality Estimation (QE) is the task of automatically predicting Machine
...
We present BERTGEN, a novel generative, decoder-only model which extends...
Data augmentation is an approach that can effectively improve the perfor...
Despite peer-reviewing being an essential component of academia since th...
Translating text into a language unknown to the text's author, dubbed
ou...
Neural Machine Translation models are brittle to input noise. Current
ro...
This paper introduces a large-scale multimodal and multilingual dataset ...
Reinforcement Learning (RL) is a powerful framework to address the
discr...
This paper addresses the problem of simultaneous machine translation (Si...
Quality estimation aims to measure the quality of translated content wit...
Pre-trained language models have been shown to improve performance in ma...
Conventional models for Visual Question Answering (VQA) explore determin...
Automatic generation of video descriptions in natural language, also cal...
In this paper, we teach machines to understand visuals and natural langu...
Automatic evaluation of language generation systems is a well-studied pr...
Since obtaining a perfect training dataset (i.e., a dataset which is
con...
We present MLQE-PE, a new dataset for Machine Translation (MT) Quality
E...
Simultaneous machine translation (SiMT) aims to translate a continuous i...
Quality Estimation (QE) is an important component in making Machine
Tran...
In order to simplify a sentence, human editors perform multiple rewritin...
Multimodal machine translation involves drawing information from more th...
This paper describes the cascaded multimodal speech translation systems
...
This paper describes the Imperial College London team's submission to th...
Devising metrics to assess translation quality has always been at the co...
Neural Machine Translation (NMT) models have been proved strong when
tra...
Localizing phrases in images is an important part of image understanding...
We introduce EASSE, a Python package aiming to facilitate and standardis...
We address the task of text translation on the How2 dataset using a stat...
We address the task of evaluating image description generation systems. ...
A major obstacle to the development of Natural Language Processing (NLP)...
Previous work on multimodal machine translation has shown that visual
in...
Current work on multimodal machine translation (MMT) has suggested that ...
In this paper, we introduce How2, a multimodal collection of instruction...
In an attempt to improve overall translation quality, there has been an
...
We hypothesize that end-to-end neural image captioning systems work seem...
A popular application of machine translation (MT) is gisting: MT is cons...
We address the task of detecting foiled image captions, i.e. identifying...
We report the findings of the second Complex Word Identification (CWI) s...