Related papers: DeepSubQE: Quality estimation for subtitle transla…
This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…
Analytic Translation Quality Evaluation (TQE), based on Multidimensional Quality Metrics (MQM), traditionally uses a linear error-to-penalty scale calibrated to a reference sample of 1000-2000 words. However, linear extrapolation biases…
Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assign different labels to a given text, the quality of produced…
Watching movies and TV shows with subtitles enabled is not simply down to audibility or speech intelligibility. A variety of evolving factors related to technological advances, cinema production and social behaviour challenge our perception…
Quality Estimation (QE) is estimating quality of the model output during inference when the ground truth is not available. Deriving output quality from the models' output probability is the most trivial and low-effort way. However, we show…
Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…
We present an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space. The key idea is to perform image retrieval over a database of images that are captioned in the target…
We propose an automatic preprocessing and ensemble learning for segmentation of cell images with low quality. It is difficult to capture cells with strong light. Therefore, the microscopic images of cells tend to have low image quality but…
Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner.…
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. MNMT has been useful in improving translation quality as a result of knowledge transfer. MNMT is more promising…
We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the…
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep…
Large Language Models (LLMs) have shown remarkable performance across a wide range of natural language processing tasks. Quality Estimation (QE) for Machine Translation (MT), which assesses the quality of a source-target pair without…
The surge of audiovisual content on streaming platforms and social media has heightened the demand for accurate and accessible subtitles. However, existing subtitle generation methods primarily speech-based transcription or OCR-based…
We present a large-scale video subtitle translation dataset, BigVideo, to facilitate the study of multi-modality machine translation. Compared with the widely used How2 and VaTeX datasets, BigVideo is more than 10 times larger, consisting…
We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned…
Large language models have demonstrated the capability to perform on machine translation when the input is prompted with a few examples (in-context learning). Translation quality depends on various features of the selected examples, such as…
Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical. In order to evaluate captions more closely to human preferences, metrics need to discriminate between…
Incorporating extra-textual context such as film metadata into the machine translation (MT) pipeline can enhance translation quality, as indicated by automatic evaluation in recent work. However, the positive impact of such systems in…
Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to…