Related papers: An Unsupervised Masking Objective for Abstractive …
Unsupervised learning is the most challenging problem in machine learning and especially in deep learning. Among many scenarios, we study an unsupervised learning problem of high economic value --- learning to predict without costly pairing…
We present work on summarising deliberative processes for non-English languages. Unlike commonly studied datasets, such as news articles, this deliberation dataset reflects difficulties of combining multiple narratives, mostly of poor…
Sentence scoring and sentence selection are two main steps in extractive document summarization systems. However, previous works treat them as two separated subtasks. In this paper, we present a novel end-to-end neural network framework for…
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate.…
While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability. We introduce a Wikipedia-derived…
Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the…
Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with…
We introduce 'extreme summarization', a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question ``What is the article about?''. We argue that extreme summarization, by nature,…
State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties. In this paper we propose a privacy-preserving approach to…
Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon…
A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the…
The task of unsupervised semantic segmentation aims to cluster pixels into semantically meaningful groups. Specifically, pixels assigned to the same cluster should share high-level semantic properties like their object or part category.…
A typical journalistic convention in news articles is to deliver the most salient information in the beginning, also known as the lead bias. While this phenomenon can be exploited in generating a summary, it has a detrimental effect on…
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on…
Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural…
Extractive summarization aims at selecting a set of indicative sentences from a source document as a summary that can express the major theme of the document. A general consensus on extractive summarization is that both relevance and…
Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the…
Recently, opinion summarization, which is the generation of a summary from multiple reviews, has been conducted in a self-supervised manner by considering a sampled review as a pseudo summary. However, non-text data such as image and…
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset. Existing methods opt to drop the noisy samples or tokens from the…
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging…