%0 Journal Article %1 arnold2023novel %A Arnold, Frederik %A Jäschke, Robert %D 2023 %J Journal of Computational Literary Studies %K 2023 citation dh digital humanities identification jcls myown nlp reuse text %N 1 %R doi.org/10.48694/jcls.3590 %T A Novel Approach for Identification and Linking of Short Quotations in Scholarly Texts and Literary Works %U https://jcls.io/article/id/3590/ %V 2 %X We present two approaches for the identification and linking of short quotations between scholarly works and literary works: ProQuo, a specialized pipeline, and ProQuoLM, a more general language model based approach. Our evaluation shows that both approaches outperform a strong baseline and the overall performance is on the same level. We compare the performance of ProQuoLM on texts with and without (page) reference information and find that reference information is not used. Based on our findings, we propose the following steps for future improvements: further analysis of the influence of a bigger context window for better handling of long distance references and the introduction of positional information of the literary work so that reference information can be utilized by ProQuoLM.

@article{arnold2023novel, abstract = {We present two approaches for the identification and linking of short quotations between scholarly works and literary works: ProQuo, a specialized pipeline, and ProQuoLM, a more general language model based approach. Our evaluation shows that both approaches outperform a strong baseline and the overall performance is on the same level. We compare the performance of ProQuoLM on texts with and without (page) reference information and find that reference information is not used. Based on our findings, we propose the following steps for future improvements: further analysis of the influence of a bigger context window for better handling of long distance references and the introduction of positional information of the literary work so that reference information can be utilized by ProQuoLM.}, added-at = {2023-05-11T15:20:49.000+0200}, author = {Arnold, Frederik and Jäschke, Robert}, biburl = {https://www.bibsonomy.org/bibtex/2fea74547303796a9daab2cd03aceeb72/jaeschke}, doi = {doi.org/10.48694/jcls.3590}, interhash = {447c9da56bc53fe1bcf056683dad5166}, intrahash = {fea74547303796a9daab2cd03aceeb72}, journal = {Journal of Computational Literary Studies}, keywords = {2023 citation dh digital humanities identification jcls myown nlp reuse text}, number = 1, timestamp = {2024-02-02T10:57:27.000+0100}, title = {A Novel Approach for Identification and Linking of Short Quotations in Scholarly Texts and Literary Works}, url = {https://jcls.io/article/id/3590/}, volume = 2, year = 2023 }