paper-with-me

Papers

Topic-Guided Abstractive Text Summarization: a Joint Learning Approach

2020-10-20 · Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang, Ling Fan, Zhe Wang

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 topic modeling with a Transformer-based sequence-to-sequence (seq2seq) model in a joint learning framework. This design can learn and preserve the global semantics of the document, which can provide additional contextual guidance for capturing important ideas of the document, thereby enhancing the generation of summary. We conduct extensive experiments on two datasets and the results show that our proposed model outperforms many extractive and abstractive systems in terms of both ROUGE measurements and human evaluation. Our code is available at: https://github.com/chz816/tas.

📄 PDF Abstract BibTeX arXiv:2010.10323

Code (1)

chz816/tas 공식 구현 pytorch

Tasks

Abstractive Text SummarizationExtractive SummarizationText Summarization

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
ProphetNet ProphetNet is a sequence-to-sequence pre-training model that introduces a novel self-supervised objective named future n-gram prediction and the proposed n-stream…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Topic-Guided Abstractive Multi-Document Summarization

2021-10-21 · Findings (EMNLP) 2021 11 · Peng Cui, Le Hu

A critical point of multi-document summarization (MDS) is to learn the relations among various documents. In this paper, we propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneo…

Document SummarizationGraph-to-SequenceMulti-Document SummarizationMulti-Task Learning

Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization

2021-11-01 · EMNLP (newsum) 2021 11 · Khalil Mrini, Can Liu, Markus Dreyer

We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of g…

Abstractive Text SummarizationDeep Reinforcement LearningReinforcement Learning (RL)

CATS: Customizable Abstractive Topic-based Summarization

2019-05-24 · Anonymous

Neural sequence-to-sequence models are a recently proposed family of approaches used in abstractive summarization of text documents, useful for producing condensed versions of source text narratives without being restric…

Abstractive Text Summarization

A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization

2018-05-09 · Li Wang, Junlin Yao, Yunzhe Tao, Li Zhong 외

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequen…

Abstractive Text SummarizationDiversityInformativenessText Summarization

Knowledge and Keywords Augmented Abstractive Sentence Summarization

2021-11-01 · EMNLP (newsum) 2021 11 · Shuo Guan

In this paper, we study the abstractive sentence summarization. There are two essential information features that can influence the quality of news summarization, which are topic keywords and the knowledge structure of t…

News SummarizationSentenceSentence Summarization