AI in Information Retrieval and Language Processing

• AI in Information Retrieval and NLP
  Agents, avatars, bots | Commercial NLP | General Resources | IR Conferences | Journals, books, publishers | Labs and a few individual researchers | Machine translation | Medical systems | Most ambitious IR projects | Question/Answer | Search Engines | Software | Special topics | NLP tools | Word games | Visualization of text info |

• Separate pages
  AI and Machine Learning | AI in Information Retrieval | Cognitive science | Computational Intelligence | Neuroscience | Software & Databases | Science & Fringes |

For general list of AI resources see AI-ML page.

• Special Interest Group on Information Retrieval, resources, conferences, mailing lists ...
• SearchTools.com: Information Retrieval Research
• Web IR and IE, great site | Resources | Mailing Lists | Newsgroups | Related sites |
• Christopher Manning links, Stanford. Statistical natural language processing and corpus-based computational linguistics: An annotated list of resources.
• IR links (Kraft)
• IRSG.eu.org
• IBM NLP |
• Microsoft IR | Microsoft NLP |
• Introduction to Information Extraction Technology (D. Appelt)
• Document Indexing Tutorial for Information Retrieval Students and Search Engine Marketers
• RISE: Repository of Online Information Sources Used in Information Extraction Tasks
• The Natural Language Processing Dictionary
• Consortium for Lexical Research (frozen)
• Digital Libraries: NSF, second phase
• Linguistic Data Consortium
• Machine Learning and Information Retrieval - Belew, Shavlik
• TextMining.org, news and resources |

Introductory texts, talks and courses:

• Text Data Mining, by Marti A. Hearst
• Text to Data using ML, course by william Cohen, CM.

• AI, CogSci and Robotics: List of Conference Lists, Organisers and Past Papers
• TREC (Text REtrieval Conference), NIST "the conference helps translate theory into practice, and provides an objective testbed".
• Web IR and IE Conference List | Online proceedings |
• Machine Learning & Information Extraction Workshops.
• NAFIPS, North American Fuzzy Information Processing Society.
• PAKDD 2006, 10th Pacific-Asia Conference on Knowledge Discovery and Data Mining.

Competitions

• Turing test page.
• Loebner Prize competition.
• Unsupervised segmentation of words into morphemes competition.

Journals

• AI, CogSci & Robotics journal list
• Kluver AI and NN journals (AI, AI Review, Machine Learning, Data Mining and Knowledge Discovery, J. of Intelligent Information Systems, Neural Processing Lett, Minds & Machines etc)
• IEEE Intelligent Systems Intelligence Technologies Journal |
• Knowledge and Information Systems | Expert Systems With Applications (Pergamon) |
• Unstructured Information Managemenet, IBM Systems Journal

Books:

• IR+IE book list
• Applied Intelligence (Kluver), text mining issue
• From Molecule to Metaphor: A Neural Theory of Language
• Information retrieval book by C. J. van Rijsbergen
• Information retrieval - book
• Modern Information Retrieval, book by Ricardo Baeza-Yates, Berthier Ribeiro-Neto
• Knowledge Representation book - John Sowa | KR ontology using formal concept analysis on a lattice |
• Foundations of Statistical Natural Language Processing - Chris Manning and Hinrich Schütze

Papers:

• Proceedings of many ACL workshops and conferences!
• IR+IE online conference proceedings list
• IR+IE PhD/MSc related work list
• Web IR+IE selected publications |
• Text Mining, J. Chen PhD thesis

• IR+IE people list | IR+IE working groups list |
• Center for Intelligent Information Retrieval, CIIR
• Cognitive Machines, situated cognition, Deb Roy MIT Lab
• N. Ide (Vassar), semantic web, NLP.
• Y. Wilks (Sheffield), dialogue systems, pragmatics, lexicons.
• S. Johnson (Columbia), NLP in biomedical domains.
• Human Language Technology Research Inst, Dallas Uni, S. Harabagiu
• Microsoft NLP | MindNet Project | Conversation: Quartet and Deep Listner |
• UAMIS AI Group , Hsinchun Chen, many interesting projects
• Mark Light, IR papers, question answering, biosciences
• Friedman Nir, Bayesian belief networks, learning
• Scott Weiss, Johns Hopkins University, with IR glossary
• Sheffield NLP - many projects

• Latent Semantic Analysis (Boulder)
• Latent Semantic Indexing (Tennesee)
• WebMining PL - SPSS

Wordnet-releated projects

• Use Wordnet | Wordnet, "an online lexical reference system whose design is inspired by current psycholinguistic theories of human lexical memory. English nouns, verbs, adjectives and adverbs are organized into synonym sets, each representing one underlying lexical concept".
• The Global WordNet Association, a platform for discussing, sharing and connecting wordnets for all languages in the world.
• Euro WordNet, building a multilingual database with wordnets for several European languages.
• Senseval, evaluate Word-Sense-Disambiguation systems with wordnet or wordnet-like resources.
• EUROTERM, extends the EuroWordNet database with specialized terminology
• BALKANET, EuroWordNet for more European languages: Czech, Romanian, Greek, Turkish, Bulgarian, and Serbian.
• MEANING, EuroWordNet with sense-tagged corpora extracted from the WWW and word-sense-disambiguation modules
• Perl access to WordNet

Other very ambitious projects:

• Hamburg Metaphor Database, a project where metaphoric relations in wordnet are explored and encoded: Hamburg Metaphor Database or Hamburger Metapherndatenbank.
• Ai (Israel), Hal, child machine MegaHAL project, started by Jason Hutchens - grow baby brain by talking to it! Current state - 18 month old, makes 2-3 word sentences in proper context, but will it ever grow?
• CANIS, Interspace, Medspace projects - solving the problem of deep semantics
• ConceptNet, commonsense knowledgebase and natural-language-processing toolkit, from the Open Mind initiative. Software Agents MIT Group using ConceptNet | Common Sense questions to collect info.
• CYC project, Cycorp, Inc has NLP components + common sense ontology
• EcoCyc/MetaCyc project, P. Karp, Stanford, is used to build biological cell models from text information
• FASTUS, Finite State Automa-based Text Understanding System (Appelt)
• FrameNet, on-line lexical resource for English, based on frame semantics.
• HAL - High Dimensional Semantic Space | Curt Burgess homepage
• High Dimensional Semantic Spaces
• High Performance Knowledge Bases (HPKB), and other projects of DARPA
• HowNet, English and Chinese
• Multicentric Technology, computer-aided thinking
• Shruti, reflexive reasoning network

• Ontolingua and Chimaera Projects, Stanford.
• Standard Upper Ontology Working Group (SUO WG), formal first order logic ontology linked to WordNet |
• Semantic Web |
• The Suggested Upper Merged Ontology portal | Sigma project on SourceForge, tools for SUMO | KSMSA ontology browser (SUMO, Wordnet) |
• Open Biomedical Ontologies for bioinformatics

More interesting projects:

• ACE - Automatic Content Extraction, NIST
• ADIOS - Automatic DIstillation of Structure - Solan, Horn, Ruppin and Edelman
• CS AKTive Space explorer for investigating CS research in UK.
• GATE, architecture, framework, development environment.
• Knowledge Web EU Project
• Latent Semantic Analysis FAQ
• MUSE - a MUlti-Source Entity finder
• Word associations learned from answers
• Semantic Web Challenge
• Semantic Organizer

Agenci: Learning Intelligent Book Recommending Agent | Prody Parrot, personal assistant from MindMaker | Talking Buddy, agent do wszystkiego |
SciAgent for Multidisciplinary Problem Solving Environments | Survey of Cognitive and Agent Architectures |

Virtual humans & avatars
Virtual Friends demos (Haptek) | Virtual Bush (Haptek) |
Pulse 3D Veepers, Virtual Personality
Sitepal flash characters | Speak2me flash |
Oddcast animated characters | AI oddcast | Sports trivia game | Vhost flash characters | Ms Dewey animated character |
CogWorks Virtual People news | Digital Space Worlds | Active worlds | John Lennon | Virtual worlds company | Talking heads in java | Center for Human Modeling and Simulation | Steven Stahlberg gallery | Virtual Humans, Peter Plantec |
Artificial-life , mobile phone bots | Artificial-life Bot-me | their e-learning portal |

Bots (chatterbots):
Chatterbot challenge | BotSpot (lista botow) | InteractiveStory good links | Agentland | 123-Bots | Simon Laven bots, many! |
Conversive Application Platform, Agents and dialog system | DELCA Ghosts, specialized | e-brain jako sprzedawca | Simon w e-brain| Chatterbot challenge| Arthur, with source code|
Talk to Alice | Botizen | Jabberwacky | Jabberwock | Chat-bot | Nicole | Ramona | SmarterChild | Start (MIT) | Ultrahall Assistant | Kiwi Logic Lingubots! |
Polish bots (Polske boty): Fido Lingubot (Kiwilogic) | Denise MYTH | Cathy (Michal Zalewski) |
Beyond bots: Amities, Automated Multilingual Interaction with Information and Services | FASiL, Flexible and Adaptive Spoken Language and Multi-modal Interface for Virtual Personal Assistant (VPA) |
Marek Kasperski: Aibotworld | Sztuczna inteligencja | Kognitywistyka.net |

Bayesian Networks:
Air Force BayesNet | Int. Soc. for Bayesian Analysis | ASA Section on Bayesian Statistical Sciences | Bayesian networks meta-resource | Bayesian belief networks

Computational biology and bioinformatics applications:
Martin Tompa, Washington (sequences) |
HMM for Proteins | HMM tutorials | Genes and disease (molecular biology book chapter) |

Emotions from text:
Emotus Ponens, MIT Lab textual affect sensing, based on Concept Net.

IR Web interfaces:
Web Intelligence Consortium (WIC) | European Network for Intelligent Information Interfaces | European Network of Excellence in Text Mining, NEMIS |
UAMIS AI Group , Hsinchun Chen - OOHAY web visualization

IR systems demonstrations:
ISYS search software |
Acrophile, acronym database.
Eliyon, business employes, automatic content generation.
Flipdog, job search.

Knowledge Modeling, Ontology:
Ontology intro (Wikipedia) | Ontology | TOP Ontology Page | KQML or the Knowledge Query and Manipulation Language
Minimum Message Length Encoding
CMU Web => KB project |
WebKB knowledge base servers |
NeuroOK document classification, annotation and search, multilinguial.
Andrew McCallum group, "to mine actionable knowledge from unstructured text", includes Bow, Rainbow and Mallet text classification systems.
Topic Maps: Wikipedia topic maps entry | Topic maps wiki page | XML Topic maps | K42 Topic maps |
Concept Maps, based on constructivist's learning ideas: Wikipedia concept map entry | Conceptual structures | Conceptual graphs | Concept mapping | IHMC Concept mapping tools | Wiki concept mapping page | Wiki software | Online Course in Knowledge Representation using Conceptual Graphs |
Other Knowledge Maps: Conceptual graphs (Wikipedia) | Conceptual schemas | Knowledge maps (Wikipedia) | Knowledge visualization (Wikipedia) | Mind mapping (Wikipedia) | Semantic networks (Wikipedia) | Semantic web (Wikipedia) |
Leximancer, automatic analysis of document collections, taxonomy discovery.

Knowledge management: Knowledge Computing Corporation, Coplink system |
CCI, Conversational Computing Inc, legal systems, dialog, NLP news/info
ERNEST is a knowledge representation language, based on semantic networks

Lexicons
One Look (870 dictionaries) | 400 On-line Dictionaries | Word reference |
Wortschatz Lexicon, Uni. Lepizig.
Visual Thesaurus
Webster's Unabridged 1913 | WWWebster Thesaurus | Roget's Thesaurus | Roget's Thesaurus - from Project Gutenberg | The Wordsmyth English Dictionary-Thesaurus | Synonym/antonym Dictionary of English |
Eurodicautom (transl. in 8 languages) |
Onet dictionaries | Free dictionary

Medical and biomedical systems:
Semantic Knowledge Representation (SKR), NIH | SKR Bibliography |
Unified Medical Language System | UMLS alternative list,
UMLS biography 1986-96 | UMLS 1990-2002 list

MetaMap Transfer (MMTx)
Indexing Initiative Systems
Word Sense Disambiguation (WSD)
Lexical system group, National Library of Medicine
Semantic network, National Library of Medicine

Medstract, Medline abstract, Brandeis University
Medical resources on the web, 2005 update
Medical Reference For Non-Medical Librarians

Medical language processor for automatic text processing and presentation, Sourceforge project.
Health Level 7" XML standard
Health Cyber Map
Language and Computing medical systems

Medical acronyms, over 200K, with 800K definitions!
Morphosaurus, mapping to standardized medical dictionary in any langauge.
Semantic Mining, biomedical, EU network.

Question answering systems:
AnswerBus
ASU Q/A Demo
BrainBoost NLP search
JAVELIN II, CMU project,
Language Computer, LCC, top 2004 Q/A system
MIT Start project
NSIR QA system
WebQA: A Fast and Simple QA System
Wondir sending questions to people!

My[Q]Box, providing question answering software for Web pages.
HOMEY, Intelligent Dialog System for telemedicine

Spoken Dialogue Technology : Resources.

NLP Tools: Taggers, Parsers, NER, NP chunking, Language models ...
NLP Stanford tools links |
Probabilistic parsing links |
Link Grammar | Link Grammar Parser |
Memory-based tagger |
Multilingual Statistical Parsing Engine, Dan Bikel |
NLP Software Registry (at DFKI) |
MinorThird, Java for text annotation, extraction, categorization (William W. Cohen) |
VisualText, general development enviroment for NLP |

Word games:
20q net - 20 questions game | 20 questions game | 20 questions about animals | Darth Vader reads your mind |
Edict word games |
Creative Language System Group (UC Dublin), word games |

Interesting Search Systems:
Links to various search engines and catalogs
Carrot2 (Dawid Weiss, Poznan)

UIMA, Unstructured Information Management Architecture (IBM), open platform for building unstructured information and knowledge management applications (released 8/2005).
IBM Public Image Monitoring Solution - what do they say about you, your product or your company?

Varia:
DFAs: Languages and Learning
IR in Chemistry
IR in Chemistry
Edict Word Frequency Text Profiler, Unique Words Text Profiler and concordancer.

Visualization of texts and documents:
Tools for visualization from CAIDA.org | Visual Browsing in Web and non-Web Databases | Citespace - visualizes evolution of a network | Chaomei Chen info visualization
Infomap - info mapping project (Stanford)
Inxight - drzewo hiperboliczne, hiperbolic tree (commercial)
NeurOK semantic explorer
Touchgraph, link trees via Web interfaces (free), including Interent links java applet
Thinkmap, taxonomy browsers
WEBSOM - free-text mining | WebSOM, PhD Timo Honkela |
VizieR astro catalog | astro A&A papers map | Astroph.J papers map | SOM digital library project |
Internet topology visualizations | The Internet Mapping Project (Lumeta) | Nonlinear Magnification InfoCenter |

Course on info visualization, Fall 2005-2006, Tamara Munzner, UBC; includes software and data links.

Machine translation& NLP:
28 systems and 38 languages: Foreignword.com | EAMT (European Association for MT) | Center for Machine Translation (CMU) |
Microsoft MT projects |
WOCADI, based on Multinet, Hartrumpf, Hagen |
MT intro, book by Doug Arnold |
Language Force | Global English (translations, lessons) | Translation Experts (25 languages ) |
Machine Translation (Kluver Journal) | Subjex dialog systems | Systran translation software | MT Introductory Guide (book!)
START natural language system (SynTactic Analysis using Reversible Transformations)

Try it here! Lernout and Haspie | Alta Vista Babel fish | Free Translation | InterTran (PL + inne) | Systran | T-mail (europ + ros, jap, kor, chin ...) | WorldLingo's free online translator |

PL/EN: Translantica.pl (PWN) | Translate.pl |

Other topics: APA Style Converter.

Commercial NLP:
TEMIS, text mining, extration, semantic solutions |

Last modification 18.1.2007,
Wlodzislaw Duch