%0 Conference Paper %1 ponvert2011 %A Ponvert, Elias %A Baldridge, Jason %A Erk, Katrin %B Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1 %C Stroudsburg, PA, USA %D 2011 %I Association for Computational Linguistics %K automaton cascade parsing unsupervised %P 1077--1086 %T Simple unsupervised grammar induction from raw text with cascaded finite state models %U http://dl.acm.org/citation.cfm?id=2002472.2002608 %X We consider a new subproblem of unsupervised parsing from raw text, unsupervised partial parsing---the unsupervised version of text chunking. We show that addressing this task directly, using probabilistic finite-state methods, produces better results than relying on the local predictions of a current best unsupervised parser, Seginer's (2007) CCL. These finite-state models are combined in a cascade to produce more general (full-sentence) constituent structures; doing so outperforms CCL by a wide margin in unlabeled PARSEVAL scores for English, German and Chinese. Finally, we address the use of phrasal punctuation as a heuristic indicator of phrasal boundaries, both in our system and in CCL. %@ 978-1-932432-87-9

@inproceedings{ponvert2011, abstract = {We consider a new subproblem of unsupervised parsing from raw text, unsupervised partial parsing---the unsupervised version of text chunking. We show that addressing this task directly, using probabilistic finite-state methods, produces better results than relying on the local predictions of a current best unsupervised parser, Seginer's (2007) CCL. These finite-state models are combined in a cascade to produce more general (full-sentence) constituent structures; doing so outperforms CCL by a wide margin in unlabeled PARSEVAL scores for English, German and Chinese. Finally, we address the use of phrasal punctuation as a heuristic indicator of phrasal boundaries, both in our system and in CCL.}, acmid = {2002608}, added-at = {2012-11-08T17:59:53.000+0100}, address = {Stroudsburg, PA, USA}, author = {Ponvert, Elias and Baldridge, Jason and Erk, Katrin}, biburl = {https://www.bibsonomy.org/bibtex/2ea0db6f32cded6cc5a59b1413f2be252/jil}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1}, description = {Simple unsupervised grammar induction from raw text with cascaded finite state models}, interhash = {0d8f375024d4c2f8f4e908127f98457f}, intrahash = {ea0db6f32cded6cc5a59b1413f2be252}, isbn = {978-1-932432-87-9}, keywords = {automaton cascade parsing unsupervised}, location = {Portland, Oregon}, numpages = {10}, pages = {1077--1086}, publisher = {Association for Computational Linguistics}, series = {HLT '11}, timestamp = {2013-11-23T20:11:51.000+0100}, title = {Simple unsupervised grammar induction from raw text with cascaded finite state models}, url = {http://dl.acm.org/citation.cfm?id=2002472.2002608}, year = 2011 }