Archive of Obsolete Projects that used Link Grammar

Perhaps of historical interest!

The below is an ad-hoc listing of old announcements and listings of obsolete projects and dead website links. All of these made use of Link Grammar in some way, but went stale & obsolete for various reasons. In some cases, the code was merged into the main LG distro. In other cases, it was simply abandoned.

Old Abisource Website

The Link Grammar project used to be hosted by abisource.com, but that website went down without warning in the fall of 2023. For your amusement, here is the last saved version available from the Wayback Machine, dated from the 25th of August 2023. They even captured what the download site looked like, but they did not capture the actual tarballs.

As a reminder, the current website is at https://opencog.github.io/link-grammar-website/, and the source-code tarballs are at https://www.gnucash.org/link-grammar/downloads/.

Stanford Parser Compatibility

A sibling project, RelEx, uses constraint-grammar-like techniques to extract dependency relations that are compatible with the Stanford parser. It's performance is comparable to the Stanford PCFG parsing model, and is more than three times faster than the Stanford "lexicalized" (factored) model.

The RelEx project is no longer in active development. We learned (the hard way) that the native Link Grammar parses contain much more information than the Stanford dependency markup is capable of supporting. The Stanford-style dependencies are simply are not rich or sophisticated enough to produce the kind of data needed for semantic analysis and comprehension, viz. tasks such as predicate-argument extraction, framing, semantic selection, and the like.

Language generation

For sentence generation, i.e. the creation of grammatically correct sentences from a bag of semantic relations, the microplanner and surface realization (sureal) portion of OpenCog is strongly recommended. A short example is here. These "sort-of work", but not very well. The primary issue is that they do not make use of the statistical information available in language to choose likely or reasonable sentence constructions.

We previously recommended two projects that should now be considered obsolete: NLGen and NLGen2. For your entertainment, they're still listed below: The NLGen and NLGen2 projects provide natural language generation modules, based on, and compatible with link-grammar and RelEx. They implement the SegSim ideas for NL generation.

See the following YouTube videos of a virtual dog, showing some of NLGen's capabilities (circa 2009):

Assorted Obsolete projects

RelEx Semantic Relation Extractor
RelEx is an English-language semantic relationship extractor, built on the Link Parser. It can identify subject, object, indirect object and many other relationships between words in a sentence. It will also provide part-of-speech tagging, noun-number tagging, verb tense tagging, gender tagging, and so on. RelEx includes a basic implementation of the Hobbs anaphora (pronoun) resolution algorithm.
On-line Link Grammar & RelEx Demo
You can try the parser online, here.

Gone; Heroku was unmaintainable.

C#.Net Framework bindings
C#.Net interface to Link Grammar from Leonard Chalk/ProAI.

Old, circa 2007, probably bit-rotted. The proai.com domain has been abandoned in 2010. Archive copy here

Ruby bindings
Ruby bindings are coordinated at the Ruby-LinkParser website. The code can be found at the ged/link-parser github page.

Obsolete, no longer available.

Perl bindings
Perl bindings, created by Danny Brian, can be found on the Lingua-LinkParser page on CPAN. Caution: those bindings appear to be unmaintained; currently, they include features that were removed more than than five years ago. (We encourage a new maintainer to step up!) There is also a tutorial written against a very old version of the bindings; some details may be different.

Psi Toolkit (Perl)
The Psi Toolkit, an NLP toolkit aimed at linguists and NLP engineers, includes bindings for link-grammar, via perl.

Website no longer exists.

Delphi bindings
Delphi (Pascal) is a popular development environment for Windows. The LaKraven Page provides the source for Delphi bindings, as well as pre-compiled DLL's for Windows.

The lakraven website went off-line sometime in 2012 or 2013 ...

Alternative Java bindings
Another, completely different set of Java bindings have been developed: a tar ball is here. These are for the old version 4.1 only. Note that these are not compatible with the bindings that ship, by default, with the main link-grammar package.

Out of date since 2006 ...

Javascript
Obsolete Javascript bindings can be found at the dijs/link-grammar github page. Someone, please port these to the latest version!

Merged into mainline Link Grammar. Now part of version 5.8.0

Pre-parsed Wikipedia
Parsed versions of various texts, including all articles from a May 2008 dump of Wikipedia, as well as a partial parse of an October 2010 dump, are available at https://gnucash.org/linas/nlp/data/

Deprecated.

English dictionary extensions
LinkGrammar-WN is a lexicon expansion for the English language Link Grammar Parser. This project adds 14K new words to the dictionaries. The extended lexicon is provided under the GPL license, and thus cannot be merged back into the current project. NOTE: these extensions are rather old, and it is likely that they are no longer compatible with current link-grammar versions.

Deprecated

Medical Text Analysis
The MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) Clinical Decision Making Group has done work to extend the Link Grammar dictionaries by adding many new words. All but the six largest of these dictionaries have been merged into link-grammar, since version 4.3.1 (January 2008). The large dictionaries EXTRA.2, EXTRA.3, EXTRA.8, EXTRA.9, EXTRA.12, and EXTRA.17 have not been merged. These dictionaries contain 180K assorted medical, biological and biochemical terms and phrases.

Olde news. Merged into mainline in version 4.5

BioLG
The BioLG project is a modification of the Link Grammar Parser adapted for the biomedical domain, as described in Lexical Adaptation of Link Grammar to the Biomedical Sublanguage: a Comparative Evaluation of Three Approaches (Sampo Pyysalo, Tapio Salakoski, Sophie Aubin and Adeline Nazarenko; BMC Bioinformatics 2006). Almost all of the BioLG changes have been merged back into the main line, as of version 4.5.0 (April 2009), with scattered bug-fixes after that.

More Dead Software Resources

Return to the Link Grammar front page