Semantic Frame Forecast

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2702–2713 June 6–11, 2021. ©2021 Association for Computational Linguistics 2702 Semantic Frame Forecast Chieh-Yang Huang and Ting-Hao (Kenneth) Huang Pennsylvania State University, University Park, PA 16802, USA {chiehyang, txh710}@psu.edu Abstract This paper introduces semantic frame fore- cast, a task that predicts the semantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story. Prior work focused on predicting the immediate fu- ture of a story, such as one to a few sen- tences ahead. However, when novelists write long stories, generating a few sentences is not enough to help them gain high-level insight to develop the follow-up story. In this paper, we formulate a long story as a sequence of “story blocks,” where each block contains a fixed number of sentences (e.g., 10, 100, or 200). This formulation allows us to predict the follow-up story arc beyond the scope of a few sentences. We represent a story block using the term frequencies (TF) of semantic frames in it, normalized by each frame’s in- verse document frequency (IDF). We conduct semantic frame forecast experiments on 4,794 books from the Bookcorpus and 7,962 scien- tific abstracts from CODA-19, with block sizes ranging from 5 to 1,000 sentences. The re- sults show that automated models can fore- cast the follow-up story blocks better than the random, prior, and replay baselines, in- dicating the task’s feasibility. We also learn that the models using the frame representa- tion as features outperform all the existing ap- proaches when the block size is over 150 sen- tences. The human evaluation also shows that the proposed frame representation, when visu- alized as word clouds, is comprehensible, rep- resentative, and specific to humans. Our code is available at: https://github.com/ appleternity/FrameForecasting. 1 Introduction Writing a good novel is hard. Creative writers can get stuck in the middle of their drafts and struggle to develop follow-up scenes. Writing support sys- tems, such as Heteroglossia (Huang et al., 2020a), generate paragraphs or ideas to help writers figure out the next part of the ongoing story. However, Figure 1: The semantic frame forecast is a task that predicts the semantic frames that will occur in the next part of a story based on the texts written so far. little literature focuses on plot prediction for long stories. Much prior work focused on predicting the immediate future of a story, i.e., one to a few sen- tences later. For example, the Creative Help system used a recurrent neural network model to generate the next sentence to support writing (Roemmele and Gordon, 2015); the Scheherazade system uses crowdsourcing and artificial intelligence techniques to interactively construct the narrative sentence by sentence (Li and Riedl, 2015); Clark et al. (2018) study machine-in-the-loop story writing where the machine constantly generates a suggestion for the next sentence to stimulate writers; and Metapho- ria (Gero and Chilton, 2019) generates metaphors, an even smaller …

Content truncated to 500 words