Story embedding: Learning distributed representations of stories based on character networks

Lee, O-Joun; Jung, Jason J.

doi:10.1016/j.artint.2020.103235

Cited by 20 publications

(47 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing methods cannot consider the structures. Regarding their reasonable accuracy shown in the previous studies [12], this problem may not be severe in representing stories in a single narrative work. However, there are various narrative multimedia distributed as series (e.g., Webtoons [14], Web novels, TV series, etc.…”

Section: Introductionmentioning

confidence: 77%

“…However, according to the proximity intensity, relationships between characters can have totally different meanings. Thus, in our previous study [12], we have modified the WL relabeling process to consider proximity between characters. This modification is called as 'the proximity-aware WL relabeling process' and described in Figure 1.…”

Section: Background and Preliminariesmentioning

confidence: 99%

“…To resolve these problems, our previous studies [12,13] conducted unsupervised representation learning for structures of the character network. Lee and Jung [12] have proposed three models-Story2Vec-F (Flow-oriented Story2Vec), Story2Vec-D (Denouement-oriented Story2Vec), and Story2Vec-U (Unified Story2Vec). First, they embed snapshots of the social relationships of each character at each moment (Role2Vec).…”

Section: Introductionmentioning

confidence: 99%

“…The previous studies [12,13] directly jumped up form the social roles to stories. However, between the social role and the story, there is a significant conceptual gap.…”

Section: Introductionmentioning

confidence: 99%

“…To verify the effectiveness of the hierarchical representation learning for the story, we conducted learning representations of characters, scenes, and stories in 142 real movies, as with our previous study [12]. Character vectors, scene vectors, and story vectors were evaluated by measuring the similarity between the characters, between the scenes, and between the stories, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning Hierarchical Representations of Stories by Using Multi-Layered Structures in Narrative Multimedia

Lee

Jung

Kim

2020

Sensors

Self Cite

View full text Add to dashboard Cite

Narrative works (e.g., novels and movies) consist of various utterances (e.g., scenes and episodes) with multi-layered structures. However, the existing studies aimed to embed only stories in a narrative work. By covering other granularity levels, we can easily compare narrative utterances that are coarser (e.g., movie series) or finer (e.g., scenes) than a narrative work. We apply the multi-layered structures on learning hierarchical representations of the narrative utterances. To represent coarser utterances, we consider adjacency and appearance of finer utterances in the coarser ones. For the movies, we suppose a four-layered structure (character roles ∈ characters ∈ scenes ∈ movies) and propose three learning methods bridging the layers: Char2Vec, Scene2Vec, and Hierarchical Story2Vec. Char2Vec represents a character by using dynamic changes in the character’s roles. To find the character roles, we use substructures of character networks (i.e., dynamic social networks of characters). A scene describes an event. Interactions between characters in the scene are designed to describe the event. Scene2Vec learns representations of a scene from interactions between characters in the scene. A story is a series of events. Meanings of the story are affected by order of the events as well as their content. Hierarchical Story2Vec uses sequential order of scenes to represent stories. The proposed model has been evaluated by estimating the similarity between narrative utterances in real movies.

show abstract

Section: Introductionmentioning

confidence: 77%

Section: Background and Preliminariesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The previous studies [12,13] directly jumped up form the social roles to stories. However, between the social role and the story, there is a significant conceptual gap.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations