Anaphora resolution module - Revision history

Unhammer: /* Cataphora / when the "antecedent" is after the target */

2022-06-24T21:13:42Z

Cataphora / when the "antecedent" is after the target

Unhammer: /* How to Use this module */

2022-06-23T11:42:04Z

How to Use this module

Unhammer: /* def-parameters */

2022-06-23T09:01:48Z

def-parameters

Khannatanmai: /* def-markables */

2020-06-16T19:31:36Z

def-markables

Khannatanmai: /* def-markables */

2020-06-14T18:00:22Z

def-markables

Francis Tyers at 17:59, 14 June 2020

2020-06-14T17:59:22Z

Francis Tyers at 17:55, 14 June 2020

2020-06-14T17:55:18Z

Francis Tyers: Francis Tyers moved page Anaphora Resolution Module to Anaphora resolution module

2020-06-14T17:54:43Z

Francis Tyers moved page Anaphora Resolution Module to Anaphora resolution module

Khannatanmai: /* def-parameters */ exclude-tags

2020-06-14T11:08:42Z

def-parameters: exclude-tags

Khannatanmai: /* def-markables */

2020-06-14T09:09:52Z

def-markables

@@ Line 331: / Line 331: @@
 == Cataphora / when the "antecedent" is after the target ==
-There is no support in apertium-anaphora for cataphora. Fortunately, most of these are close to the target(citation needed), so you can probably deal with it in transfer rules.
+There is no support in apertium-anaphora for cataphora. Fortunately, most of these are close to the target(citation needed), so you can probably deal with it in transfer rules, though see https://github.com/apertium/apertium-anaphora/issues/28 .
 == How to Use this module ==

@@ Line 329: / Line 329: @@
 '''Example: Changes made to [https://github.com/apertium/apertium-eng-spa/pull/13/files#diff-8bbb1dad5ab918be99ea69cb408f413c apertium-eng-spa.spa-eng.t1x]'''
+== Cataphora / when the "antecedent" is after the target ==
+There is no support in apertium-anaphora for cataphora. Fortunately, most of these are close to the target(citation needed), so you can probably deal with it in transfer rules.
 == How to Use this module ==

@@ Line 199: / Line 199: @@
 			<parameter-item has-tags="n"/>
 			<parameter-item has-tags="np"/>
+			<parameter-item has-tags="prn" lemma="it" />
 		</antecedent>
 	</def-parameter>
@@ Line 205: / Line 206: @@
 </pre>
-In this example we tell the module that our anaphors could be possessive determiners, and that our antecedents could be nouns or proper nouns. We also define another parameter, where we say that our anaphor is a verb and our antecedents could be nouns or proper nouns.
+In this example we tell the module that our anaphors could be possessive determiners, and that our antecedents could be nouns or proper nouns (or one lemma-specific pronoun). We also define another parameter, where we say that our anaphor is a verb and our antecedents could be nouns or proper nouns.
 You also define the delimiter here, which is the tag <sent> which marks the ends of sentences, which is used to keep a context of the current and last three sentences. Make sure this is defined in your arx file.

@@ Line 319: / Line 319: @@
 '''If you don't mention a parameter with the score, then that markable score will be applied to all detected antecedents. If you mention a parameter, such as in the markable "Cop", then that score will only be applied for when Anaphora Resolution is happening for that anaphor-antecedent pair. (i.e. only if the anaphor is a possessive determiner). '''
-'''Example File: [https://github.com/apertium/apertium-anaphora/blob/master/samples/apertium-eng-spa.spa-eng.arx]'''
+'''Example File: [https://github.com/apertium/apertium-anaphora/blob/master/tests/apertium-eng-spa.spa-eng.arx]'''
 === Modifying Transfer Rules (t1x) ===

@@ Line 317: / Line 317: @@
 If you put the score as -1, every antecedent which is a part of that markable gets 1 subtracted from its score when the algorithm is calculating the final score to find the antecedent of an anaphor.
-'''If you don't mention a parameter with the score, then that markable score will be applied to all detected antecedents. If you mention a parameter, such as in the markable "Cop", then that score will only be applied for when Anaphora Resolution is happening for that anaphor-antecedent pair. (i.e. only if the anaphor is a possessive determiner).
+'''If you don't mention a parameter with the score, then that markable score will be applied to all detected antecedents. If you mention a parameter, such as in the markable "Cop", then that score will only be applied for when Anaphora Resolution is happening for that anaphor-antecedent pair. (i.e. only if the anaphor is a possessive determiner). '''
 '''Example File: [https://github.com/apertium/apertium-anaphora/blob/master/samples/apertium-eng-spa.spa-eng.arx]'''

@@ Line 473: / Line 473: @@
 In a test done by [[User:ScoopGracie]], adding the Anaphora module to the pipeline increased the duration from 31.515 seconds to 32.046 seconds, a 1.68% increase. The module on its own took 11.698 seconds to run. See https://scoopgracie.com/apertium-anaphora-timing.pdf for the full report.
 -->
+[[Category:Tools]]

← Older revision		Revision as of 17:55, 14 June 2020
Line 1:		Line 1:
			{{TOCD}}

	Here you will find the documentation for the Anaphora Resolution module created during the Google Summer of Code 2019. ([http://wiki.apertium.org/wiki/User:Khannatanmai Proposal])		Here you will find the documentation for the Anaphora Resolution module created during the Google Summer of Code 2019. ([http://wiki.apertium.org/wiki/User:Khannatanmai Proposal])

← Older revision	Revision as of 17:54, 14 June 2020
(No difference)

@@ Line 172: / Line 172: @@
 Here you define what the module will identify as anaphors and as antecedents. All antecedents will be given scores in the module and all anaphors will have an antecedent attached to them in the module's output.
-Now you can define multiple types of antecedent-anaphor pairs, so that your scores don't have to all apply to all kinds of anaphors. You can define them like this:
+Now you can define multiple types of antecedent-anaphor pairs, so that your scores don't have to all apply to all kinds of anaphors. You can also use exclude-tags in parameter-items so that you can mention tags you don't want to match. You can define them like this:
 <pre>
 <section-parameters>
@@ Line 185: / Line 185: @@
 		<antecedent>
-			<parameter-item has-tags="n"/>
+			<parameter-item has-tags="n" exclude-tags="rel"/>
-			<parameter-item has-tags="np"/>
+			<parameter-item has-tags="np" exclude-tags="rel"/>
 		</antecedent>
 	</def-parameter>

@@ Line 260: / Line 260: @@
                 .
                 <score n="-1"/>
+	</markable>
+        <markable n="IP">
+	        <pattern>
+			<pattern-item n="ind"/>
+			<pattern-item n="nom"/>
+		</pattern>
+		<pattern>
+			<pattern-item n="ind"/>
+			<pattern-item n="adj"/>
+			<pattern-item n="nom"/>
+		</pattern>
+		<score n="-1"/> <!-- This gives a -1 score to any antecedent that is part of a Indefinite Noun Phrase -->
+        </markable>
+	<markable n="PNP">
+		<pattern>
+			<pattern-item n="np"/>
+		</pattern>
+		<score n="1"/> <!-- This gives a +1 score to any antecedent that is part of a Proper Noun -->
+	</markable>
+	<markable n="AdNP"> <!-- NP that is being addressed , for example, "Madam President, ..."-->
+		<pattern>
+			<pattern-item n="nom"/>
+			<pattern-item n="com"/>
+		</pattern>
+		<pattern>
+			<pattern-item n="nom"/>
+			<pattern-item n="nom"/>
+			<pattern-item n="com"/>
+		</pattern>
+		<score n="-2"/>
+	</markable>
+	<markable n="Cop">
+		<pattern>
+			<pattern-item n="nom"/>
+			<pattern-item n="cop"/>
+			<pattern-item n="anaphor"/>
+		</pattern>
+		<score n="-5" parameter="detpos"/>
 	</markable>
 </section-markables>
@@ Line 269: / Line 316: @@
 If you put the score as -1, every antecedent which is a part of that markable gets 1 subtracted from its score when the algorithm is calculating the final score to find the antecedent of an anaphor.
+'''If you don't mention a parameter with the score, then that markable score will be applied to all detected antecedents. If you mention a parameter, such as in the markable "Cop", then that score will only be applied for when Anaphora Resolution is happening for that anaphor-antecedent pair. (i.e. only if the anaphor is a possessive determiner).
-'''Example File: [https://github.com/apertium/apertium-eng-spa/blob/anaphora-transfer/apertium-eng-spa.spa-eng.arx apertium-eng-spa.spa-eng.arx]'''
+'''Example File: [https://github.com/apertium/apertium-anaphora/blob/master/samples/apertium-eng-spa.spa-eng.arx]'''
-'''NOTE:''' All indicators are applied on All possible antecedents to give the final score of each antecedent. As mentioned earlier, the highest scored antecedent is then chosen as the final antecedent.
 === Modifying Transfer Rules (t1x) ===