#textsummarization #unsupervised #naturallangaugeprocessing #research
In this video, we will do a walkthrough of the paper that proposes a Unsupervised Multi-document text summarisation method based on Sentence Graph Compression Technique. This work claims to be produce equivalent results compared to supervised models in the domain.

Please feel free to share out the content and subscribe to my channel :)
⏩ Subscribe - [ Ссылка ]

⏩ Abstract: Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.

⏩ OUTLINE:
0:00 - Abstract and Introduction
2:18 - Text Processing (Proposed Pipeline - Step 1)
3:15 - Sentence Graph Construction (Proposed Pipeline - Step 2)
6:32 - Spectral Clustering on Sentence Graphs (Proposed Pipeline - Step 3)
11:53 - Multi-sentence Compression for Summary (Proposed Pipeline - Step 4)
15:59 - Diagramatic Flow of the Pipeline

⏩ Paper Title: SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
⏩ Paper Link: [ Ссылка ]
⏩ Paper Authors: Jinming Zhao, Ming Liu, Longxiang Gao, Yuan Jin, Lan Du, He Zhao, He Zhang, Gholamreza Haffari
⏩ Organization: Monash University, Shandesitong, Deakin University

Multi-Sentence Compression: Finding Shortest Paths in Word Graphs - [ Ссылка ]
Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression - [ Ссылка ]
Another video on Unsupervised Multi-document Summarization - [ Ссылка ]

*********************************************
If you want to support me financially which totally optional and voluntary :) ❤️
You can consider buying me chai ( because i don't drink coffee :) ) at [ Ссылка ]

*********************************************
⏩ Youtube - [ Ссылка ]
⏩ Blog - [ Ссылка ]
⏩ LinkedIn - [ Ссылка ]
⏩ Medium - [ Ссылка ]
⏩ GitHub - [ Ссылка ]
*********************************************

Tools I use for making videos :)
⏩ iPad - [ Ссылка ]
⏩ Apple Pencil - [ Ссылка ]
⏩ GoodNotes - [ Ссылка ]

Please feel free to share out the content and subscribe to my channel :)
⏩ Subscribe - [ Ссылка ]

About Me:
I am Prakhar Mishra and this channel is my passion project. I am currently pursuing my MS (by research) in Data Science. I have an industry work-ex of 3 years in the field of Data Science and Machine Learning with a particular focus in Natural Langauge Processing (NLP).

#multidocument #summarization #graphcompression #techviz #datascienceguy #researchpaperwalkthrough #nlp #embeddings

свернуть