A Character-Centric Neural Model for Automated Story Generation

Liu, Danyang; Li, Juntao; Yu, Meng-Hsuan; Huang, Ziming; Liu, Gongshen; Zhao, Dongyan; Yan, Rui

doi:10.1609/aaai.v34i02.5536

Cited by 22 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been other datasets built from TV shows, such as summarizing TV show character descriptions (Shi et al, 2021), constructing knowledge bases , summarizing TV show screenplays (Chen et al, 2021), entity tracking (Chen and Choi, 2016;Choi and Chen, 2018), coreference resolution (Chen et al, 2017;Zhou and Choi, 2018), question answering (Ma et al, 2018;Yang and Choi, 2019), speaker identification (Ma et al, 2017), sarcasm detection (Joshi et al, 2016), emotion detection (Zahiri and Choi, 2017;Hsu and Ku, 2018), and character relation extraction (Yu et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

TVRecap: A Dataset for Generating Stories with Character Descriptions

Chen¹,

Gimpel²

2021

Preprint

View full text Add to dashboard Cite

We introduce TVRECAP, a story generation dataset that requires generating detailed TV show episode recaps from a brief summary and a set of documents describing the characters involved. Unlike other story generation datasets, TVRECAP contains stories that are authored by professional screenwriters and that feature complex interactions among multiple characters. Generating stories in TVRECAP requires drawing relevant information from the lengthy provided documents about characters based on the brief summary. In addition, by swapping the input and output, TVRECAP can serve as a challenging testbed for abstractive summarization. We create TVRECAP from fancontributed websites, which allows us to collect 26k episode recaps with 1868.7 tokens on average. Empirically, we take a hierarchical story generation approach and find that the neural model that uses oracle content selectors for character descriptions demonstrates the best performance on automatic metrics, showing the potential of our dataset to inspire future research on story generation with constraints. Qualitative analysis shows that the best-performing model sometimes generates content that is unfaithful to the short summaries, suggesting promising directions for future work. 1

show abstract

Section: Related Workmentioning

confidence: 99%

TVRecap: A Dataset for Generating Stories with Character Descriptions

Chen¹,

Gimpel²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Prior work on story generation has largely focused on plot outline via keywords or key phrases (Yao et al, 2019;Xu et al, 2018), event-based representations Fan et al, 2019), or a sentence theme (Chen et al, 2019). Liu et al (2020) propose a method to generate a story conditioned on a character description. Prior work on narrative text generation with plans has mostly relied on external resources or tools to extract outlines (Zhou et al, 2018;Fan et al, 2019), and then training in a supervised manner.…”

Section: Related Workmentioning

confidence: 99%

Narrative Text Generation with a Latent Discrete Plan

Jhamtani

Berg-Kirkpatrick

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the desired type of plan, and then train generation models in a supervised fashion. In this paper, we propose a deep latent variable model that first samples a sequence of anchor words, one per sentence in the story, as part of its generative process. During training, our model treats the sequence of anchor words as a latent variable and attempts to induce anchoring sequences that help guide generation in an unsupervised fashion. We conduct experiments with several types of sentence decoder distributions -left-to-right and non-monotonic, with different degrees of restriction. Further, since we use amortized variational inference to train our model, we introduce two corresponding types of inference network for predicting the posterior on anchor words. We conduct human evaluations which demonstrate that the stories produced by our model are rated better in comparison with baselines which do not consider story plans, and are similar or better in quality relative to baselines which use external supervision for plans. Additionally, the proposed model gets favorable scores when evaluated on perplexity, diversity, and control of story via discrete plan.

show abstract

“…Headline Generation. In recent years, text generation has made impressive progress (Li et al 2019;Chan et al 2019;Liu et al 2020;Xie et al 2020;Chan et al 2020;Chen et al 2021), and headline generation has become a research hotspot in Natural Language Processing. Most existing headline generation works solely focus on summarizing the document.…”

Section: Related Workmentioning

confidence: 99%

The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement

Li¹,

Chen²,

Yang³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Eye-catching headlines function as the first device to trigger more clicks, bringing reciprocal effect between producers and viewers. Producers can obtain more traffic and profits, and readers can have access to outstanding articles. When generating attractive headlines, it is important to not only capture the attractive content but also follow an eye-catching written style. In this paper, we propose a Disentanglement-based Attractive Headline Generator (DAHG) that generates headline which captures the attractive content following the attractive style. Concretely, we first devise a disentanglement module to divide the style and content of an attractive prototype headline into latent spaces, with two auxiliary constraints to ensure the two spaces are indeed disentangled. The latent content information is then used to further polish the document representation and help capture the salient part. Finally, the generator takes the polished document as input to generate headline under the guidance of the attractive style. Extensive experiments on the public Kuaibao dataset show that DAHG achieves state-ofthe-art performance. Human evaluation also demonstrates that DAHG triggers 22% more clicks than existing models.

show abstract

A Character-Centric Neural Model for Automated Story Generation

Cited by 22 publications

References 10 publications

TVRecap: A Dataset for Generating Stories with Character Descriptions

TVRecap: A Dataset for Generating Stories with Character Descriptions

Narrative Text Generation with a Latent Discrete Plan

The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement

Contact Info

Product

Resources

About