paper-with-me

Papers

Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations

2019-10-24 · WS 2019 11 · Sangwoo Cho, Chen Li, Dong Yu, Hassan Foroosh, Fei Liu

Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select the most probable set of sentences to form a summary according to a probability measure defined by modeling sentence prominence and pairwise repulsion. Traditionally, these aspects are modelled using shallow and linguistically informed features, but the rise of deep contextualized representations raises an interesting question of whether, and to what extent, contextualized representations can be used to improve DPP modeling. Our findings suggest that, despite the success of deep representations, it remains necessary to combine them with surface indicators for effective identification of summary sentences.

📄 PDF Abstract BibTeX arXiv:1910.11411

Code (0)

등록된 구현이 없습니다.

Tasks

Document SummarizationExtractive SummarizationMulti-Document SummarizationPoint ProcessesSentence

Similar Papers 제목 키워드 기반

Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization

2019-05-31 · ACL 2019 7 · Sangwoo Cho, Logan Lebanoff, Hassan Foroosh, Fei Liu

The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being us…

DecoderDocument SummarizationMulti-Document SummarizationPoint Processes

Learning Determinantal Point Processes in Sublinear Time

2016-10-19 · Christophe Dupuy, Francis Bach

We propose a new class of determinantal point processes (DPPs) which can be manipulated for inference and parameter learning in potentially sublinear time in the number of items. This class, based on a specific low-rank …

Document SummarizationPoint Processes

Multi-Document Summarization withDeterminantal Point Process Attention

2021-07-13 · Journal of Artificial Intelligence Research 2021 7 · Laura Perez-Beltrachini, Mirella Lapata

The ability to convey relevant and diverse information is critical in multi-documentsummarization and yet remains elusive for neural seq-to-seq models whose outputs are of-ten redundant and fail to correctly c…

Document SummarizationMulti-Document Summarization

Large-Margin Determinantal Point Processes

2014-11-06 · Boqing Gong, Wei-Lun Chao, Kristen Grauman, Fei Sha

Determinantal point processes (DPPs) offer a powerful approach to modeling diversity in many applications where the goal is to select a diverse subset. We study the problem of learning the parameters (the kernel matrix) …

Diversityparameter estimationPoint ProcessesVideo Summarization

In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes

2019-09-24 · CONLL 2019 11 · Lei Li, Wei Liu, Marina Litvak, Natalia Vanetik 외

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summar…

Abstractive Text SummarizationDiversityMachine TranslationPoint Processes+1