(Enter summary)
Abstract: This paper presents a method for inducing the parts of speech of a language and part-of-speech labels for individual words from a large text corpus. Vector representations for the part-of-speech of a word are formed from entries of its near lexical neighbors. A dimensionality reduction creates a space representing the syntactic categories of unambiguous words. A neural net trained on these spatial representations classifies individual contexts of occurrence of ambiguous words. The method... (Update)
Context of citations to this paper: More
.... 84, 18] and Brill [15, 16] There have also been efforts at learning parts of speech from word distributions, with application to tagging [76, 77]. Taggers are currently wide spread and readily available. Those available for free include an HMM tagger implemented at Xerox [23]...
.... in which contexts (where context includes morphological features e.g. Resnik [135] as well as syntactic ones e.g. Schutze [143]) Some psychologists crtitcise this approach whenever it is proposed as a potential model for child language acquisition, but it does...
Cited by: More
Customizing a Lexicon to Better Suit a Computational Task - Hearst, Schütze (1996)
(Correct)
Part-of-Speech Tagging and Partial Parsing - Abney (1996)
(Correct)
Statistical Language Processing based on Self-Organising Word.. - McMahon (1994)
(Correct)
Similar documents based on text: More All
0.2: Using SQL with Prolog to improve performance with large databases - Boone (1999)
(Correct)
0.2: Word Space - Schütze (1993)
(Correct)
0.2: Dimensions of Meaning - Schütze (1992)
(Correct)
Related documents from co-citation: More All
8: A tree-based statistical language model for natural language speech recognition (context) - Bahl, Brown et al. - 1989
7: Finding Structure in Language (context) - Finch - 1993
7: gram models of natural language (context) - Brown, n- - 1992
BibTeX entry: (Update)
Hinrich Sch¨utze. Part-of-speech induction from scratch. In Proceedings of ACL 31, Ohio State University, 1993. http://citeseer.ist.psu.edu/575905.html More
@inproceedings{ schutze93partspeech,
author = "H. Sch{\"u}tze",
title = "Part-of-speech induction from scratch",
booktitle = "Proceedings of ACL 31, Ohio State University",
year = "1993",
url = "citeseer.ist.psu.edu/575905.html" }
Citations not processed or no citations identified.
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://acl.ldc.upenn.edu/P/P93/): More
Towards The Automatic Identification Of Adjectival.. - Vasileios.. (1993)
(Correct)
On The Decidability Of Functional Uncertainty - Backofen (1993)
(Correct)
Integrating Word Boundary Identification With Sentence Understanding - Gan
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC