POS Induction (State of the art) - Revision history

Jonsafari: /* Software */ fix mkcls link

2014-03-08T00:40:10Z

Software: fix mkcls link

← Older revision		Revision as of 00:40, 8 March 2014
Line 56:		Line 56:
	* [http://www.cs.rhul.ac.uk/home/alexc/pos2.tar.gz alexc]		* [http://www.cs.rhul.ac.uk/home/alexc/pos2.tar.gz alexc]
	* [https://github.com/percyliang/brown-cluster brown-cluster]		* [https://github.com/percyliang/brown-cluster brown-cluster]
	* [~~http~~://~~www~~.~~statmt~~.~~org~~/~~moses~~/giza/~~mkcls.html~~ mkcls]		* [https://code.google.com/p/giza-pp/ mkcls]
	* [http://wortschatz.uni-leipzig.de/~cbiemann/software/unsupos.html unsupos]		* [http://wortschatz.uni-leipzig.de/~cbiemann/software/unsupos.html unsupos]
	* [https://github.com/ai-ku/upos upos]		* [https://github.com/ai-ku/upos upos]

Jonsafari: +software links

2014-03-07T23:24:21Z

+software links

← Older revision		Revision as of 23:24, 7 March 2014
Line 53:		Line 53:
	* Yatbaz, Mehmet Ali, Enis Sert and Deniz Yuret. 2012. [http://aclweb.org/anthology//D/D12/D12-1086.pdf Learning Syntactic Categories Using Paradigmatic Representations of Word Context]. In Proceedings of EMNLP 2012, pages 940–951.		* Yatbaz, Mehmet Ali, Enis Sert and Deniz Yuret. 2012. [http://aclweb.org/anthology//D/D12/D12-1086.pdf Learning Syntactic Categories Using Paradigmatic Representations of Word Context]. In Proceedings of EMNLP 2012, pages 940–951.

			== Software ==
			* [http://www.cs.rhul.ac.uk/home/alexc/pos2.tar.gz alexc]
			* [https://github.com/percyliang/brown-cluster brown-cluster]
			* [http://www.statmt.org/moses/giza/mkcls.html mkcls]
			* [http://wortschatz.uni-leipzig.de/~cbiemann/software/unsupos.html unsupos]
			* [https://github.com/ai-ku/upos upos]

	== See also ==		== See also ==

Jonsafari: clean refs

2014-03-07T23:12:14Z

clean refs

← Older revision		Revision as of 23:12, 7 March 2014
Line 5:		Line 5:

	==Results==		==Results==
			'''Listed in order of decreasing accuracy'''
	* '''Listed in order of decreasing accuracy'''


Line 47:		Line 46:

	== References ==		== References ==
			'''Listed alphabetically.'''

	* ~~'''Listed alphabetically~~.~~'''~~		* Berg-Kirkpatrick, Taylor, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. [http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Painless Unsupervised Learning with Features]. NAACL 2010.
			* Christodoulopoulos, Christos, Sharon Goldwater and Mark Steedman. 2010. [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Two Decades of Unsupervised POS induction: How far have we come?] In Proceedings of EMNLP 2010.
			* Clark, Alexander. 2003. [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Combining distributional and morphological information for part of speech induction]. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.
	[http://www.aclweb.org/anthology/N/N10/N10-1083.pdf ~~Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010.~~ Painless Unsupervised Learning with Features. NAACL 2010.]		* Yatbaz, Mehmet Ali, Enis Sert and Deniz Yuret. 2012. [http://aclweb.org/anthology//D/D12/D12-1086.pdf Learning Syntactic Categories Using Paradigmatic Representations of Word Context]. In Proceedings of EMNLP 2012, pages 940–951.

	[http://www.aclweb.org/anthology/D/D10/D10-1056.pdf ~~Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010.~~ Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]

	[http://www.aclweb.org/anthology/E/E03/E03-1009.pdf ~~Alexander Clark. 2003.~~ Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]

	[http://aclweb.org/anthology//D/D12/D12-1086.pdf ~~Mehmet Ali Yatbaz, Enis Sert and Deniz Yuret. 2012.~~ Learning Syntactic Categories Using Paradigmatic Representations of Word Context. In Proceedings of EMNLP 2012, pages ~~940-951~~.]

Pdturney at 12:27, 23 October 2013

2013-10-23T12:27:35Z

← Older revision		Revision as of 12:27, 23 October 2013
Line 1:		Line 1:
	==Evaluation==		==Evaluation==

	'''Many-to-1:''' Map every induced label to a gold standard tag greedily (45 labels to 45 tags of the Penn tag set). Use the mapping to compute tag accuracy on the Wall Street Journal portion of the Penn TreeBank.		'''Many-to-1:''' Map every induced label to a gold standard tag greedily (45 labels to 45 tags of the Penn tag set). Use the mapping to compute tag accuracy on the Wall Street Journal portion of the Penn TreeBank.


	==Results==		==Results==

			* '''Listed in order of decreasing accuracy'''


	{\| border="1" cellpadding="5" cellspacing="1" width="100%"		{\| border="1" cellpadding="5" cellspacing="1" width="100%"
Line 39:		Line 44:

	<nowiki>*</nowiki> according to Christodoulopoulos, Goldwater and Steedman (2010)		<nowiki>*</nowiki> according to Christodoulopoulos, Goldwater and Steedman (2010)


	== References ==		== References ==

	* [http://aclweb.org/anthology//D/~~D12~~/~~D12~~-~~1086~~.pdf ~~Mehmet Ali Yatbaz~~, ~~Enis Sert~~ and ~~Deniz Yuret~~. ~~2012~~. ~~Learning Syntactic Categories Using Paradigmatic Representations~~ of ~~Word Context.~~ In Proceedings of EMNLP ~~2012, pages 940-951~~.]		* '''Listed alphabetically.'''


			[http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. Painless Unsupervised Learning with Features. NAACL 2010.]

			[http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]

	* [http://www.aclweb.org/anthology/D/~~D10~~/~~D10~~-~~1056~~.pdf ~~Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman~~. ~~2010~~. ~~Two Decades~~ of ~~Unsupervised POS~~ induction~~: How far have we come?~~ In Proceedings of ~~EMNLP 2010~~.]		[http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]

	* [http://~~www.~~aclweb.org/anthology/N/~~N10~~/~~N10~~-~~1083~~.pdf ~~Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero~~, and ~~Dan Klein~~. ~~2010~~. ~~Painless Unsupervised~~ Learning ~~with Features~~. ~~NAACL 2010~~.]		[http://aclweb.org/anthology//D/D12/D12-1086.pdf Mehmet Ali Yatbaz, Enis Sert and Deniz Yuret. 2012. Learning Syntactic Categories Using Paradigmatic Representations of Word Context. In Proceedings of EMNLP 2012, pages 940-951.]

	* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]

	== See also ==		== See also ==

Denizyuret: /* References */

2013-10-23T12:14:45Z

References

← Older revision		Revision as of 12:14, 23 October 2013
Line 41:		Line 41:

	== References ==		== References ==

			* [http://aclweb.org/anthology//D/D12/D12-1086.pdf Mehmet Ali Yatbaz, Enis Sert and Deniz Yuret. 2012. Learning Syntactic Categories Using Paradigmatic Representations of Word Context. In Proceedings of EMNLP 2012, pages 940-951.]

	* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]		* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]
Line 47:		Line 49:

	* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]		* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]

	* [http://aclweb.org/anthology//D/D12/D12-1086.pdf Mehmet Ali Yatbaz, Enis Sert and Deniz Yuret. 2012. Learning Syntactic Categories Using Paradigmatic Representations of Word Context. In Proceedings of EMNLP 2012, pages 940-951.]

	== See also ==		== See also ==

Aydinhan at 12:10, 23 October 2013

2013-10-23T12:10:17Z

← Older revision		Revision as of 12:10, 23 October 2013
Line 11:		Line 11:
	! Software		! Software
	! Many-to-1		! Many-to-1
			\|-
			\| UPOS
			\| Learning Syntactic Categories Using Paradigmatic Representations of Word Context
			\| Yatbaz et al. (2012)
			\| [https://github.com/ai-ku/upos/tree/emnlp2012 upos]
			\| 80.2%
	\|-		\|-
	\| Brown+proto		\| Brown+proto
Line 41:		Line 47:

	* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]		* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]

			* [http://aclweb.org/anthology//D/D12/D12-1086.pdf Mehmet Ali Yatbaz, Enis Sert and Deniz Yuret. 2012. Learning Syntactic Categories Using Paradigmatic Representations of Word Context. In Proceedings of EMNLP 2012, pages 940-951.]

	== See also ==		== See also ==

Pdturney: Reverted edits by Creek (talk) to last revision by Auser

2012-06-25T11:17:00Z

Reverted edits by Creek (talk) to last revision by Auser

← Older revision		Revision as of 11:17, 25 June 2012
Line 15:		Line 15:
	\| MRF initialized with Brown prototypes		\| MRF initialized with Brown prototypes
	\| Christodoulopoulos, Goldwater and Steedman (2010)		\| Christodoulopoulos, Goldwater and Steedman (2010)
	\| ~~[http://www.thai-sbobet.com sbo]~~		\|
	\| 76.1%		\| 76.1%
	\|-		\|-
Line 21:		Line 21:
	\| Logistic regression with features and LBFGS		\| Logistic regression with features and LBFGS
	\| Berg-Kirkpatrick et al. (2010)		\| Berg-Kirkpatrick et al. (2010)
	\| ~~[http://www.thai-sbobet.com sbobet]~~		\|
	\| 75.5%		\| 75.5%
	\|-		\|-

Creek: /* Results */

2012-06-25T08:57:27Z

Results

← Older revision		Revision as of 08:57, 25 June 2012
Line 18:		Line 18:
	\| 76.1%		\| 76.1%
	\|-		\|-
	\| ~~[http://www.thai-sbobet.com sbobet]~~		\|
	\| Logistic regression with features and LBFGS		\| Logistic regression with features and LBFGS
	\| Berg-Kirkpatrick et al. (2010)		\| Berg-Kirkpatrick et al. (2010)
	\|		\| [http://www.thai-sbobet.com sbobet]
	\| 75.5%		\| 75.5%
	\|-		\|-

Creek: /* Results */

2012-06-25T08:56:57Z

Results

← Older revision		Revision as of 08:56, 25 June 2012
Line 15:		Line 15:
	\| MRF initialized with Brown prototypes		\| MRF initialized with Brown prototypes
	\| Christodoulopoulos, Goldwater and Steedman (2010)		\| Christodoulopoulos, Goldwater and Steedman (2010)
	\|		\| [http://www.thai-sbobet.com sbo]
	\| 76.1%		\| 76.1%
	\|-		\|-
	\|		\| [http://www.thai-sbobet.com sbobet]
	\| Logistic regression with features and LBFGS		\| Logistic regression with features and LBFGS
	\| Berg-Kirkpatrick et al. (2010)		\| Berg-Kirkpatrick et al. (2010)

Auser: evaluate 45 labels

2011-01-27T22:07:19Z

evaluate 45 labels

← Older revision		Revision as of 22:07, 27 January 2011
Line 1:		Line 1:
	==Evaluation==		==Evaluation==
	'''Many-to-1:''' ~~Mapping~~ every induced label to a gold standard tag greedily. Use the mapping to compute tag accuracy on the Wall Street Journal ~~part~~ of the Penn TreeBank.		'''Many-to-1:''' Map every induced label to a gold standard tag greedily (45 labels to 45 tags of the Penn tag set). Use the mapping to compute tag accuracy on the Wall Street Journal portion of the Penn TreeBank.

	==Results==		==Results==