Script Induction as Language Modeling

By Rachel Rudinger, Pushpendre Rastogi, Francis Ferraro, Benjamin Van Durme. 2015

102 citations recorded by the source corpus.

The narrative cloze is an evaluation metric commonly used for work on automatic script induction. While prior work in this area has focused on count-based methods from distributional semantics, such as pointwise mutual information, we argue that the narrative cloze can be productively reframed as a language modeling task. By training a discriminative language model for this task, we attain improvements of up to 27 percent over prior methods on standard narrative cloze metrics.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yejin Choi
2. Jianfeng Gao
3. Mohit Bansal
4. Percy Liang
5. Benjamin Van Durme
6. Devi Parikh
7. Luke S. Zettlemoyer
8. Noah A. Smith

In Natural Language Processing

1. Yejin Choi
2. Mohit Bansal
3. Benjamin Van Durme
4. Jianfeng Gao
5. Percy Liang
6. Devi Parikh
7. Rachel Rudinger
8. Dhruv Batra

Citations in the corpus

• A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “Since then, others have shown language-modeling techniques perform well (Pichotta and Mooney, 2014a; Rudinger et al., 2015).”
• Ordinal Common-sense Inference (2016, background): “To resolve the definite reference the windows , one needs to know that rooms have windows is probable. world (Rudinger et al., 2015).”
• Enabling Language Models to Fill in the Blanks (2020, background): “Rudinger et al. (2015) frame narrative cloze as a generation task and employ language models, but they only consider one infill of a fixed length.”
• CaTeRS: Causal and Temporal Relation Scheme for Semantic Annotation of Event Structures (2016, methodology): “Earlier work (Chambers and Jurafsky, 2008; Chambers and Jurafsky, 2009; Pichotta and Mooney, 2014; Rudinger et al., 2015) defines verbs as events and uses TimeML-based (Pustejovsky et al.”
• Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, unknown): “Previous works [16], [17] showed that”
• Connecting the Dots: Event Graph Schema Induction with Path Language Modeling (2020, unknown): “Previous work (Chambers and Jurafsky, 2008, 2009, 2010; Jans et al., 2012; Balasubramanian et al., 2013; Pi-chotta and Mooney, 2014, 2016; Rudinger et al., 2015; Granroth-Wilding and Clark, 2016; Modi, 2016; Mostafazadeh et al., 2016a; Peng et al., 2019) focuses on inducing narrative schemas as…”