[Corpora-List] Syntactic parsing performance by humans?

Koos Wilt kooswilt at gmail.com
Fri May 13 20:26:44 CEST 2016

Also please allow me to give a plug for the Stanford Parser. I cannot claim if performs worse or better than Google's, but it's become my trusty of war-horse.

2016-05-13 20:24 GMT+02:00 Koos Wilt <kooswilt at gmail.com>:

> Bob Berwick
> 20:13 (10 minuten geleden)
> aan mij
> would be useful for the list and the community. please do.
> Koos Wilt <kooswilt at gmail.com>
> 20:14 (9 minuten geleden)
> aan Bob
> Coming up tomorrow or so.
> 2016-05-13 19:51 GMT+02:00 Koos Wilt <kooswilt at gmail.com>:
>> I wrote an overview of the performance of parsers about 4 years ago.
>> Would sending it somewhere (e.g. to Mr Brew) be helpful to anyone? It's on
>> my other laptop so I have to dig for it.
>> Best,
>> -K
>> 2016-05-13 19:30 GMT+02:00 chris brew <cbrew at acm.org>:
>>> It is an unarguable fact that Google's parser gets a higher score, on
>>> the metrics chosen, which are completely standard in the NLP community.
>>> What is really being measured is what percentage of the links in a graph
>>> that links words to words via labeled links are correct. If, as is common,
>>> there are many words in the sentence, there will be many links too, and
>>> many opportunities for mistakes. You could get a 90% score and still have a
>>> mistake or two in nearly every sentence.
>>> Whether this quality level is OK depends entirely on what use you plan
>>> to make of the graph that has been produced.
>>> The Penn Treebank was made many years ago, with version 2 coming out in
>>> 1995. We have learnt a lot about how to annotate corpora and evaluate
>>> parsing since then. The Web Treebank is much newer, and reflects painfully
>>> learned best practices, so should be good quality, but is on the other hand
>>> dealing with much messier language, so performance scores are lower.
>>> The current practice of evaluating individual dependencies was
>>> introduced as a result of major deficiencies in the first evaluation
>>> metrics that were used. It has the major plus of being transparent and
>>> straightforward. I believe that improvements in the metric will usually
>>> translate into improvements for downstream tasks that use parsing as
>>> inputs, and I wasn't so sure using earlier metrics. This is progress, but
>>> quite modest progress.
>>> On 13 May 2016 at 12:55, Darren Cook <darren at dcook.org> wrote:
>>>> Google have trained a neural net (part of publicizing their open-source
>>>> TensorFlow framework?) to parse syntax, claiming it is the world's best:
>>>> http://googleresearch.blogspot.co.uk/2016/05/announcing-syntaxnet-worlds-most.html
>>>> I just wanted to quote this bit, on performance: (they've called in
>>>> Parsey McParseface)
>>>> "Parsey McParseface recovers individual dependencies between words
>>>> with over 94% accuracy, ... While there are no explicit studies in the
>>>> literature about human performance, we know from our in-house annotation
>>>> projects that linguists trained for this task agree in 96-97% of the
>>>> cases ... Sentences drawn from the web are a lot harder to analyze,
>>>> ...[it] achieves just over 90% of parse accuracy on this dataset. "
>>>> Are there really no studies of human performance?! Surely some professor
>>>> has hinted to their PhD students that it is a nice bit of relatively
>>>> easy linguistics research, that should also get them cited a lot...
>>>> (I was mainly curious what the human performance gap between Penn
>>>> Treebank and Google WebTreebank would be; if it would be more or less
>>>> than the 4% gap for the deep learning algorithm.)
>>>> Darren
>>>> _______________________________________________
>>>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>>>> Corpora mailing list
>>>> Corpora at uib.no
>>>> http://mailman.uib.no/listinfo/corpora
>>> _______________________________________________
>>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>>> Corpora mailing list
>>> Corpora at uib.no
>>> http://mailman.uib.no/listinfo/corpora
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 8718 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160513/71e6fafa/attachment.txt>

More information about the Corpora mailing list