Predictability and Causality in Spanish and English Natural Language Generation

In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG sy...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org
Main Authors: Busto-Castiñeira, Andrea, González-Castaño, Francisco J, García-Méndez, Silvia, Francisco de Arriba-Pérez
Format: Paper
Language:English
Published: Ithaca Cornell University Library, arXiv.org 26.08.2024
Subjects:
ISSN:2331-8422
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models.
AbstractList In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models.
Author García-Méndez, Silvia
González-Castaño, Francisco J
Francisco de Arriba-Pérez
Busto-Castiñeira, Andrea
Author_xml – sequence: 1
  givenname: Andrea
  surname: Busto-Castiñeira
  fullname: Busto-Castiñeira, Andrea
– sequence: 2
  givenname: Francisco
  surname: González-Castaño
  middlename: J
  fullname: González-Castaño, Francisco J
– sequence: 3
  givenname: Silvia
  surname: García-Méndez
  fullname: García-Méndez, Silvia
– sequence: 4
  fullname: Francisco de Arriba-Pérez
BookMark eNotjV1LwzAYhYMoOOd-gHcFr1vTN0mTXsqYm1Cc4O7Hm-RtzSjp7Ifov3dOr85zeOCcG3YZu0iM3eU8k0Yp_oD9V_jMQHKT5RKMuGAzECJPjQS4ZothOHDOodCglJix7WtPPrgRbWjD-J1g9MkSpwHPLcTk7YgxDO9nsYpN-8svOE49tkmFsZmwoWRNkXocQxdv2VWN7UCL_5yz3dNqt9yk1Xb9vHysUlQAqQaJBRVYWOedrk0OdW2d9pa0htyT4KZ00hPw_CRL0FR7bq2vwZCzSos5u_-bPfbdx0TDuD90Ux9Pj3vBS10AcAniB_GYUyE
ContentType Paper
Copyright 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
DOI 10.48550/arxiv.2408.14283
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni Edition)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central Korea
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 2331-8422
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FG
ABJCF
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FRJ
HCIFZ
L6V
M7S
M~E
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
ID FETCH-LOGICAL-a522-724a6e6a6bcdc7f812ffbc7dbe7721de3089c4de201f81927efd0bbdf28ecb573
IEDL.DBID BENPR
IngestDate Mon Jun 30 09:17:46 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a522-724a6e6a6bcdc7f812ffbc7dbe7721de3089c4de201f81927efd0bbdf28ecb573
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
OpenAccessLink https://www.proquest.com/docview/3097622042?pq-origsite=%requestingapplication%
PQID 3097622042
PQPubID 2050157
ParticipantIDs proquest_journals_3097622042
PublicationCentury 2000
PublicationDate 20240826
PublicationDateYYYYMMDD 2024-08-26
PublicationDate_xml – month: 08
  year: 2024
  text: 20240826
  day: 26
PublicationDecade 2020
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2024
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 1.880542
SecondaryResourceType preprint
Snippet In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Context
English language
Entropy
Information theory
Language
Languages
Natural language
Speech recognition
Transformers
Title Predictability and Causality in Spanish and English Natural Language Generation
URI https://www.proquest.com/docview/3097622042
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagBYmJt3iUKgOr29Rx7HhCoioCCUJEO5SpOj8iuqQlaSv499huCgMSC6Plxbqz7z59d_4OoWtKCRcgYqwEKEwhklgSFmEgSlASxiRn2g-b4GmajMciqwm3qm6r3MREH6j1TDmOvBuFNnESYu_Yzfwdu6lRrrpaj9DYRk2nVEYbqHk7SLOXb5aFMG4xc7QuZ3rxri6UH9NVxyl7dbza2K8g7DPL3f5_z3SAmhnMTXmItkxxhHZ9R6eqjtFzVroazGKtw_0ZQKGDPiwrj7uDaREMbRyYVm9-o_7MG6TgZTiCx5rFDNaq1M55J2h0Nxj173E9PQGDxVSYEwrMMGBSacVzm8fzXCqupbF4uqdNFCZCUW0sAMidKBo3uQ6l1DlJjJIxj05Ro5gV5gwFkCgKVCrGqKAAsYxFLJOol3MNQmp-jlob80zqF1BNfmxz8ff2JdojFig4npawFmosyqW5QjtqtZhWZbt2aNv1ZA7tKnt4yl6_AMz8r-E
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V07T8MwED5BAcHEW7zxAGOgdRw7HhADD1FRSiU6wFSdHxFdAiRtgR_Ff8R2UxiQ2BiYLVk63_ne9x3AAWNUSJRJpCXqiGGsIkV5HCHVktF6QjNuwrIJ0W6n9_eyMwUfk1kY31Y50YlBUZsn7XPkx3HdGU5KnYydPr9EfmuUr65OVmiMxeLavr-6kK08aZ47_h5SennRPbuKqq0CETpfIxKUIbccudJGi8zZtyxTWhhlnZ_ZMDaup1IzY51hzDxYmLCZqStlMpparRIRu2unYcbRmKQ1mOk0bzoPX0kdyoVz0eNx9TRghR1j8dYfHXkgsaMAbvZD5wdDdrn4z55gyZGOz7ZYhimbr8Bc6FfV5SrcdgpfYRqMUcbfCeaGnOGwDFEF6efkzmm5fvkYDqpRZdLGADJCWlWOlowxt71orkH3L0hYh1r-lNsNIJhqhkxpzplkiIlKZKLSuJEJg1IZsQk7E270qv9d9r5ZsfX78T7MX3VvWr1Ws329DQvUuUQ-I035DtQGxdDuwqweDfplsVfJEoHeH7PuE0MSDKw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predictability+and+Causality+in+Spanish+and+English+Natural+Language+Generation&rft.jtitle=arXiv.org&rft.au=Busto-Casti%C3%B1eira%2C+Andrea&rft.au=Gonz%C3%A1lez-Casta%C3%B1o%2C+Francisco+J&rft.au=Garc%C3%ADa-M%C3%A9ndez%2C+Silvia&rft.au=Francisco+de+Arriba-P%C3%A9rez&rft.date=2024-08-26&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2408.14283