Research

Touché [2020 - today]
Research Network on Computational Argumentation
[data] [events] [publications]

PAN [2007 - today]
Research Network on Digital Text Forensics
[data] [events] [publications]

Other Shared Tasks on Societal Challenges
[data] [events] [publications]

Information Retrieval Anthology [2021 - today]
Collecting papers on the study of information retrieval.
[publications] [service]

Conversational Search [2018 - today]
Research on information-seeking conversations with machines.
[demo: lecturenotes infobot, user simulation] [events] [publications]

Args [2017 - today]
The first search engine for arguments on the web.
[api] [demo: image search] [publications] [service]

Information Nutrition Label [2017 - today]
Providing information nutrition labels for documents.
[publications]

ChatNoir [2010 - today]
Research search engine with ranking explanation indexing the ClueWeb and CommonCrawl.
[api] [publications] [service]

Netspeak [2006 - today]
Technology for text correction and idiomatic writing.
[api] [publications] [service] [video]

Picapica [2005 - today]
Technology for automated plagiarism detection.
[demo: essay viewer, scientific reuse, wikipedia reuse] [publications] [service] [video]

Retrieval Models [2011 - 2014]
Interactive map to overview and compare the characteristics of well-known retrieval models.
[demo: model map] [publications]

Query Analytics [2010 - 2022]
Second-guess the user’s intent from a search query.
[api] [data] [demo: query segmentation] [publications]

Wikipedia Fingerprinting [2007]
Search engine implementing full text queries against Wikipedia based on fingerprinting.
[publications]

AIsearch [2003 - 2006]
Meta search engine for Web document categorization and graphical access.
[awards] [publications] [video]

Discourse Generation [2023 - today]
Generation of discourse with human-in-the-loop.
[demo: lecturenotes infobot, story writing, turing game, user simulation] [publications]

Trigger Warning [2022 - today]
Technology to warn people about potentially disturbing content.
[data] [events] [publications]

Human Values [2022 - today]
Analysis of human values in discourse.
[data] [demo: argument analysis, article analysis] [events] [publications]

Computational Causality [2020 - today]
Extraction, retrieval and utilization of causal claims.
[data] [publications]

Science Studies [2019 - today]
Analysis of scientific documents and actors.

Text Summarization [2018 - today]
Generating and evaluating summaries for diverse document types.
[demo: progress, summary explorer, summary workbench] [publications]

Clickbait [2016 - today]
Analysis of clickbait messages in social media.
[events] [publications]

Computational Argumentation [2012 - today]
Argumentation analysis in discourse.
[api: argument search, argument tagging, object comparison] [demo: argument tagging, essay scoring, image search, object comparison, review analysis] [events] [publications] [service]

Social Media Analytics [2008 - today]
On the fly comment summarization for YouTube and Flickr.
[publications]

Authorship Analytics [2007 - today]
Analysis and comparison of authorial style in written documents.
[demo: unmasking] [events] [publications]

Business Analytics [2009 - 2011]
Information extraction for business applications.
[demo: sentiment analysis] [publications]

Person Resolution [2007 - 2008]
Resolution of named entities in Web pages.
[awards] [publications]

Web Archive [2018 - today]
Analysis of the Web using an 8 PB dataset of the Internet Archive's Web archive.
[awards] [illustration] [publications]

Digital Engineering [1994 - today]
Tackling engineering problems with AI technology.
[awards: ArtDeco, FluidSIM1, FluidSIM2] [publications]

Wikipedia Vandalism [2007 - 2019]
Analysis and detection of vandalism on Wikipedia.
[demo: spatio-temporal analysis] [publications]

Wikipedia Quality [2010 - 2016]
Analysis and prediction of quality flaws in Wikipedia.
[publications]

Cluster Analysis [2002 - today]
Semantic cluster analysis in information retrieval.
[data] [publications]

Web Genre [2006 - 2008]
On the fly genre analysis for Web pages.
[publications] [video]

TIRA [2007 - today]
Online experiment configuration and execution.
[publications] [service] [video]

WAT-SL [2017 - 2020]
Web Annotation Tool for Segment Labeling.
[code] [demo: annotation tool] [publications]

AItools [2003 - 2020]
Java library for information retrieval and data mining.