A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion
We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.
Code (1)
Tasks
Abstractive Text SummarizationNews SummarizationText GenerationText SummarizationSimilar Papers 제목 키워드 기반
Composing Elementary Discourse Units in Abstractive Summarization
In this paper, we argue that elementary discourse unit (EDU) is a more appropriate textual unit of content selection than the sentence unit in abstractive summarization. To well handle the problem of composing EDUs into …
Abstractive Text Summarizationreinforcement-learningReinforcement Learning (RL)SentenceTowards End-to-end Speech-to-text Summarization
Speech-to-text (S2T) summarization is a time-saving technique for filtering and keeping up with the broadcast news uploaded online on a daily basis. The rise of large language models from deep learning with impressive te…
Abstractive Text SummarizationSpeech-to-TextText GenerationText Summarization+1Attention Head Masking for Inference Time Content Selection in Abstractive Summarization
How can we effectively inform content selection in Transformer-based abstractive summarization models? In this work, we present a simple-yet-effective attention head masking technique, which is applied on encoder-decoder…
Abstractive Text SummarizationDecoderDocument SummarizationDifferentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization
The IMPRESSIONS section of a radiology report about an imaging study is a summary of the radiologist's reasoning and conclusions, and it also aids the referring physician in confirming or excluding certain diagnoses. A c…
Abstractive Text SummarizationExtractive SummarizationFactorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by facto…
Abstractive Text SummarizationDisentanglementDocument SummarizationDomain Adaptation+1