lil-lab / amr

Cornell AMR Semantic Parser (Artzi et al., EMNLP 2015)
http://yoavartzi.com/amr
GNU General Public License v2.0
23 stars 10 forks source link

Train #1

Closed Ramesh-X closed 7 years ago

Ramesh-X commented 7 years ago

How to create a new model using new dataset..?

yoavartzi commented 7 years ago

You will have to prepare the data. You can do it by customizing the customizing this part: https://github.com/yoavartzi/amr#preparing-the-data-required-only-for-training-and-testing

Then you will need to create .exp files. You can see how they look by looking here: https://github.com/yoavartzi/amr/blob/master/experiments/dev.proxy/dev.proxy.exp This includes customizing some of the included files. When you run using such an .exp file, a complete training process starts: java -jar dist/amr-1.0.jar experiments/dev.proxy/dev.proxy.exp

You can also use the included distributed learning framework. The key files for this are: experiments/dev.proxy.dev.proxy.dist.exp (for example) experiments/worker/worker.exp

I am sorry this is not better documented. We hope to improve this in the future, but it will take time.

Ramesh-X commented 7 years ago

Thanks for reply. I tried to start the training as you said. I get the following error.

Reading POS tagger model from /data/ramesh/amr/amr/experiments/dev.proxy/../../resources/stanford-models/english-bidirectional-distsim.tagger ... done [0.5 sec]. Exception in thread "main" java.lang.RuntimeException: org.xml.sax.SAXParseException; systemId: file:///data/ramesh/amr/amr/experiments/dev.proxy/../../resources/propbank/._funnel.xml; lineNumber: 1; columnNumber: 1; Content is not allowed in prolog. at edu.uw.cs.lil.amr.util.propbank.PropBankReader.of(PropBankReader.java:44) at edu.uw.cs.lil.amr.util.propbank.PropBank.lambda$new$2(PropBank.java:26) at java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:267) at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175) at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175) at java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193) at java.util.Iterator.forEachRemaining(Iterator.java:116) at java.util.Spliterators$IteratorSpliterator.forEachRemaining(Spliterators.java:1801) at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:481) at java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:471) at java.util.stream.ReduceOps$ReduceOp.evaluateSequential(ReduceOps.java:708) at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234) at java.util.stream.ReferencePipeline.collect(ReferencePipeline.java:499) at edu.uw.cs.lil.amr.util.propbank.PropBank.(PropBank.java:28) at edu.uw.cs.lil.amr.lambda.AMRServices.(AMRServices.java:144) at edu.uw.cs.lil.amr.lambda.AMRServices.(AMRServices.java:50) at edu.uw.cs.lil.amr.lambda.AMRServices$Builder.build(AMRServices.java:710) at edu.uw.cs.lil.amr.Init.init(Init.java:129) at edu.uw.cs.lil.amr.exp.AmrExp.(AmrExp.java:87) at edu.uw.cs.lil.amr.exp.AmrExp.(AmrExp.java:117) at edu.uw.cs.lil.amr.exp.AmrGenericExperiment.main(AmrGenericExperiment.java:28) at edu.uw.cs.lil.amr.Main.main(Main.java:61) Caused by: org.xml.sax.SAXParseException; systemId: file:///data/ramesh/amr/amr/experiments/dev.proxy/../../resources/propbank/._funnel.xml; lineNumber: 1; columnNumber: 1; Content is not allowed in prolog. at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(ErrorHandlerWrapper.java:203) at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(ErrorHandlerWrapper.java:177) at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:400) at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:327) at com.sun.org.apache.xerces.internal.impl.XMLScanner.reportFatalError(XMLScanner.java:1472) at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl$PrologDriver.next(XMLDocumentScannerImpl.java:994) at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:602) at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:505) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:841) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:770) at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:141) at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1213) at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:643) at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl.parse(SAXParserImpl.java:327) at javax.xml.parsers.SAXParser.parse(SAXParser.java:274) at edu.uw.cs.lil.amr.util.propbank.PropBankReader.of(PropBankReader.java:42) ... 21 more

._funnel.xml file that is reffered in the error is attached here as funnel.txt file. Hope for a help.. funnel.txt

yoavartzi commented 7 years ago

Sorry for the delayed reply.

I am not sure why this is happening. This looks like a problem in either our PropBank reader or in the PropBank files you have. That said, I don’t think we ended up using PropBank in any meaningful way. I suggest trying to delete the “propBank=“ line in experiments/params.inc.

If you try it, can you let me know if it works?

Thanks,

Yoav

On Sun, Nov 6, 2016 at 10:32 PM, Ramesh-X notifications@github.com wrote:

Thanks for reply. I tried to start the training as you said. I get the following error.

_Reading POS tagger model from /data/ramesh/amr/amr/experiments/dev.proxy/../../resources/stanford-models/english-bidirectional-distsim.tagger ... done [0.5 sec]. Exception in thread "main" java.lang.RuntimeException: org.xml.sax.SAXParseException; systemId: file:///data/ramesh/amr/amr/experiments/dev.proxy/../../resources/propbank/._funnel.xml; lineNumber: 1; columnNumber: 1; Content is not allowed in prolog. at edu.uw.cs.lil.amr.util.propbank.PropBankReader.of(PropBankReader.java:44) at edu.uw.cs.lil.amr.util.propbank.PropBank.lambda$new$2(PropBank.java:26) at java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:267) at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175) at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175) at java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193) at java.util.Iterator.forEachRemaining(Iterator.java:116) at java.util.Spliterators$IteratorSpliterator.forEachRemaining(Spliterators.java:1801) at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:481) at java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:471) at java.util.stream.ReduceOps$ReduceOp.evaluateSequential(ReduceOps.java:708) at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234) at java.util.stream.ReferencePipeline.collect(ReferencePipeline.java:499) at edu.uw.cs.lil.amr.util.propbank.PropBank.(PropBank.java:28) at edu.uw.cs.lil.amr.lambda.AMRServices.(AMRServices.java:144) at edu.uw.cs.lil.amr.lambda.AMRServices.(AMRServices.java:50) at edu.uw.cs.lil.amr.lambda.AMRServices$Builder.build(AMRServices.java:710) at edu.uw.cs.lil.amr.Init.init(Init.java:129) at edu.uw.cs.lil.amr.exp.AmrExp.(AmrExp.java:87) at edu.uw.cs.lil.amr.exp.AmrExp.(AmrExp.java:117) at edu.uw.cs.lil.amr.exp.AmrGenericExperiment.main(AmrGenericExperiment.java:28) at edu.uw.cs.lil.amr.Main.main(Main.java:61) Caused by: org.xml.sax.SAXParseException; systemId: file:///data/ramesh/amr/amr/experiments/dev.proxy/../../resources/propbank/.funnel.xml; lineNumber: 1; columnNumber: 1; Content is not allowed in prolog. at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(ErrorHandlerWrapper.java:203) at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(ErrorHandlerWrapper.java:177) at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:400) at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:327) at com.sun.org.apache.xerces.internal.impl.XMLScanner.reportFatalError(XMLScanner.java:1472) at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl$PrologDriver.next(XMLDocumentScannerImpl.java:994) at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:602) at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:505) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:841) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:770) at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:141) at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1213) at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:643) at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl.parse(SAXParserImpl.java:327) at javax.xml.parsers.SAXParser.parse(SAXParser.java:274) at edu.uw.cs.lil.amr.util.propbank.PropBankReader.of(PropBankReader.java:42) ... 21 more

._funnel.xml file that is reffered in the error is attached here as funnel.txt file. Hope for a help.. funnel.txt https://github.com/yoavartzi/amr/files/574394/funnel.txt

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/yoavartzi/amr/issues/1#issuecomment-258740096, or mute the thread https://github.com/notifications/unsubscribe-auth/ADIzEewZV4kn2Vrejzvrxp3w9PLkzjCwks5q7pvFgaJpZM4KijLk .

yoavartzi commented 7 years ago

This problem might be due to issue https://github.com/yoavartzi/amr/issues/2

I fixed the getres.sh script, so hopefully this issue is solved now. Closing it.

Thanks