Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AVVYBGBAQ" target="_blank" >RIV/00216208:11320/25:VVYBGBAQ - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85199101252&doi=10.1162%2fcoli_a_00519&partnerID=40&md5=51a4fc7a5078fdb617f4542610a2b591" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85199101252&doi=10.1162%2fcoli_a_00519&partnerID=40&md5=51a4fc7a5078fdb617f4542610a2b591</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1162/coli_a_00519" target="_blank" >10.1162/coli_a_00519</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation

Popis výsledku v původním jazyce

While summarization has been extensively researched in natural language processing (NLP), cross-lingual cross-temporal summarization (CLCTS) is a largely unexplored area that has the potential to improve cross-cultural accessibility and understanding. This article comprehensively addresses the CLCTS task, including dataset creation, modeling, and evaluation. We (1) build the first CLCTS corpus with 328 instances for hDe-En (extended version with 455 instances) and 289 for hEn-De (extended version with 501 instances), leveraging historical fiction texts and Wikipedia summaries in English and German; (2) examine the effectiveness of popular transformer end-to-end models with different intermediate fine-tuning tasks; (3) explore the potential of GPT-3.5 as a summarizer; and (4) report evaluations from humans, GPT-4, and several recent automatic evaluation metrics. Our results indicate that intermediate task finetuned end-to-end models generate bad to moderate quality summaries while GPT-3.5, as a zero-shot summarizer, provides moderate to good quality outputs. GPT-3.5 also seems very adept at normalizing historical text. To assess data contamination in GPT-3.5, we design an adversarial attack scheme in which we find that GPT-3.5 performs slightly worse for unseen source documents compared to seen documents. Moreover, it sometimes hallucinates when the source sentences are inverted against its prior knowledge with a summarization accuracy of 0.67 for plot omission, 0.71 for entity swap, and 0.53 for plot negation. Overall, our regression results of model performances suggest that longer, older, and more complex source texts (all of which are more characteristic for historical language variants) are harder to summarize for all models, indicating the difficulty of the CLCTS task. Regarding evaluation, we observe that both the GPT-4 and BERTScore correlate moderately with human evaluations, implicating great potential for future improvement. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation

Popis výsledku anglicky

While summarization has been extensively researched in natural language processing (NLP), cross-lingual cross-temporal summarization (CLCTS) is a largely unexplored area that has the potential to improve cross-cultural accessibility and understanding. This article comprehensively addresses the CLCTS task, including dataset creation, modeling, and evaluation. We (1) build the first CLCTS corpus with 328 instances for hDe-En (extended version with 455 instances) and 289 for hEn-De (extended version with 501 instances), leveraging historical fiction texts and Wikipedia summaries in English and German; (2) examine the effectiveness of popular transformer end-to-end models with different intermediate fine-tuning tasks; (3) explore the potential of GPT-3.5 as a summarizer; and (4) report evaluations from humans, GPT-4, and several recent automatic evaluation metrics. Our results indicate that intermediate task finetuned end-to-end models generate bad to moderate quality summaries while GPT-3.5, as a zero-shot summarizer, provides moderate to good quality outputs. GPT-3.5 also seems very adept at normalizing historical text. To assess data contamination in GPT-3.5, we design an adversarial attack scheme in which we find that GPT-3.5 performs slightly worse for unseen source documents compared to seen documents. Moreover, it sometimes hallucinates when the source sentences are inverted against its prior knowledge with a summarization accuracy of 0.67 for plot omission, 0.71 for entity swap, and 0.53 for plot negation. Overall, our regression results of model performances suggest that longer, older, and more complex source texts (all of which are more characteristic for historical language variants) are harder to summarize for all models, indicating the difficulty of the CLCTS task. Regarding evaluation, we observe that both the GPT-4 and BERTScore correlate moderately with human evaluations, implicating great potential for future improvement. © 2024 Association for Computational Linguistics.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computational Linguistics

ISSN

0891-2017

e-ISSN

—

Svazek periodika

50

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

47

Strana od-do

1001-1047

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85199101252