Computational Linguistics/Language Engineering

Organizations

The Association for Computational Linguistics (ACL)
ACL claims to be the largest organization for people concerned with research and development in the area of computational linguistics. ACL has a set of sub groups called Special Interest Groups (SIG) covering e.g., parsing, mathematics of language and generation.

Nordisk Datalingvistisk Nettverk (NoDaLiNe)
NoDaLiNe is mostly for us in scandinavia. The site contains links to local and regional resources in linguistics and computational linguistics.

The Summer Institute of Linguistics
A site managed by The International Linguistics Center in Dallas, Texas. SIL is mainly focused on minority languages and cultures.

European Network in Language and Speech (ELSNET)
The aim of ELSNET is to build resources for multilingual systems dealing with unrestricted text and speech.

Software

The Natural Language Software Registry
This site is a registry for software dealing with a range of aspects within natural language processing. The database is an initiaitve taken by the Association for Computational Linguistics (ACL) and it is maintained by the German Center for Artificial Intelligence GmbH (DFKI).

Linguistic Data Consortium (LDC)
This is an american site maintained by the University of Pennsylvania. LDC is said to be an open consortium consisting of universities, governmental agencies and commercial companies and the aim of which is to collect and distribute corpora (written as well as spoken), lexica and other things of interest to the research community. LDC dates back to 1992.

European Language Resources Association (ELRA)
ELRA is a euroean initiative similar to that of LDC. It was founded in Luxembourg in 1995 and it aims to collect, verify and distribute european language resources.

On-line demos

Morphology, Syntax and Discourse

Indexing and Retrieval: Morphological Analysis
LingSoft, Inc. shows off its capabilities in morphological processing.

Syntax and Terminology
LingSoft, Inc. again, syntax and semantics are the topic in this demo.

DRT-demo, DORIS: Discourse Oriented Representation and Inference System
DORIS serves to illustrate the computational semantic tools of the lecture notes on Representation and Inference for Natural Language, by Patrick Blackburn and Johan Bos (see below).

Functional Dependency Grammar (FDG) parser for English
The dependency parser makes syntactic analyses for English sentences. The analysis contains part-of-speech tags, morpho-syntactic functions and syntactic dependency functions.

Machine Translation

Systranet Translation Online
Send an email in one language and recieve the translation in another. An example of the technique behind this service can be found in AltaVista; BabelFish

Natural Language Interfaces

CIAO Web Chat system
This is a limited domain natural language interface to a database. Developed at the CLIP Lab at Universidad Politecnia de Madrid.

Ask Jeeves
Ask Jeeves is claimed to be: "It's the first natural language search service-with a massive Knowledgebase of 6 million answers to the most popular questions asked online."

Text-to-Speech

Text-to-speech (TTS) Synthesis at Bell Labs
The Bell Labs Text-to-Speech system (TTS) has various applications including reading electronic mail messages, generating spoken prompts in voice response systems, and as an interface to an order-verification system for salespeople in the field.

Emu: An Email Preprocessor for TTS (Bell Labs)
The analysis of an email message by Emu decomposes into the following notionally distinct phases: (i) analysis and parsing of text regions (markup); (ii) `normalization' of text content (device-independent rendering); (iii) synthesis of the text (audio rendering ).

AT&T Labs Research: Text-To-Speech Synthesis
AT&T Labs' Next-Generation TTS converts machine-readable English text into audible speech. They also collaborate on Visual TTS, the synchronization of an animated face with synthesized speech. Visit their main demo page and have a look.

Text Generation

ILEX: The Intelligent Labelling Explorer
Here, textgeneration is used for presenting objects in a museum; where the visitor has been and what he has been looking at is taken into account when a new explanation is generated.

Automatic Text Generation from MicroSoft
MS presents three web-based text generation systems.

Language Identification

XRCE Language Identifier
A program that tries to identifiy the input as being one of the 31 languages coped with. From Xerox.

The Language Guesser Demo
N-Gram-Based text categorization from Groningen. 60 languages.

FAQs

The Language Technology Group Helpdesk - Frequently Asked Questions
This is a FAQ for R&D people who wants to know more about software, tools and other resources for natural language processing.

Natural Language Processing FAQ
Created by Dragomir R. Radev and posted to some news groups in december 1996.

The sci.lang FAQ
Originally created by Michael Covington, now maintained by Mark Rosenfelder. This FAQ is geared towards linguistics rahter than computational linguistics.

Papers, databases and other goodies

Survey of the State of the Art in Human Language Technology
A 590 page book that gives an overview of the technologies currently used in NLP. The book contains 13 chapters which are written by experts in each area. The site is maintained by the Center for Spoken Language Understanding at the Oregon Graduate Institute of Science and Technology.

The Linguist's Guide to Statistics
Written by Christer Samuelsson and Brigitte Krenn. Approximately 170 pages and the latest version is dated december 1997.

Syntactic Theory: A Formal Introduction
A 300 pages introduction to formal syntax by Ivan A. Sag and Thomas Wasow. Dated september 1997.

Natural Language Parsers: A "Course In Cooking"
From this page, one can access the tutorial notes for a workshop on parsing held in conjunction with COLING-ACL'98 in Montreal, Canada, by Peter Hellwig. The booklet is dated september 1998 and is approx. 70 pages.

Representation and Inference for Natural Language - A First Course in Computational Semantics
This page introduces a basic course in computational semantics. At the bottom of the page, there is a link to some tutorial notes on the subject (from COLING-ACL'98) dated july 17, 1998. The booklet is approx. 280 pages and it is written by Patrick Blackburn and Johan Bos.

What is Computational Linguistics?
A short but good text on what computational linguistics is all about. From the University of the Saarland.

Le Journal
An on-line news service concerning language technology in europe.

The Computation and Languge E-Print Archive
This database contains a large number of papers on different aspects of computational linguistics. Apart from the papers, there are also some ten complete proceedings available.

Ovis Electronic Library
A set of papers categorized by subject.

Magazines

Computational Linguistics

Linguistic Inquiry

Natural Language Engineering

Email-lists

The Linguist List
Maintained by the Eastern Michigan University and Wayne State University. The list started out in 1990 as an emailing-list with 60 members and has now grown to be one of the largest resources concerned with (computational) linguistics on the web.

Colibri
Colibri is a weekly newsletter on linguistics, computational linguistics, speech technology and logic, and it is distributed by the Utrecht Institute of Linguistics togehter with Utrecht University.

Nordisk Datalingvistisk Nettverk (NoDaLiNe)
NoDaLiNe has a couple of email-lists; one for announcements and one for discussions on linguistics. Mostly for us living in scandinavia.

Academic sites on (computational) linguistics in Sweden

Uppsala

Stockholm

Göteborg

Linköping

Lund

Umeå

Skövde

Senast uppdaterad av Fredrik Olsson klockan 13:21:22 den 24/11 -99.