Surface forms in the pipe - Revision history

Francis Tyers: /* Idea #2 */

2020-06-26T22:51:24Z

Idea #2

2020-06-24T16:50:30Z

Idea #2

2020-06-24T08:58:27Z

2020-06-23T12:55:05Z

Idea #2

2020-06-23T12:52:05Z

Idea #2

2020-06-23T12:51:41Z

2020-06-22T14:14:48Z

2020-06-22T14:12:09Z

2020-06-22T14:10:14Z

2020-06-22T14:07:07Z

@@ Line 96: / Line 96: @@
 </pre>
-: But here it has tags, so it's included in the monodix, but with the lemma changed to surface form?
-: What about CG rules referring to lemmas?
-[[User:Khannatanmai|Tanmai Khanna]] ([[User talk:Khannatanmai|talk]]) I brought up the same thing and he said that if there's a CG rule referring to a lemma then it's most likely going to be in the bidix as well, which makes sense. We just need to make this change before the tagger/CG throws away the surface form. Or if lt-trim can do it when it finds out an entry is to be trimmed then even better. (If to be trimmed, make right side = left side)
 [[Category:Ideas]]

@@ Line 99: / Line 99: @@
 : But here it has tags, so it's included in the monodix, but with the lemma changed to surface form?
 : What about CG rules referring to lemmas?
+[[User:Khannatanmai|Tanmai Khanna]] ([[User talk:Khannatanmai|talk]]) I brought up the same thing and he said that if there's a CG rule referring to a lemma then it's most likely going to be in the bidix as well, which makes sense. We just need to make this change before the tagger/CG throws away the surface form. Or if lt-trim can do it when it finds out an entry is to be trimmed then even better. (If to be trimmed, make right side = left side)
 [[Category:Ideas]]

@@ Line 97: / Line 97: @@
+: But here it has tags, so it's included in the monodix, but with the lemma changed to surface form?
+: What about CG rules referring to lemmas?
 [[Category:Ideas]]

@@ Line 78: / Line 78: @@
 		"lu" det def f sg
 "<ammiguitati>"
-	"*ammiguitati<n><f><sg>"
+	"*ammiguitati<n><f><sp>"
 </pre>
@@ Line 85: / Line 85: @@
 It's not like we're going to be able to use the lemma anyway.
+E.g. we could have a program in the pipeline... maybe it could be pretransfer, before separable, that reads the bilingual dictionary and reduces analyses.
+<pre>
+in:
+^ammiguitati/ammiguitati<n><f><sp>$
+out:
+^ammiguitati/*ammiguitati<n><f><sp>$
+</pre>

← Older revision		Revision as of 12:52, 23 June 2020
Line 83:		Line 83:

	This could then also be combined with guessers. The surface form would never change, and could just be output as is at the other end.		This could then also be combined with guessers. The surface form would never change, and could just be output as is at the other end.

			It's not like we're going to be able to use the lemma anyway.

@@ Line 4: / Line 4: @@
 Another usage could be allowing surface-form embeddings, like those produced by <tt>word2vec</tt> to be used in the tagger and lexical selection modules. Lexical selection could also potentially use surface forms too.
+==Idea #1==
 <pre>
@@ Line 52: / Line 54: @@
 * This will complicate the code for bidix lookup and for lexical selection (we'll need to be able to support '+' and output the product of each part
+==Idea #2==
+It occurs to me that if we want to "eliminate trimming" in order to get better context, then one thing we could do is
+do trimming, but pass the surface form instead of the lemma for those words not found in the bilingual dictionary.
+For example:
+''Sparti dâ ammiguitati'':
+<pre>
+"<Sparti>"
+	"spartiri" vblex pri p3 sg SELECT:291
+	"spàrtiri" vblex pri p3 sg SELECT:291
+;	"sparti" adv SELECT:291
+;	"spartiri" vblex imp p2 sg REMOVE:227
+;	"spartiri" vblex pri p2 sg SELECT:291
+;	"spàrtiri" vblex imp p2 sg REMOVE:227
+;	"spàrtiri" vblex pri p2 sg SELECT:291
+"<dâ>"
+	"di" pr
+		"lu" det def f sg
+"<ammiguitati>"
+	"*ammiguitati<n><f><sg>"
+</pre>
+This could then also be combined with guessers. The surface form would never change, and could just be output as is at the other end.
+[[Category:Ideas]]

@@ Line 1: / Line 1: @@
+{{TOCD}}
 Currently the surface form is thrown away after the tagger. It might be handy to be able to keep it until transfer in order to be able to substitute things unknown to the bidix.
@@ Line 46: / Line 48: @@
 ^de<pr>+el<det><def><m><sg>/del$
 </pre>
+==Questions==
+* This will complicate the code for bidix lookup and for lexical selection (we'll need to be able to support '+' and output the product of each part

@@ Line 28: / Line 28: @@
 Generation (?):
-Machiavelli lo dio por echo que *would-be *leaders apuntar en gloria o honor.
+Machiavelli lo dio por hecho que *would-be *leaders apuntar en gloria o honor.
 </pre>

@@ Line 26: / Line 26: @@
+Generation (?):
+Machiavelli lo dio por echo que *would-be *leaders apuntar en gloria o honor.
+</pre>
+Potentially generation could output something like <tt>^dar# por hecho<vblex><ifi><p3><sg>/dio por hecho$</tt> but then how would postgeneration work? e.g. for
+<pre>
+^de<pr>$ ^el<det><def><m><sg>$
+</pre>
+Could it be:
+<pre>
 Generation:
+^de<pr>/de$ ^el<det><def><m><sg>/el$
+Postgeneration:
+^de<pr>+el<det><def><m><sg>/del$
 </pre>