Apertium separable/report2017 - Revision history

Irene: Irene moved page Lsx module/report2017 to Apertium separable/report2017: Rename page

2017-11-15T18:36:13Z

Irene moved page Lsx module/report2017 to Apertium separable/report2017: Rename page

Firespeaker: /* Work done */ tmk, nothing special was done for the "plus thing"

2017-09-03T17:22:51Z

Work done: tmk, nothing special was done for the "plus thing"

Firespeaker: /* Work done */

2017-09-03T17:21:57Z

Work done

Firespeaker: /* Future work */

2017-08-31T22:04:04Z

Future work

Irene: Irene moved page Lsx module/report to Lsx module/report2017

2017-08-29T03:27:04Z

Irene moved page Lsx module/report to Lsx module/report2017

Irene: Created page with "==Project description== The purpose of this project is to allow Apertium language-pair developers to better translate "seperable" or "discontiguous" multiwords. We do this by ..."

2017-08-29T03:23:42Z

Created page with "==Project description== The purpose of this project is to allow Apertium language-pair developers to better translate "seperable" or "discontiguous" multiwords. We do this by ..."

New page

==Project description==
The purpose of this project is to allow Apertium language-pair developers to better translate "seperable" or "discontiguous" multiwords. We do this by re-ordering word tokens before translation occurs. For example, "take something out" becomes "take out something" so that "take out" can be translated as a single unit.

To do this, a finite-state transducer was used. The transducer accepted certain patterns of words (paradigms), such as adj-noun or det-adj-noun, that could separate the multiword. If the pattern was accepted, then the transducer would output the re-ordered words for better translation quality.

==Work done==
* established dictionary format
** <j/>, <t/>, <w/> are supported within pair entries and loop as expected
** see https://svn.code.sf.net/p/apertium/svn/branches/apertium-separable/examples/apertium-eng-spa.eng-spa.lsx for an example dictionary

* implemented a compiler for the separable-words dictionary and a processor to process tagged input
** see https://svn.code.sf.net/p/apertium/svn/branches/apertium-separable/src/

* all spacing, punctuation, and superblanks were preserved

* support for the "plus thing":
<pre>
echo "^абай<adj>$ ^бол<v><iv><neg><aor><p2><sg>+ма<qst>$^.<sent>$" | lsx-proc kaz-kir.autoseq.bin
^абай бол<v><iv><neg><aor><p2><sg>+ма<qst>$^.<sent>$
</pre>

* (for language developers: have the language-data writer write it explicitly in the .lsx file)

* For a full list of commits, see https://apertium.projectjj.com/gsoc2017/irene-tang.html
* For further documentation usage instructions, see [[Lsx_module]]

==Future work==
* 10:53 firespeaker: pektii: if we offload multiwords from the transducers to lsx, (1) how do we do N N compounds with lsx? (2) how does translation *to* a multiword work?
* recycling dictionaries and/or paradigms? lsx-dictionaries are packaged in language pairs. the eng-spa lsx-dictionary can mostly be reaped by eng-cat. could we make use of the similarity?
* Support for language pairs: we haven't gotten much extensive beta testing. The following are language pairs that have packaged the lsx-module:
** eng-cat
** eng-deu (?)

← Older revision	Revision as of 18:36, 15 November 2017
(No difference)

@@ Line 13: / Line 13: @@
 * all spacing, punctuation, and superblanks were preserved
-* support for the "plus thing":
-<pre>
-echo "^абай<adj>$ ^бол<v><iv><neg><aor><p2><sg>+ма<qst>$^.<sent>$" | lsx-proc kaz-kir.autoseq.bin
-^абай бол<v><iv><neg><aor><p2><sg>+ма<qst>$^.<sent>$
-</pre>
 * (for language developers: have the language-data writer write it explicitly in the .lsx file)

@@ Line 22: / Line 22: @@
 * (for language developers: have the language-data writer write it explicitly in the .lsx file)
-* For a full list of commits, see https://apertium.projectjj.com/gsoc2017/irene-tang.html
+* For a '''full list of commits''', see https://apertium.projectjj.com/gsoc2017/irene-tang.html
 * For further documentation usage instructions, see [[Lsx_module]]

@@ Line 26: / Line 26: @@
 ==Future work==
+See [[Lsx_module#Future_work]].
-* 10:53 firespeaker: pektii: if we offload multiwords from the transducers to lsx, (1) how do we do N N compounds with lsx?  (2) how does translation *to* a multiword work?
-* recycling dictionaries and/or paradigms? lsx-dictionaries are packaged in language pairs. the eng-spa lsx-dictionary can mostly be reaped by eng-cat. could we make use of the similarity?
-* Support for language pairs: we haven't gotten much extensive beta testing. The following are language pairs that have packaged the lsx-module:
-** eng-cat
-** eng-deu (?)

← Older revision	Revision as of 03:27, 29 August 2017
(No difference)