Keyphrase Generation Overview and Challenges
Dive into the world of keyphrase generation with a focus on real human annotation methods. Explore the importance of keyphrases in summarizing text efficiently while overcoming challenges such as inaccuracies and vocabulary limitations. Discover the evolution of keyphrase prediction models and the effectiveness of simpler approaches.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Deep Deep keyphrase keyphrase generation generation Group presentation Group presentation Wang Yue 2018.03.27
Puzzle Puzzle Part 0
Puzzle Puzzle Part 0
Puzzle Puzzle Part 0
Ten English Ten English sentences sentences Part 0 1. 2. We use the term keyphrase interchangeably with keyword in the rest of this paper. To overcome the limitations of previous studies, we re-examine the process of keyphrase prediction with a focus on how real human annotators would assign keyphrases A keyphrase provides a succinct and accurate way of describing a subject or a subtopic in a document The model would potentially give preference to the appearing words, which caters to the fact that most keyphrases tend to appear in the source text Previous methods are liable to reproduce factual details inaccurately Summarization is the task of condensing a piece of text to a shorter version that contains the main information from the original Though these systems are promising, they exhibit undesirable behavior such as inaccurately reproducing factual details, an inability to deal with out-of-vocabulary (OOV) words, and repeating themselves We find our simpler approach suffices Originating from Statistical Machine Translation (Koehn, 2009), coverage was adapted for NMT by Tu et al. (2016) 10. We found this to be ineffective, with no discernible reduction in repetition 3. 4. 5. 6. 7. 8. 9. (The first 4 sentences are from the paper deep keyphrase generation while the rest are from the paper Get To The Point: Summarization with Pointer-Generator Networks )
Outline Outline Slides for Deep keyphrase generation (2017 ACL paper) link http://memray.me/uploads/acl17-deep-keyphrase-generation-slides.pdf Transformer Copy mechanism from the paper Get To The Point: Summarization with Pointer-Generator Networks (2017 ACL paper)
Overview Overview Part 1 ACL 2017
Overview Overview Part 1 Task: multi-sentence summarization Challenge Previous methods are liable to reproduce factual details inaccurately Tend to repeat themselves Proposed model: Pointer and generator architecture Coverage mechanism Comment: adopted as a mainstream copy mechanism
Overview Overview Part 1 Pointer-generator model Final distribution:
Deep keyphrase generation Yue Wang, 1155085636, CSE, CUHK Thank you!
