Language modeling using efficient best-first bottom-up parsing

Keith Hall; Mark Johnson

doi:10.1109/ASRU.2003.1318492

Language modeling using efficient best-first bottom-up parsing

Keith Hall, Mark Johnson

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

16 Citations (Scopus)

Abstract

In this paper we present a two-stage best-first bottom-up word-lattice parser which we use as a language model for speech recognition. The parser works by using a "Figure of Merit" that selects lattice paths while simultaneously selecting syntactic category edges for parsing. Additionally, we introduce a modified version of the Inside-Outside algorithm used as a pruning stage between syntactic context-free parsing and lexicalized context-dependent parsing. We report our results in terms of Word Error Rate on the HUB-1 word-lattices and compare these results to other syntactic language modeling techniques.

Original language	English
Title of host publication	2003 IEEE Workshop on Automatic Speech Recognition and Understanding
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	507-512
Number of pages	6
ISBN (Electronic)	0780379802, 9780780379800
DOIs	https://doi.org/10.1109/ASRU.2003.1318492
Publication status	Published - Dec 2003
Externally published	Yes
Event	IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003 - St. Thomas, United States Duration: 30 Nov 2003 → 4 Dec 2003

Other

Other	IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003
Country/Territory	United States
City	St. Thomas
Period	30/11/03 → 4/12/03

Access to Document

10.1109/ASRU.2003.1318492

Cite this

@inproceedings{3648c29d42aa421890323839a0361659,

title = "Language modeling using efficient best-first bottom-up parsing",

abstract = "In this paper we present a two-stage best-first bottom-up word-lattice parser which we use as a language model for speech recognition. The parser works by using a {"}Figure of Merit{"} that selects lattice paths while simultaneously selecting syntactic category edges for parsing. Additionally, we introduce a modified version of the Inside-Outside algorithm used as a pruning stage between syntactic context-free parsing and lexicalized context-dependent parsing. We report our results in terms of Word Error Rate on the HUB-1 word-lattices and compare these results to other syntactic language modeling techniques.",

author = "Keith Hall and Mark Johnson",

year = "2003",

month = dec,

doi = "10.1109/ASRU.2003.1318492",

language = "English",

pages = "507--512",

booktitle = "2003 IEEE Workshop on Automatic Speech Recognition and Understanding",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003 ; Conference date: 30-11-2003 Through 04-12-2003",

}

Hall, K & Johnson, M 2003, Language modeling using efficient best-first bottom-up parsing. in 2003 IEEE Workshop on Automatic Speech Recognition and Understanding., 1318492, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 507-512, IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003, St. Thomas, United States, 30/11/03. https://doi.org/10.1109/ASRU.2003.1318492

Language modeling using efficient best-first bottom-up parsing. / Hall, Keith; Johnson, Mark.
2003 IEEE Workshop on Automatic Speech Recognition and Understanding. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2003. p. 507-512 1318492.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Language modeling using efficient best-first bottom-up parsing

AU - Hall, Keith

AU - Johnson, Mark

PY - 2003/12

Y1 - 2003/12

N2 - In this paper we present a two-stage best-first bottom-up word-lattice parser which we use as a language model for speech recognition. The parser works by using a "Figure of Merit" that selects lattice paths while simultaneously selecting syntactic category edges for parsing. Additionally, we introduce a modified version of the Inside-Outside algorithm used as a pruning stage between syntactic context-free parsing and lexicalized context-dependent parsing. We report our results in terms of Word Error Rate on the HUB-1 word-lattices and compare these results to other syntactic language modeling techniques.

AB - In this paper we present a two-stage best-first bottom-up word-lattice parser which we use as a language model for speech recognition. The parser works by using a "Figure of Merit" that selects lattice paths while simultaneously selecting syntactic category edges for parsing. Additionally, we introduce a modified version of the Inside-Outside algorithm used as a pruning stage between syntactic context-free parsing and lexicalized context-dependent parsing. We report our results in terms of Word Error Rate on the HUB-1 word-lattices and compare these results to other syntactic language modeling techniques.

UR - http://www.scopus.com/inward/record.url?scp=84946708857&partnerID=8YFLogxK

U2 - 10.1109/ASRU.2003.1318492

DO - 10.1109/ASRU.2003.1318492

M3 - Conference proceeding contribution

AN - SCOPUS:84946708857

SP - 507

EP - 512

BT - 2003 IEEE Workshop on Automatic Speech Recognition and Understanding

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003

Y2 - 30 November 2003 through 4 December 2003

ER -

Language modeling using efficient best-first bottom-up parsing

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this