Software & Demos

Opinosis Text Summarization Web API

The Opinosis REST API is available to all academic researchers. You can use a command line tool like cURL to access the API or you can also easily access the API from any programming language using HTTP request and response libraries.

Opinosis Textual Opinion Summarization Library (Command Line Jar)

The Opinosis Summarizer Software is a demo version of a summarizer that generates concise abstractive summaries of highly redundant text. It  was primarily used to summarize opinions, and thus it can  be regarded as a opinion summarization software.

Wrapper over Stanford's POS Tagger

This is a Java based wrapper over Stanford's NLP POS Tagger (English only). It reads the contents of the user specified input file (line by line) and prints out the parsed text in the following format: "that/DT has/VBZ never/RB happened/VBN before/RB ./.". More instructions in the readme. Example usage: java -Xmx1G -Xms1G -jar Postag1.0.jar "<PATH TO INPUT FILE>" > parsed_output.txt

rouge2csv - Script to Interpret ROUGE Scores

This is a perl script that helps in interpreting ROUGE scores generated by the perl (original) implementation of ROUGE. If you need Instructions on how to set-up ROUGE for evaluation of your summarization tasks go here.

prepare4rouge - Script to Prepare for Rouge Evaluation

This is a perl script that takes in all your system generated files, then all your gold standard/reference summary files, and prepares it in the format used by the ROUGE evaluation toolkit. In other words, it prepares the following from the input that you provide:

  • models/
  • systems/
  • settings.xml

There are 2 versions of the script, one is output using jackknifing and the other is the usual evaluation without the need for jackknifing.

FindiLike: Opinion-Driven Hotel Search

, Ganesan, Kavita A., and Zhai ChengXiang , Proceedings of the 21st International Conference on World Wide Web 2012 (WWW '12), Demo, (2012)

Traditional web search engines enable users to find documents based on topics. However, in finding entities such as restaurants, hotels and products, traditional search engines fail to suffice as users are often interested in finding entities based on structured attributes such as price and brand and unstructured information such as opinions of other web users. In this paper, we showcase a preference driven search system, that enables users to find entities of interest based on a set of structured preferences as well as unstructured opinion preferences.

FindiLike - Finding Entities by Preferences

FindiLike is a preference driven search engine that enables people to find and analyze entities (currently only hotels) based on personal preferences. These preferences can be a combination of unstructured information such as opinions or structured ones such as price, distance and so on depending on the domain. The opinion preferences can be expressed as a set of natural keywords such as 'close to place xyz', 'safe location', 'good breakfast', etc. FindiLike also provides tools to further analyze the recommended entities.