Breaking the Narrative: Scene Segmentation through Sequential Sentence Classification

Kurfalı, Murathan,1990-Stockholms universitet,Avdelningen för datorlingvistik,murathan.kurfali@ling.su.se (författare)

In this paper, we describe our submission to the Shared Task on Scene Segmentation (STSS). The shared task requires participants to segment novels into coherent segments, called scenes. We approach this as a sequential sentence classification task and offer a BERT-based solution with a weighted cross-entropy loss. According to the results, the proposed approach performs relatively well on the task as our model ranks first and second, in official in-domain and out-domain evaluations, respectively. However, the overall low performances (0.37 F1-score) suggest that there is still much room for improvement.

Wirén, Mats,1954-Stockholms universitet,Avdelningen för datorlingvistik,Albin Zehe, Leonard Konle, Lea Dümpelmann, Evelyn Gius, Svenja Guhr, Andreas Hotho, Fotis Jannidis, Lucas Kaufmann, Markus Krug, Frank Puppe, Nils Reiter, Annekea Schreiber(Swepub:su)mwir (författare)
Stockholms universitetAvdelningen för datorlingvistik (creator_code:org_t)

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.