diff options
| author | aarne <aarne@cs.chalmers.se> | 2009-03-11 16:54:16 +0000 |
|---|---|---|
| committer | aarne <aarne@cs.chalmers.se> | 2009-03-11 16:54:16 +0000 |
| commit | a175874e2c144a55ea88bf6e351e7b6b9ea4ab07 (patch) | |
| tree | 7857e78be106651e70813022b2297e95a3a625a2 | |
| parent | af1fc9306a98a70bc405755f458ba2986f426685 (diff) | |
idea page
| -rw-r--r-- | doc/gf-ideas.html | 284 | ||||
| -rw-r--r-- | doc/gf-ideas.txt | 216 | ||||
| -rw-r--r-- | examples/bronzeage/SwadeshEng.gf | 3 | ||||
| -rw-r--r-- | examples/bronzeage/SwadeshI.gf | 1 | ||||
| -rw-r--r-- | next-lib/src/Make.hs | 4 | ||||
| -rw-r--r-- | src/server/lighttpd.conf | 2 |
6 files changed, 508 insertions, 2 deletions
diff --git a/doc/gf-ideas.html b/doc/gf-ideas.html new file mode 100644 index 000000000..a032061e1 --- /dev/null +++ b/doc/gf-ideas.html @@ -0,0 +1,284 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"> +<HTML> +<HEAD> +<META NAME="generator" CONTENT="http://txt2tags.sf.net"> +<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"> +<TITLE>GF Project Ideas</TITLE> +</HEAD><BODY BGCOLOR="white" TEXT="black"> +<P ALIGN="center"><CENTER><H1>GF Project Ideas</H1> +<FONT SIZE="4"> +<I>Resource Grammars, Web Applications, etc</I><BR> +contact: Aarne Ranta (aarne at chalmers dot se) +</FONT></CENTER> + +<P></P> +<HR NOSHADE SIZE=1> +<P></P> + <UL> + <LI><A HREF="#toc1">Resource Grammar Implementations</A> + <UL> + <LI><A HREF="#toc2">Tasks</A> + <LI><A HREF="#toc3">Who is qualified</A> + <LI><A HREF="#toc4">The Summer School</A> + </UL> + <LI><A HREF="#toc5">Other project ideas</A> + <UL> + <LI><A HREF="#toc6">GF interpreter in Java</A> + <LI><A HREF="#toc7">GF interpreter in C#</A> + <LI><A HREF="#toc8">GF localization library</A> + <LI><A HREF="#toc9">Multilingual grammar applications for mobile phones</A> + <LI><A HREF="#toc10">Multilingual grammar applications for the web</A> + <LI><A HREF="#toc11">GMail gadget for GF</A> + </UL> + <LI><A HREF="#toc12">Dissemination and intellectual property</A> + </UL> + +<P></P> +<HR NOSHADE SIZE=1> +<P></P> +<P> +<center> +<IMG ALIGN="middle" SRC="gf-logo.png" BORDER="0" ALT=""> +</center> +</P> +<A NAME="toc1"></A> +<H2>Resource Grammar Implementations</H2> +<P> +GF Resource Grammar Library is an open-source computational grammar resource +that currently covers 12 languages. +The Library is a collaborative effort to which programmers from many countries +have contributed. The next goal is to extend the library +to all of the 23 official EU languages. Also other languages +are welcome all the time. The following diagram show the current status of the +library. Each of the red and yellow ones are a potential project. +</P> +<P> +<center> +<IMG ALIGN="middle" SRC="school-langs.png" BORDER="0" ALT=""> +</center> +</P> +<P> +<I>red=wanted, green=exists, orange=in-progress, solid=official-eu, dotted=non-eu</I> +</P> +<P> +The linguistic coverage of the library includes the inflectional morphology +and basic syntax of each language. It can be used in GF applications +and also ported to other formats. It can also be used for building other +linguistic resources, such as morphological lexica and parsers. +The library is licensed under LGPL. +</P> +<A NAME="toc2"></A> +<H3>Tasks</H3> +<P> +Writing a grammar for a language is usually easier if other languages +from the same family already have grammars. The colours have the same +meaning as in the diagram above. Thus, in particular, each of the languages +coloured red below are possible programming projects. +</P> +<P> +Baltic: +</P> +<UL> +<LI><font color="red"> Latvian </font> +<LI><font color="red"> Lithuanian </font> +</UL> + +<P> +Celtic: +</P> +<UL> +<LI><font color="red"> Irish </font> +</UL> + +<P> +Fenno-Ugric: +</P> +<UL> +<LI><font color="red"> Estonian </font> +<LI><font color="green" size="-1"> Finnish </font> +<LI><font color="red"> Hungarian </font> +</UL> + +<P> +Germanic: +</P> +<UL> +<LI><font color="green" size="-1"> Danish </font> +<LI><font color="red"> Dutch </font> +<LI><font color="green" size="-1"> English </font> +<LI><font color="green" size="-1"> German </font> +<LI><font color="green" size="-1"> Norwegian </font> +<LI><font color="green" size="-1"> Swedish </font> +</UL> + +<P> +Hellenic: +</P> +<UL> +<LI><font color="red"> Greek </font> +</UL> + +<P> +Romance: +</P> +<UL> +<LI><font color="green" size="-1"> Catalan </font> +<LI><font color="green" size="-1"> French </font> +<LI><font color="green" size="-1"> Italian </font> +<LI><font color="red"> Portuguese </font> +<LI><font color="orange"> Romanian </font> +<LI><font color="green" size="-1"> Spanish </font> +</UL> + +<P> +Semitic: +</P> +<UL> +<LI><font color="orange"> Arabic </font> +<LI><font color="red"> Maltese </font> +</UL> + +<P> +Slavonic: +</P> +<UL> +<LI><font color="green" size="-1"> Bulgarian </font> +<LI><font color="red"> Czech </font> +<LI><font color="orange"> Polish </font> +<LI><font color="green" size="-1"> Russian </font> +<LI><font color="red"> Slovak </font> +<LI><font color="red"> Slovenian </font> +</UL> + +<A NAME="toc3"></A> +<H3>Who is qualified</H3> +<P> +Writing a resource grammar implementation requires good general programming +skills, and a good explicit knowledge of the grammar of the target language. +A typical participant could be +</P> +<UL> +<LI>native or fluent speaker of the target language +<LI>interested in languages on the theoretical level, and preferably familiar + with many languages (to be able to think about them on an abstract level) +<LI>familiar with functional programming languages such as ML or Haskell + (GF itself is a language similar to these) +<LI>on Master's or PhD level in linguistics, computer science, or mathematics +</UL> + +<P> +But it is the quality of the assignment that is assessed, not any formal +requirements. The "typical participant" was described to give an idea of +who is likely to succeed in this. +</P> +<A NAME="toc4"></A> +<H3>The Summer School</H3> +<P> +A Summer School on resource grammars and applications will +be organized at the campus of Chalmers University of Technology in Gothenburg, +Sweden, on 17-28 August 2009. It can be seen as a natural checkpoint in +a resource grammar project; the participants are assumed to learn GF before +the Summer School, but how far they have come in their projects may vary. +</P> +<P> +More information on the Summer School web page: +</P> +<P> +<A HREF="http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/doc/gf-summerschool.html"><CODE>http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/doc/gf-summerschool.html</CODE></A> +</P> +<A NAME="toc5"></A> +<H2>Other project ideas</H2> +<A NAME="toc6"></A> +<H3>GF interpreter in Java</H3> +<P> +The idea is to write a run-time system for GF grammars in Java. This enables +the use of <B>embedded grammars</B> in Java applications. This project is +a fresh-up of <A HREF="http://www.cs.chalmers.se/~bringert/gf/gf-java.html">earlier work</A>, +now using the new run-time format PGF and addressing a new parsing algorithm. +</P> +<P> +Requirements: Java, Haskell, basics of compilers and parsing algorithms. +</P> +<A NAME="toc7"></A> +<H3>GF interpreter in C#</H3> +<P> +The idea is to write a run-time system for GF grammars in C#. This enables +the use of <B>embedded grammars</B> in C# applications. This project is +similar to <A HREF="http://www.cs.chalmers.se/~bringert/gf/gf-java.html">earlier work</A> +on Java, now addressing C# and using the new run-time format PGF. +</P> +<P> +Requirements: C#, Haskell, basics of compilers and parsing algorithms. +</P> +<A NAME="toc8"></A> +<H3>GF localization library</H3> +<P> +This is an idea for a software localization library using GF grammars. +The library should replace strings by grammar rules, which can be conceived +as very smart templates always guaranteeing grammatically correct output. +The library should be based on the +<A HREF="http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/lib/resource/doc/synopsis.html">GF Resource Grammar Library</A>, providing infrastructure +currently for 12 languages. +</P> +<P> +Requirements: GF, some natural languages, some localization platform +</P> +<A NAME="toc9"></A> +<H3>Multilingual grammar applications for mobile phones</H3> +<P> +GF grammars can be compiled into programs that can be run on different +platforms, such as web browsers and mobile phones. An example is a +<A HREF="http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/demos/index-numbers.html">numeral translator</A> running on both these platforms. +</P> +<P> +The proposed project is rather open: find some cool applications of +the technology that are useful or entertaining for mobile phone users. A +part of the project is to investigate implementation issues such as making +the best use of the phone's resources. Possible applications have +something to do with translation; one suggestion is an sms editor/translator. +</P> +<P> +Requirements: GF, JavaScript, some phone application development tools +</P> +<A NAME="toc10"></A> +<H3>Multilingual grammar applications for the web</H3> +<P> +This project is rather open: find some cool applications of +the technology that are useful or entertaining on the web. Examples include +</P> +<UL> +<LI>translators: see <A HREF="http://tournesol.cs.chalmers.se:41296/translate">demo</A> +<LI>multilingual wikis: see <A HREF="http://csmisc14.cs.chalmers.se/~meza/restWiki/wiki.cgi">demo</A> +<LI>fridge magnets: see <A HREF="http://tournesol.cs.chalmers.se:41296/fridge">demo</A> +</UL> + +<P> +Requirements: GF, JavaScript or Java and Google Web Toolkit, CGI +</P> +<A NAME="toc11"></A> +<H3>GMail gadget for GF</H3> +<P> +It is possible to add custom gadgets to GMail. If you are going to write +e-mail in a foreign language then you probably will need help from +dictonary or you may want to check something in the grammar. GF provides +all resources that you may need but you have to think about how to +design gadget that fits well in the GMail environment and what +functionality from GF you want to expose. +</P> +<P> +Requirements: GF, Google Web Toolkit +</P> +<A NAME="toc12"></A> +<H2>Dissemination and intellectual property</H2> +<P> +All code suggested here will be released under the LGPL just like +the current resource grammars and run-time GF libraries, +with the copyright held by respective authors. +</P> +<P> +As a rule, the code will be distributed via the GF web site. +</P> + +<!-- html code generated by txt2tags 2.4 (http://txt2tags.sf.net) --> +<!-- cmdline: txt2tags -thtml -\-toc gf-ideas.txt --> +</BODY></HTML> diff --git a/doc/gf-ideas.txt b/doc/gf-ideas.txt new file mode 100644 index 000000000..cf66a589e --- /dev/null +++ b/doc/gf-ideas.txt @@ -0,0 +1,216 @@ +GF Project Ideas +Resource Grammars, Web Applications, etc +contact: Aarne Ranta (aarne at chalmers dot se) + +%!Encoding : iso-8859-1 + +%!target:html +%!postproc(html): #BECE <center> +%!postproc(html): #ENCE </center> +%!postproc(html): #GRAY <font color="green" size="-1"> +%!postproc(html): #EGRAY </font> +%!postproc(html): #RED <font color="red"> +%!postproc(html): #YELLOW <font color="orange"> +%!postproc(html): #ERED </font> + +#BECE +[gf-logo.png] +#ENCE + + +==Resource Grammar Implementations== + +GF Resource Grammar Library is an open-source computational grammar resource +that currently covers 12 languages. +The Library is a collaborative effort to which programmers from many countries +have contributed. The next goal is to extend the library +to all of the 23 official EU languages. Also other languages +are welcome all the time. The following diagram show the current status of the +library. Each of the red and yellow ones are a potential project. + +#BECE +[school-langs.png] +#ENCE + + +//red=wanted, green=exists, orange=in-progress, solid=official-eu, dotted=non-eu// + +The linguistic coverage of the library includes the inflectional morphology +and basic syntax of each language. It can be used in GF applications +and also ported to other formats. It can also be used for building other +linguistic resources, such as morphological lexica and parsers. +The library is licensed under LGPL. + + +===Tasks=== + +Writing a grammar for a language is usually easier if other languages +from the same family already have grammars. The colours have the same +meaning as in the diagram above. Thus, in particular, each of the languages +coloured red below are possible programming projects. + +Baltic: +- #RED Latvian #ERED +- #RED Lithuanian #ERED + + +Celtic: +- #RED Irish #ERED + + +Fenno-Ugric: +- #RED Estonian #ERED +- #GRAY Finnish #EGRAY +- #RED Hungarian #ERED + + +Germanic: +- #GRAY Danish #EGRAY +- #RED Dutch #ERED +- #GRAY English #EGRAY +- #GRAY German #EGRAY +- #GRAY Norwegian #EGRAY +- #GRAY Swedish #EGRAY + + +Hellenic: +- #RED Greek #ERED + + +Romance: +- #GRAY Catalan #EGRAY +- #GRAY French #EGRAY +- #GRAY Italian #EGRAY +- #RED Portuguese #ERED +- #YELLOW Romanian #ERED +- #GRAY Spanish #EGRAY + + +Semitic: +- #YELLOW Arabic #ERED +- #RED Maltese #ERED + + +Slavonic: +- #GRAY Bulgarian #EGRAY +- #RED Czech #ERED +- #YELLOW Polish #ERED +- #GRAY Russian #EGRAY +- #RED Slovak #ERED +- #RED Slovenian #ERED + + + +===Who is qualified=== + +Writing a resource grammar implementation requires good general programming +skills, and a good explicit knowledge of the grammar of the target language. +A typical participant could be +- native or fluent speaker of the target language +- interested in languages on the theoretical level, and preferably familiar + with many languages (to be able to think about them on an abstract level) +- familiar with functional programming languages such as ML or Haskell + (GF itself is a language similar to these) +- on Master's or PhD level in linguistics, computer science, or mathematics + + +But it is the quality of the assignment that is assessed, not any formal +requirements. The "typical participant" was described to give an idea of +who is likely to succeed in this. + + +===The Summer School=== + +A Summer School on resource grammars and applications will +be organized at the campus of Chalmers University of Technology in Gothenburg, +Sweden, on 17-28 August 2009. It can be seen as a natural checkpoint in +a resource grammar project; the participants are assumed to learn GF before +the Summer School, but how far they have come in their projects may vary. + +More information on the Summer School web page: + +[``http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/doc/gf-summerschool.html`` http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/doc/gf-summerschool.html] + + +==Other project ideas== + +===GF interpreter in Java=== + +The idea is to write a run-time system for GF grammars in Java. This enables +the use of **embedded grammars** in Java applications. This project is +a fresh-up of [earlier work http://www.cs.chalmers.se/~bringert/gf/gf-java.html], +now using the new run-time format PGF and addressing a new parsing algorithm. + +Requirements: Java, Haskell, basics of compilers and parsing algorithms. + + +===GF interpreter in C#=== + +The idea is to write a run-time system for GF grammars in C#. This enables +the use of **embedded grammars** in C# applications. This project is +similar to [earlier work http://www.cs.chalmers.se/~bringert/gf/gf-java.html] +on Java, now addressing C# and using the new run-time format PGF. + +Requirements: C#, Haskell, basics of compilers and parsing algorithms. + + +===GF localization library=== + +This is an idea for a software localization library using GF grammars. +The library should replace strings by grammar rules, which can be conceived +as very smart templates always guaranteeing grammatically correct output. +The library should be based on the +[GF Resource Grammar Library http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/lib/resource/doc/synopsis.html], providing infrastructure +currently for 12 languages. + +Requirements: GF, some natural languages, some localization platform + + +===Multilingual grammar applications for mobile phones=== + +GF grammars can be compiled into programs that can be run on different +platforms, such as web browsers and mobile phones. An example is a +[numeral translator http://www.cs.chalmers.se/Cs/Research/Language-technology/GF/demos/index-numbers.html] running on both these platforms. + +The proposed project is rather open: find some cool applications of +the technology that are useful or entertaining for mobile phone users. A +part of the project is to investigate implementation issues such as making +the best use of the phone's resources. Possible applications have +something to do with translation; one suggestion is an sms editor/translator. + +Requirements: GF, JavaScript, some phone application development tools + + +===Multilingual grammar applications for the web=== + +This project is rather open: find some cool applications of +the technology that are useful or entertaining on the web. Examples include +- translators: see [demo http://tournesol.cs.chalmers.se:41296/translate] +- multilingual wikis: see [demo http://csmisc14.cs.chalmers.se/~meza/restWiki/wiki.cgi] +- fridge magnets: see [demo http://tournesol.cs.chalmers.se:41296/fridge] + + +Requirements: GF, JavaScript or Java and Google Web Toolkit, CGI + + +===GMail gadget for GF=== + +It is possible to add custom gadgets to GMail. If you are going to write +e-mail in a foreign language then you probably will need help from +dictonary or you may want to check something in the grammar. GF provides +all resources that you may need but you have to think about how to +design gadget that fits well in the GMail environment and what +functionality from GF you want to expose. + +Requirements: GF, Google Web Toolkit + + + +==Dissemination and intellectual property== + +All code suggested here will be released under the LGPL just like +the current resource grammars and run-time GF libraries, +with the copyright held by respective authors. + +As a rule, the code will be distributed via the GF web site. + diff --git a/examples/bronzeage/SwadeshEng.gf b/examples/bronzeage/SwadeshEng.gf index 7ebab9596..9b2cb878e 100644 --- a/examples/bronzeage/SwadeshEng.gf +++ b/examples/bronzeage/SwadeshEng.gf @@ -2,5 +2,6 @@ concrete SwadeshEng of Swadesh = SwadeshI with (Syntax = SyntaxEng), +v v v v v v v +^ ^ ^ ^ ^ ^ ^ (Lexicon = LexiconEng) ; - diff --git a/examples/bronzeage/SwadeshI.gf b/examples/bronzeage/SwadeshI.gf index 331f926aa..192ad95e9 100644 --- a/examples/bronzeage/SwadeshI.gf +++ b/examples/bronzeage/SwadeshI.gf @@ -98,6 +98,7 @@ incomplete concrete SwadeshI of Swadesh = open Syntax, Lexicon in { white_A = Lexicon.white_A ; wide_A = Lexicon.wide_A ; yellow_A = Lexicon.yellow_A ; + -- Nouns animal_N = Lexicon.animal_N ; ashes_N = Lexicon.ashes_N ; diff --git a/next-lib/src/Make.hs b/next-lib/src/Make.hs index 9fca1713a..bd835def4 100644 --- a/next-lib/src/Make.hs +++ b/next-lib/src/Make.hs @@ -152,8 +152,12 @@ demos abstr ls = "gr -number=100 | l -treebank " ++ unlexer abstr ls ++ lang (lla,la) = lla ++ "/All" ++ la ++ ".gf" compat (lla,la) = lla ++ "/Compatibility" ++ la ++ ".gf" symbol (lla,la) = lla ++ "/Symbol" ++ la ++ ".gf" +v v v v v v v +try (lla,la) = "api/Syntax" ++ la ++ ".gf" +************* try (lla,la) = "api/Try" ++ la ++ ".gf" syntax (lla,la) = "api/Syntax" ++ la ++ ".gf" +^ ^ ^ ^ ^ ^ ^ symbolic (lla,la) = "api/Symbolic" ++ la ++ ".gf" parse (lla,la) = "parse/Parse" ++ la ++ ".gf" diff --git a/src/server/lighttpd.conf b/src/server/lighttpd.conf index 09f73f102..23b7f6d8c 100644 --- a/src/server/lighttpd.conf +++ b/src/server/lighttpd.conf @@ -50,7 +50,7 @@ fastcgi.debug = 0 fastcgi.server = ( ".pgf" => (( "socket" => basedir + "/" + var.PID + "-pgf.socket", - "bin-path" => basedir + "/pgf.fcgi", + "bin-path" => basedir + "/dist/build/pgf-server/pgf-server", # Use 2 OS threads (to be able to use 2 cores). # Limit heap size to 512 MB. "bin-environment" => ("GHCRTS" => "-N2 -M512M"), |
