HFST Training Environment and Recent Additions

Erik Axelson; Sam Hardwick; Krister Linden

HFST Training Environment and Recent Additions

Erik Axelson, Sam Hardwick, Krister Linden

Avdelningen för digital humaniora

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Kapitel › Vetenskaplig › Peer review

Sammanfattning

HFST - the Helsinki Finite-State Technology toolkit was launched in 2009 (Lindén & al, 2009) and has since been used for developing a number of rule-based morphologies for processing natural language. To promote the uptake of the toolkit a training environment for linguists to learn how to use HFST has been designed in Jupyter. This paper presents an overview of the training environment and some of the recent features that have been added to HFST to keep the run-time size of the transducer reasonably small despite exceptions and negative constraints that need to be added during practical FST development.

Originalspråk	engelska
Titel på värdpublikation	Rule-Based Language Technology
Redaktörer	Arvi Hurskainen, Kimmo Koskenniemi, Tommi Pirinen
Antal sidor	10
Utgivningsort	Tartu
Förlag	Northern European Association for Language Technology
Utgivningsdatum	2023
Sidor	60-69
Status	Publicerad - 2023
MoE-publikationstyp	A3 Del av bok eller annan forskningsbok

Publikationsserier

Namn	NEALT Monograph Series
Förlag	Northern European Association for Language Technology (NEALT)
Nummer	2[1]
ISSN (elektroniskt)	1736-6291

Vetenskapsgrenar

6121 Språkvetenskaper
113 Data- och informationsvetenskap

Åtkomst av dokument

5-RBLT-HFST-updatesSlutlig publicerad version, 590 KBLicens: !!Unspecified

Andra filer och länkar

http://hdl.handle.net/10062/89595

CLARIN - Finländska språkresurser i gemensamt bruk
Linden, K. (Chef)
Avdelningen för digital humaniora
Utrustning/facilitet: Coordination office

Citera det här

@inbook{e176ae32550a4c6eaf7f8154c2a7ba3a,

title = "HFST Training Environment and Recent Additions",

abstract = "HFST - the Helsinki Finite-State Technology toolkit was launched in 2009 (Lind{\'e}n & al, 2009) and has since been used for developing a number of rule-based morphologies for processing natural language. To promote the uptake of the toolkit a training environment for linguists to learn how to use HFST has been designed in Jupyter. This paper presents an overview of the training environment and some of the recent features that have been added to HFST to keep the run-time size of the transducer reasonably small despite exceptions and negative constraints that need to be added during practical FST development.",

keywords = "6121 Languages, 113 Computer and information sciences",

author = "Erik Axelson and Sam Hardwick and Krister Linden",

year = "2023",

language = "English",

series = "NEALT Monograph Series",

publisher = "Northern European Association for Language Technology ",

number = "2[1]",

pages = "60--69",

editor = "Arvi Hurskainen and Kimmo Koskenniemi and {Tommi Pirinen}",

booktitle = "Rule-Based Language Technology",

address = "Estonia",

}

HFST Training Environment and Recent Additions. / Axelson, Erik; Hardwick, Sam; Linden, Krister.
Rule-Based Language Technology. red. / Arvi Hurskainen; Kimmo Koskenniemi; Tommi Pirinen. Tartu: Northern European Association for Language Technology , 2023. s. 60-69 (NEALT Monograph Series; Nr. 2[1]).

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Kapitel › Vetenskaplig › Peer review

TY - CHAP

T1 - HFST Training Environment and Recent Additions

AU - Axelson, Erik

AU - Hardwick, Sam

AU - Linden, Krister

PY - 2023

Y1 - 2023

N2 - HFST - the Helsinki Finite-State Technology toolkit was launched in 2009 (Lindén & al, 2009) and has since been used for developing a number of rule-based morphologies for processing natural language. To promote the uptake of the toolkit a training environment for linguists to learn how to use HFST has been designed in Jupyter. This paper presents an overview of the training environment and some of the recent features that have been added to HFST to keep the run-time size of the transducer reasonably small despite exceptions and negative constraints that need to be added during practical FST development.

AB - HFST - the Helsinki Finite-State Technology toolkit was launched in 2009 (Lindén & al, 2009) and has since been used for developing a number of rule-based morphologies for processing natural language. To promote the uptake of the toolkit a training environment for linguists to learn how to use HFST has been designed in Jupyter. This paper presents an overview of the training environment and some of the recent features that have been added to HFST to keep the run-time size of the transducer reasonably small despite exceptions and negative constraints that need to be added during practical FST development.

KW - 6121 Languages

KW - 113 Computer and information sciences

UR - http://hdl.handle.net/10062/89595

M3 - Chapter

T3 - NEALT Monograph Series

SP - 60

EP - 69

BT - Rule-Based Language Technology

A2 - Hurskainen, Arvi

A2 - Koskenniemi, Kimmo

A2 - , Tommi Pirinen

PB - Northern European Association for Language Technology

CY - Tartu

ER -

HFST Training Environment and Recent Additions

Sammanfattning

Publikationsserier

Vetenskapsgrenar

Åtkomst av dokument

Andra filer och länkar

Utrustning

CLARIN - Finländska språkresurser i gemensamt bruk

Citera det här