D3.8 Lexical-semantic analytics for NLP

Federico Martelli; Marco Maru; Cesare Campagnano; Roberto Navigli; Paola Velardi; Rafael-J. Ureña-Ruiz; Francesca Frontini; Valeria Quochi; Jelena Kallas; Kristina Koppel; Margit Langemets; Jesse de Does; Rob Tempelaars; Carole Tiberius; Rute Costa; Ana Salgado; Sanni Nimb; Sussi Olsen; Simon Krek; Jaka Čibej; Kaja Dobrovoljc; Polona Gantar; Tina Munda

D3.8 Lexical-semantic analytics for NLP

Federico Martelli, Marco Maru, Cesare Campagnano, Roberto Navigli, Paola Velardi , Rafael-J. Ureña-Ruiz, Francesca Frontini, Valeria Quochi, Jelena Kallas, Kristina Koppel, Margit Langemets, Jesse de Does, Rob Tempelaars, Carole Tiberius, Rute Costa, Ana Salgado, Sanni Nimb, Sussi Olsen, Simon Krek, Jaka ČibejKaja Dobrovoljc, Polona Gantar, Tina Munda

Research output: Book/Report › Commissioned report › peer-review

80 Downloads (Pure)

Abstract

The present document illustrates the work carried out in task 3.3 (work package 3) of ELEXIS project focused on lexical-semantic analytics for Natural Language Processing (NLP). This task aims at computing analytics for lexical-semantic information such as words, senses and domains in the available resources, investigating their role in NLP applications.
Specifically, this task concentrates on three research directions, namely i) sense clustering, in which grouping senses based on their semantic similarity improves the performance of NLP tasks such as Word Sense Disambiguation (WSD), ii) domain labeling of text, in which the lexicographic resources made available by the ELEXIS project for research purposes allow better performances to be achieved, and finally iii) analysing the diachronic distribution of senses, for which a software package is made available.

Original language	English
Publisher	ELEXIS - European Lexicographic Infrastructure
Commissioning body	European Union
Number of pages	67
Publication status	Published - 2022

Access to Document

ELEXIS_D3_8_Lexical-Semantic_Analytics_for_NLP_final_reportFinal published version, 1.31 MBLicence: Unspecified

Cite this

@book{bc7ac16e57fe419bad57024a331bbb7f,

title = "D3.8 Lexical-semantic analytics for NLP",

abstract = "The present document illustrates the work carried out in task 3.3 (work package 3) of ELEXIS project focused on lexical-semantic analytics for Natural Language Processing (NLP). This task aims at computing analytics for lexical-semantic information such as words, senses and domains in the available resources, investigating their role in NLP applications.Specifically, this task concentrates on three research directions, namely i) sense clustering, in which grouping senses based on their semantic similarity improves the performance of NLP tasks such as Word Sense Disambiguation (WSD), ii) domain labeling of text, in which the lexicographic resources made available by the ELEXIS project for research purposes allow better performances to be achieved, and finally iii) analysing the diachronic distribution of senses, for which a software package is made available.",

author = "Federico Martelli and Marco Maru and Cesare Campagnano and Roberto Navigli and Paola Velardi and Rafael-J. Ure{\~n}a-Ruiz and Francesca Frontini and Valeria Quochi and Jelena Kallas and Kristina Koppel and Margit Langemets and {de Does}, Jesse and Rob Tempelaars and Carole Tiberius and Rute Costa and Ana Salgado and Sanni Nimb and Sussi Olsen and Simon Krek and Jaka {\v C}ibej and Kaja Dobrovoljc and Polona Gantar and Tina Munda",

note = "info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F03213%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F03213%2F2020/PT# UIDB/03213/2020 UIDP/03213/2020",

year = "2022",

language = "English",

publisher = "ELEXIS - European Lexicographic Infrastructure",

}

Martelli, F, Maru, M, Campagnano, C, Navigli, R, Velardi , P, Ureña-Ruiz, R-J, Frontini, F, Quochi, V, Kallas, J, Koppel, K, Langemets, M, de Does, J, Tempelaars, R, Tiberius, C, Costa, R , Salgado, A, Nimb, S, Olsen, S, Krek, S, Čibej, J, Dobrovoljc, K, Gantar, P & Munda, T 2022, D3.8 Lexical-semantic analytics for NLP. ELEXIS - European Lexicographic Infrastructure.

TY - BOOK

T1 - D3.8 Lexical-semantic analytics for NLP

AU - Martelli, Federico

AU - Maru, Marco

AU - Campagnano, Cesare

AU - Navigli, Roberto

AU - Velardi , Paola

AU - Ureña-Ruiz, Rafael-J.

AU - Frontini, Francesca

AU - Quochi, Valeria

AU - Kallas, Jelena

AU - Koppel, Kristina

AU - Langemets, Margit

AU - de Does, Jesse

AU - Tempelaars, Rob

AU - Tiberius, Carole

AU - Costa, Rute

AU - Salgado, Ana

AU - Nimb, Sanni

AU - Olsen, Sussi

AU - Krek, Simon

AU - Čibej, Jaka

AU - Dobrovoljc, Kaja

AU - Gantar, Polona

AU - Munda, Tina

N1 - info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F03213%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F03213%2F2020/PT# UIDB/03213/2020 UIDP/03213/2020

PY - 2022

Y1 - 2022

N2 - The present document illustrates the work carried out in task 3.3 (work package 3) of ELEXIS project focused on lexical-semantic analytics for Natural Language Processing (NLP). This task aims at computing analytics for lexical-semantic information such as words, senses and domains in the available resources, investigating their role in NLP applications.Specifically, this task concentrates on three research directions, namely i) sense clustering, in which grouping senses based on their semantic similarity improves the performance of NLP tasks such as Word Sense Disambiguation (WSD), ii) domain labeling of text, in which the lexicographic resources made available by the ELEXIS project for research purposes allow better performances to be achieved, and finally iii) analysing the diachronic distribution of senses, for which a software package is made available.

AB - The present document illustrates the work carried out in task 3.3 (work package 3) of ELEXIS project focused on lexical-semantic analytics for Natural Language Processing (NLP). This task aims at computing analytics for lexical-semantic information such as words, senses and domains in the available resources, investigating their role in NLP applications.Specifically, this task concentrates on three research directions, namely i) sense clustering, in which grouping senses based on their semantic similarity improves the performance of NLP tasks such as Word Sense Disambiguation (WSD), ii) domain labeling of text, in which the lexicographic resources made available by the ELEXIS project for research purposes allow better performances to be achieved, and finally iii) analysing the diachronic distribution of senses, for which a software package is made available.

M3 - Commissioned report

BT - D3.8 Lexical-semantic analytics for NLP

PB - ELEXIS - European Lexicographic Infrastructure

ER -

D3.8 Lexical-semantic analytics for NLP

Abstract

Access to Document

Fingerprint

Cite this