"A Cocoa Objective-C 2.0 rtf-Text Editor optimized for fast transcription of audio- or video material."

Some interesting linguistic tools towards the middle of this page.

WGBH provides a for-hire captioning service? Do other PBS stations do that?

"AGTK is a suite of software components for building tools for annotating linguistic signals, time-series data which documents any kind of linguistic behavior (e.g. audio, video). The internal data structures are based on annotation graphs."

"Built around LDC's champollion sentence aligner kernel, Champollion Tool Kit (CTK) aims to providing ready-to-use parallel text sentence alignment tools for as many language pairs as possible."

"As the web is becoming ubiquitous, interactive, and multimodal, technology needs to deal increasingly with human factors, including emotions. The present Final Report of the Emotion Markup Language Incubator Group provides elements for an Emotion Markup Language striking a balance between scientific well-foundedness and practical applicability. The language is conceived as a "plug-in" language suitable for use in three different areas: (1) manual annotation of data; (2) automatic recognition of emotion-related states from user behaviour; and (3) generation of emotion-related system behaviour."

"Speex is an Open Source/Free Software patent-free audio compression format designed for speech. The Speex Project aims to lower the barrier of entry for voice applications by providing a free alternative to expensive proprietary speech codecs. Moreover, Speex is well-adapted to Internet applications and provides useful features that are not present in most other codecs. Finally, Speex is part of the GNU Project and is available under the revised BSD license."

"Ken Ingham, Ph.D. will describe the architecture and motivation behind the development of Amazability, Inc.'s Adept1 product. The Adept1 performs natural language analysis and interprets spoken words and phrases or typed input. The Adept1 is equipped with voice recognition and text-to-speech output that dynamically adapts multilingual spoken output to context. The Adept1 offers such applications as word processing, email, address book, web browsing, and access to an online library of thousands of books. The product represents a foundation for implementing practical natural language transaction processing where simple English phrases and sentences are interpreted to command a sequence of complex operations. The Adept1 will be demonstrated and a roadmap for future applications will be given."

"Is the beloved paper dictionary doomed to extinction? In this infectiously exuberant talk, leading lexicographer Erin McKean looks at the many ways today's print dictionary is poised for transformation."

Humane Imperative Parser (HIP), a simple testbed for playing around with linguistic command-line ideas.

Grammar-based Reading Difficulty Prediction

While I don't think this will satisfy the Mark Libermans of the world it is still nice to have. Facebook's corpus is clearly a different demographic than say... all of Google.

Targets Scandinavian languages

"It would stand to reason, therefore, that when something is easier to articulate, it is also easier to think about."

nerds

"Wordie lets you make lists of words. Practical lists, words you love, words you hate, whatever."

A natural language user interface generation development environment for multimodal applications

"Using comparable corpora, corpora where texts in the two languages deal in some of the same topics and therefore share references to named entities but are not translations of each other."

context free grammar parsing

A search engine focusing on linguistic properties. The corpus content is either newspaper texts or randomly collected web pages.

Well there's a text corpus I haven't seen yet...

"Pyparsing provides a framework for creating recursive-descent parsers, taking care of the overhead functions of scanning the input string, handling expression mismatches, selecting the longest of matching alternatives, invoking callback functions..."

A David Foster Wallace article dripping with the usual hubris over language issues. Still a facinating read.

Further detail on why Google can not be used for language research.

Weblog terminology translated across English, Spanish, French, Portuguese, Galician, German.

"Convert Japanese text completely to Hiragana, Katakana or Romanji."

A discussion of problems with using Google for language research.

A little linguistic smack down on a columnist and her latest article that appeared in the New Yorker.

Yay! Looks like tidy little class at that. Get your ling on!

"33,000 words, grouped by meaning. Each word is given the average color of web images found when searching for that term. You can see clusters of words related to plants, flesh, food, and water. Some specific clusters are shown below."

Performance results of systems trainted to perform translation from a given source language into the target language. The source languages were Arabic and Chinese, and the target language was English.

Problems in translating arabic, particularly entity names. Arabic, as a language, is *so* interesting.

beyond helpful

Computers can learn the meaning of words simply by plugging into Google.

"WordCount™ is an artistic experiment in the way we use language. It presents the 86,800 most frequently used English words, ranked in order of commonality."