Funkquist, Martin ; Kuznetsov, Ilia ; Hou, Yufang ; Gurevych, Iryna (2024)
CiteBench: A Benchmark for Scientific Citation Text Generation.
The 2023 Conference on Empirical Methods in Natural Language Processing. Singapore (06.-10.12.2023)
doi: 10.26083/tuprints-00027660
Konferenzveröffentlichung, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Funkquist, Martin ; Kuznetsov, Ilia ; Hou, Yufang ; Gurevych, Iryna |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | CiteBench: A Benchmark for Scientific Citation Text Generation |
| Sprache: | Englisch |
| Publikationsjahr: | 8 Juli 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2023 |
| Ort der Erstveröffentlichung: | Kerrville, TX, USA |
| Verlag: | ACL |
| Buchtitel: | Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing |
| Veranstaltungstitel: | The 2023 Conference on Empirical Methods in Natural Language Processing |
| Veranstaltungsort: | Singapore |
| Veranstaltungsdatum: | 06.-10.12.2023 |
| DOI: | 10.26083/tuprints-00027660 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/27660 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench. |
| ID-Nummer: | 2023.emnlp-main.455 |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-276602 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 08 Jul 2024 09:31 |
| Letzte Änderung: | 09 Jul 2024 09:29 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- CiteBench: A Benchmark for Scientific Citation Text Generation. (deposited 08 Jul 2024 09:31) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum