is a free*, commonsense-enriched, end-to-end natural language understander
for English. Feed raw English text into MontyLingua, and the output
will be a semantic interpretation of that text. Perfect for information
retrieval and extraction, request processing, and question answering.
From English sentences, it extracts subject/verb/object tuples,
extracts adjectives, noun phrases and verb phrases, and extracts
people's names, places, events, dates and times, and other semantic
information. MontyLingua makes traditionally
difficult language processing tasks trivial!
2.0 is substantially FASTER, MORE ACCURATE, and MORE RELIABLE than
version 1.3.1. It has now been tested across Windows, many flavors
of UNIX, and Mac OS X, and several flavors of Java, and is in use
by several university research projects and under several commercial
differs from other natural language processing tools because:
is complete end-to-end.. input raw_text; output semantic
many dated tools and implementations sewn together; it is one
does not require "training" and other fidgetting,
and will work right out-of-the-box
is enriched with "common
sense" knowledge about the everyday world, allowing
it to escape many stupid interpretive mistakes. e.g.:
(c) 2002-2004 by Hugo Liu, MIT Media Lab
All rights reserved.
Non-commercial use is free, as provided in
the MontyLingua version 2.0 License.
By downloading and using MontyLingua, you agree to abide by
the additional copyright and licensing information in "license.txt",
included in this distribution.
If you use this software in your research, please acknowledge
MontyLingua and its author, and link to back to the project
Please cite montylingua in academic publications as:
Liu, Hugo (2004). MontyLingua: An end-to-end natural
processor with common sense. Available
read the following information to proceed to the download of
Version 2.1 for Java and Python.
you have read and agree to the
(your IP address will also be recorded):
is a 12 MB zip file)
THIS if you are running ML on Mac OS X, or Unix
distribution ZIP includes datafiles designed for windows. If
you are running MontyLingua on Unix or Mac OS X, and the phrase
"I love you" is tagged incorrectly, then the datafiles
need to be rebuilt. This is simple:
all files of the form, FASTLEXICON_n.MDF, where n is a number.
the MontyLingua program, either from Python, or Java, and the
correct datafiles will be rebuilt. If running Java and you run
out of memory during the rebuild process, use the -MX or -Xmx
option in Java to increase the memory size. You will only need
to rebuild these datafiles once.
William W. Cohen (2004) Minorthird: Methods for Identifying Names
and Ontological Relations in Text using Heuristics for Inducing
Regularities from Data, http://minorthird.sourceforge.net (website)
Eisenstein and Randall Davis. Visual and Linguistic Information
in Gesture Classification. Accepted to International Conference
on Multimodal Interfaces (ICMI'04) (paper)
Xie, L. Kennedy, S.-F. Chang, A. Divakaran, H. Sun, C.-Y. Lin (2004).
"Discovering Meaningful Multimedia Patterns with Audio-visual
Concepts and Associated Text." IEEE International Conference
on Image Processing (ICIP 2004), Singapore, October 2004. (paper)
Kumar, Sharad C. Sundararajan, Henry Lieberman (2004). Common Sense
Investing: Bridging the Gap Between Expert and Novice. Conference
on Human Factors in Computing Systems (CHI 04), Vienna, Austria.
Hugo Liu and Push Singh (2004) ConceptNet: A Practical Commonsense
Reasoning Toolkit. BT Technology Journal, upcoming. Kluwer
Academic Publishers. (website)