Simple Unsupervised Keyphrase Extraction using Sentence Embeddings (Research Paper Walkthrough)

#naturallanguageprocessing #researchpaperwalkthrough #datascience #keywordextraction
Keywords/Keyphrase extraction is the task of extracting relevant and representative words that best describe the underlying document

⏩ Abstract : Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amounts of labeled training data and generalizes very poorly outside the domain of the training data. At the same time, unsupervised systems have poor accuracy, and often do not generalize well, as they require the input document to belong to a larger corpus also given as input. Addressing these drawbacks, in this paper, we tackle keyphrase extraction from single documents with EmbedRank: a novel unsupervised method, that leverages sentence embeddings. EmbedRank achieves higher F-scores than graph-based state of the art systems on standard datasets and is suitable for real-time processing of large amounts of Web data. With EmbedRank, we also explicitly increase coverage and diversity among the selected keyphrases by introducing an embedding-based maximal marginal relevance (MMR) for new phrases. A user study including over 200 votes showed that, although reducing the phrases' semantic overlap leads to no gains in F-score, our high diversity selection is preferred by humans.

⏩ OUTLINE:
0:00 - Intro & Overview
4:15 - Diversity Problem in Keyphrase Extraction
6:03 - Main Algorithm
8:35 - Diagramatic Flow of Main Algorithm
10:02 - Maximal Marginal Relevance (MMR)
15:35 - Sentence Embedding Techniques - Doc2Vec and Sent2Vec
20:13 - My thoughts and takeaways on the paper

⏩ Paper: https://arxiv.org/abs/1801.04470
⏩ Authors: Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl, Martin Jaggi
⏩ Organisation: Machine Learning and Optimization Laboratory, EPFL

⏩ IMPORTANT LINKS:
MMR (Maximal Margin Relevance) - http://www.cs.bilkent.edu.tr/~canf/CS533/hwSpring14/eightMinPresentations/handoutMMR.pdf
Topic Rank (Keyword Extraction) - https://www.aclweb.org/anthology/I13-1062/
WordAttraction Rank (Keyword Extraction) - https://pdfs.semanticscholar.org/bd37/94c777af5ba363abae5708050ea78ecc97e2.pdf
TextRank (Keyword Extraction) - https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf

*********************************************
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 https://www.buymeacoffee.com/TechvizCoffee

*********************************************
⏩ Youtube - https://youtube.com/channel/UCoz8NrwgL7U9535VNc0mRPA
⏩ Blog - https://prakhartechviz.blogspot.com
⏩ LinkedIn - https://linkedin.com/in/prakhar21
⏩ Medium - https://medium.com/@prakhar.mishra
⏩ GitHub - https://github.com/prakhar21
*********************************************

Please feel free to share out the content and subscribe to my channel :)

⏩ Subscribe - https://youtube.com/channel/UCoz8NrwgL7U9535VNc0mRPA?sub_confirmation=1

Tools I use for making videos :)
⏩ iPad - https://tinyurl.com/y39p6pwc
⏩ Apple Pencil - https://tinyurl.com/y5rk8txn
⏩ GoodNotes - https://tinyurl.com/y627cfsa

#techviz #datascienceguy #machinelearning #wordembeddings