What's new

NLP & Document Understanding

Relevance Feedback Search Based on Automatic Annotation and Classification of Texts

Last edited:

Real-Time Web Scale Event Summarization Using Sequential Decision Making

Graph-Based Text Generation

Knowledge-based Review Generation by Coherence Enhanced Text Planning

Screen Shot 2021-09-29 at 10.23.02 AM.png

Context-aware query design combines knowledge and data for efficient reading and reasoning

SQL Queries for WordPress

$search = $wpdb->escape($search);
$posts = $wpdb->get_results("SELECT ID, post_title, post_content FROM $wpdb->posts WHERE post_status = 'publish' AND (post_title LIKE '%$search%' OR post_content LIKE '%$search%') ORDER BY post_title LIMIT 0,5");

Source: WordPress Plugin Development: Beginner's Guide

Screen Shot 2021-09-12 at 6.23.49 PM.png
Source: Wordpress Web Application Development - Third Edition

Last edited:

Research Graph Meta Model

Last edited:

Query expansion techniques for information retrieval: A survey

Screen Shot 2021-09-09 at 11.48.52 AM.pngScreen Shot 2021-09-09 at 11.56.15 AM.png
Last edited:

Exploiting pivot words to classify and summarize discourse facets of scientific papers

Topic Intersection & Visualization

Last edited:

Cluster-based information retrieval using pattern mining


A Framework towards Computational Narrative Analysis on Blogs

Time-Efficient Creation of an Accurate Sentence Fusion Corpus

"Recent research has investigated methods for generating new sentences using a technique called sentence fusion (Barzilay and McKeown, 2005; Marsi and Krahmer, 2005; Filippova and Strube, 2008) where output sentences are generated by fusing together portions of related sentences."

"Our goal is the generation of accurate fusions between pairs of sentences that have some information in common. To ensure that the task is performed consistently, we abide by the distinction proposed by Marsi and Krahmer (2005) between intersection fusion and union fusion. Intersection fusion results in a sentence that contains only the information that the sentences had in common and is usually shorter than either of the original sentences. Union fusion, on the other hand, results in a sentence that contains all information content from the original two sentences."

"When sentences are too similar, the result of fusion is simply one of the input sentences. For example (Fig. 2), if sentence A contains all the information in sentence B but not vice versa, then B is also their intersection while A is their union and no sentence generation is required. On the other hand, if the two sentences are too dissimilar, then no intersection is possible and the union is just the conjunction of the sentences."

Free PDF Search Tools

Document Cards

This paper got a lot of citations and is still of interest.

Smart Notes


Last edited:

Srikumar et al

  • Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes. Jie Cao, Michael Tanana, Zac Imel, Eric Poitras, David Atkins and Vivek Srikumar. Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
    [pdf] [details]

  • Modeling Biological Processes for Reading Comprehension. Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark and Christopher D. Manning. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
    [pdf] [details] [Best paper award]
Last edited: