• Corpus ID: 17751318

PPS Gen : Learning-Based Presentation Slides Generation for Academic Papers

@inproceedings{Shaikh2015PPSG,
  title={PPS Gen : Learning-Based Presentation Slides Generation for Academic Papers},
  author={Parvez Shaikh},
  year={2015}
}
Some rough structure for slide presentations from papers capable to save the author much time when organizing presentations. In this paper we investigate different perspective for academic papers slide generation. To write the slides from scratch takes a lot of time of presenter. They generally contain several sections like abstract, introduction, related work, proposed method, experiments and conclusions. To maintain uniqueness in preparing slides this idea is essential and unique. Each… 
3 Citations
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
TLDR
An Automatic Slide Generation System is proposed that works on natural language processing (NLP) rules to classify data for the desired slides and is more reliable than the existing system.
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
TLDR
This paper is enforcing the automated PPT creation from multi-documents of different extensions based on input query or title that formulate extraction of valuable information source and model a presentation view to automating slide creation using integer linear programming (ILP) method to generate well-structured slides by selecting and aligning key phrases and sentences.
Leveraging Contextual Sentence Relations for Extractive Summarization Using a Neural Attention Model
TLDR
A neural network model, Contextual Relation-based Summarization (CRSum), is proposed to take advantage of contextual relations among sentences so as to improve the performance of sentence regression and can achieve comparable performance with state-of-the-art approaches.

References

SHOWING 1-10 OF 12 REFERENCES
PPSGen: Learning-Based Presentation Slides Generation for Academic Papers
  • Yue Hu, Xiaojun Wan
  • Computer Science
    IEEE Transactions on Knowledge and Data Engineering
  • 2015
TLDR
Evaluation results on a test set of 200 pairs of papers and slides collected on the web demonstrate that the proposed PPSGen system can generate slides with better quality.
Automatic Slide Presentation from Semantically Annotated Documents
TLDR
This paper discusses how to automatically generate slide shows by extracting relevant sentences and paraphrasing them to an itemized summary in the GDA tagset, an XML tagset which allows machines to automatically infer the semantic structure underlying the raw documents.
Generating Extractive Summaries of Scientific Paradigms
TLDR
C-LexRank is proposed, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences and shows that citations have unique information amenable to creating a summary.
The automated design of believable dialogues for animated presentation teams
TLDR
A new style for presenting information is investigated and the notion of presentation teams which—rather than addressing the user directly—convey information in the style of performances to be observed by the user is introduced.
Automatically summarising Web sites: is there a way around it?
TLDR
This work suggests a new approach, which relies on the structure of hypertext and the way people describe information in it, which offers an easy way to produce unbiased, coherent, and contentfull summaries of Web sites.
A Scalable Global Model for Summarization
TLDR
This work presents an Integer Linear Program for exact inference under a maximum coverage model for automatic summarization, and shows how to include sentence compression in the ILP formulation, which has the desirable property of performing compression and sentence selection simultaneously.
Jointly Learning to Extract and Compress
TLDR
A joint model of sentence extraction and compression for multi-document summarization and its jointly extracted and compressed summaries outperform both unlearned baselines and the authors' learned extraction-only system on both ROUGE and Pyramid, without a drop in judged linguistic quality.
Abstractive Summarization of Line Graphs from Popular Media
TLDR
This paper presents the work on abstractive summarization of line graphs, which involves hypothesizing the intended message of a line graph and using it as the core of a summary of the graphic.
Towards Robust Context-Sensitive Sentence Alignment for Monolingual Corpora
TLDR
A new monolingual sentence alignment algorithm is presented, combining a sentence-based TF*IDF score, turned into a probability distribution using logistic regression, with a global alignment dynamic programming algorithm, achieving a substantial improvement in accuracy over existing systems.
AUEB at TAC 2008
TLDR
Aueb participated in the summarization and textual entailment recognition tracks of tac 2008 and trained a Support Vector Regression model that is used to rank the summary’s candidate sentences.
...
1
2
...