Accepted author manuscript, 29.8 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - A sequence labelling approach for automatic analysis of ello
T2 - Tagging pronouns, antecedents, and connective phrases
AU - Parodi, Giovanni
AU - Evans, Richard
AU - Ha, Le An
AU - Mitkov, Ruslan
AU - Vergara, Cristóbal Jesus Julio
AU - Olivares-López , Raúl Ignacio
PY - 2022/3/31
Y1 - 2022/3/31
N2 - Encapsulators are linguistic units which which establish coherent links to preceding text units. In this paper, we address the challenge of automatically analysing the pronoun ello in Spanish text. Our method identifies, for each occurrence, the antecedent of the pronoun, the connective phrase which links ello to its antecedent, the semantic relation holding between the two, and... We describe our annotation of a corpus to inform the development of our method and to finetune an automatic analyser based on bidirectional encoder representation transformers (BERT). On testing our method, we find that it performs with greater accuracy than two baselines (0.76 for the resolution task), and sets a promising benchmark for the automatic annotation of occurrences of the pronoun ello, their antecedents, and the semantic relations holding between these encapsulators and their antecedents .
AB - Encapsulators are linguistic units which which establish coherent links to preceding text units. In this paper, we address the challenge of automatically analysing the pronoun ello in Spanish text. Our method identifies, for each occurrence, the antecedent of the pronoun, the connective phrase which links ello to its antecedent, the semantic relation holding between the two, and... We describe our annotation of a corpus to inform the development of our method and to finetune an automatic analyser based on bidirectional encoder representation transformers (BERT). On testing our method, we find that it performs with greater accuracy than two baselines (0.76 for the resolution task), and sets a promising benchmark for the automatic annotation of occurrences of the pronoun ello, their antecedents, and the semantic relations holding between these encapsulators and their antecedents .
U2 - 10.1007/s10579-021-09559-z
DO - 10.1007/s10579-021-09559-z
M3 - Journal article
VL - 56
SP - 139
EP - 164
JO - Language Resources and Evaluation
JF - Language Resources and Evaluation
SN - 1574-020X
ER -