"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding

  title={"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding},
  author={Faeze Brahman and Meng Huang and Oyvind Tafjord and Chao Zhao and Mrinmaya Sachan and Snigdha Chaturvedi},
When reading a literary piece, readers often make inferences about various characters’ roles, personalities, relationships, intents, actions, etc. While humans can readily draw upon their past experiences to build such a character-centric view of the narrative, understanding characters in narratives can be a chal-lenging task for machines. To encourage research in this field of character-centric narrative understanding, we present LiSCU – a new dataset of literary pieces and their summaries… 
TVShowGuess: Character Comprehension in Stories as Speaker Guessing
A new task for assessing machines’ skills of understanding fictional characters in narrative stories, TVShowGuess, takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues, and proposes new model architectures to support the contextualized encoding of long scene texts.
Persona-Guided Planning for Controlling the Protagonist’s Persona in Story Generation
This paper proposes a planning-based generation model named ConPer to explicitly model the relationship between personas and events, and demonstrates that ConPer outperforms state-of-the-art baselines for generating more coherent and persona-controllable stories.
Learning and Evaluating Character Representations in Novels
This work proposes two novel methods for representing characters: graph neural network-based embeddings from a full corpus-based character network; and low-dimensional embeddeddings constructed from the occurrence pattern of characters in each novel.
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, it is shown that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions, and the dataset supports question generation (QG) task in the education domain.
Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
A video-language story dataset, Synopses of Movie Narratives (SYMON), containing 5,193 video summaries of popular movies and TV series, which has higher story coverage and more frequent mental-state references than similar videolanguage story datasets.


Generating Character Descriptions for Automatic Summarization of Fiction
This work collects a dataset of one million fiction stories with accompanying author-written summaries from Wattpad, an online story sharing platform, and proposes two approaches to generate character descriptions, one based on ranking attributes found in the story text, the other based on classifying into a list of pre-defined attributes.
Inferring Interpersonal Relations in Narrative Summaries
This work addresses the problem of inferring the polarity of relationships between people in narrative summaries as a joint structured prediction for each narrative, and presents a general model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text.
Unsupervised Learning of Evolving Relationships Between Literary Characters
This paper model relationships as dynamic phenomenon, represented as evolving sequences of latent states empirically learned from data, which enables data-driven inference of inter-character relationship types beyond simple sentiment polarities, by incorporating lexical and semantic representations, and leveraging large quantities of raw text.
Automatically Producing Plot Unit Representations for Narrative Text
This research explores whether current NLP technology can be used to automatically produce plot unit representations for narrative text by creating a system called AESOP, which exploits a variety of existing resources to identify affect states and applies "projection rules" to map the affect states onto the characters in a story.
Plot Induction and Evolutionary Search for Story Generation
A story generator that leverages knowledge inherent in corpora without requiring extensive manual involvement is developed, and it is shown that this system outperforms previous data-driven approaches.
Unsupervised Learning of Narrative Event Chains
A three step process to learning narrative event chains using unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments and introduces two evaluations: the narrative cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order.
Extracting Social Networks from Literary Fiction
The method involves character name chunking, quoted speech attribution and conversation detection given the set of quotes, which provides evidence that the majority of novels in this time period do not fit two characterizations provided by literacy scholars.
Learning Personas from Dialogue with Attentive Memory Networks
Neural models to learn persona embeddings in a supervised character trope classification task are introduced and the use of short conversational text as input, and the ability to learn from prior knowledge using memory, suggests these methods could be applied to other domains.
Exploring Content Selection in Summarization of Novel Chapters
A new metric for aligning reference summary sentences with chapter sentences to create gold extracts is presented and significant improvement over prior alignment approaches for this task is demonstrated through automatic metrics and a crowd-sourced pyramid analysis.
Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
This paper formalizes it as a new task and describes the annotation of a corpus, based on fan-fiction short stories, and provides results using several approaches previously proposed for relation identification with neural methods.