Related papers: Differentiable N-gram Objective on Abstractive Sum…

Recently, encoder-decoder models are widely used in social media text summarization. However, these models sometimes select noise words in irrelevant sentences as part of a summary by error, thus declining the performance. In order to…

Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to the reference summary.…

This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and…

We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content. The idea is to incorporate neural…

Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to…

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms.…

Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be categorically…

Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under…

Recent work on abstractive summarization has made progress with neural encoder-decoder architectures. However, such models are often challenged due to their lack of explicit semantic modeling of the source document and its summary. In this…

Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or retrieval-augmented pipelines achieve progress in fluency but remain…

This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. Instead of following the commonly used framework of extracting sentences individually and modeling the relationship between…

Existing graph- and hypergraph-based algorithms for document summarization represent the sentences of a corpus as the nodes of a graph or a hypergraph in which the edges represent relationships of lexical similarities between sentences.…

Sequential labeling is a fundamental NLP task, forming the backbone of many applications. Supervised learning of Seq2Seq models has shown great success on these problems. However, the training objectives are still significantly disconnected…

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when…

In natural language processing tasks performance of the models is often measured with some non-differentiable metric, such as BLEU score. To use efficient gradient-based methods for optimization, it is a common workaround to optimize some…

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive. We argue that, to address these issues,…

Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to…

Natural Language Processing is booming with its applications in the real world, one of which is Text Summarization for large texts including news articles. This research paper provides an extensive comparative evaluation of extractive and…

Neural models for abstractive summarization tend to achieve the best performance in the presence of highly specialized, summarization specific modeling add-ons such as pointer-generator, coverage-modeling, and inferencetime heuristics. We…