Incorporating Structured Commonsense Knowledge in Story Completion

By Jiaao Chen, Jianshu Chen, Zhou Yu. 2018

75 citations recorded by the source corpus.

The ability to select an appropriate story ending is the first step towards perfect narrative comprehension. Story ending prediction requires not only the explicit clues within the context, but also the implicit knowledge (such as commonsense) to construct a reasonable and consistent story. However, most previous approaches do not explicitly use background commonsense knowledge. We present a neural story ending selection model that integrates three types of information: narrative sequence, sentiment evolution and commonsense knowledge. Experiments show that our model outperforms state-ofthe-art approaches on a public dataset, ROCStory Cloze Task (Mostafazadeh et al. 2017), and the performance gain from adding the additional commonsense knowledge is significant.

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

In Natural Language Processing

Citations in the corpus

Story Ending Prediction by Transferable BERT (2019, methodology): “DSSM [Huang et al. , 2013] 58.5 CGAN [Wang et al. , 2017] 60.9 HBiLSTM [Cai et al. , 2017] 74.7 Msap [Schwartz et al. , 2017] 75.2 HCM [Chaturvedi et al. , 2017] 77.6 HintNet [Zhou et al. , 2019] 79.2 SeqMANN [Li et al. , 2018a] 84.7 GPT [Radford et al. , 2018] 86.5 ISCK [Chen et al. , 2019] 87 ISCK”
Unsupervised Commonsense Question Answering with Self-Talk (2020, methodology): “…high-precision world knowledge and facilitate multi-hop reasoning by making intermediate reasoning steps explicit, prior work incorporated KBs (e.g. ConceptNet; Speer and Havasi, 2012) and knowledge-informed models into LM-based models (Xia et al., 2019; Bosselut and Choi, 2019; Chen et al., 2019).”
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification (2020, background): “The pre-training and ﬁne-tuning framework has achieved huge success on NLP applications in recent years, and has been applied to a variety of NLP tasks (Radford et al., 2018; Chen et al., 2019; Akbik et al., 2019).”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, background): “…facts (or events), inasmuch as it supports countless knowledge-driven tasks in areas such as information retrieval (Liu et al. 2018), natural language understanding (Chen, Chen, and Yu 2019; He et al. 2017), recommender systems (Koren, Bell, and Volinsky 2009) and healthcare (Hao et al. 2020).”
Controllable Story Generation with External Knowledge Using Large-Scale Language Models (2020, background): “Other works focus on incorporating commonsense knowledge into story generation with attention-based models (Guan et al., 2019; Chen et al., 2019).”
Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, methodology): “including SeqMANN [28], FTLM (also known asOpenAIGPT) [29], and Commonsense-Model [30], showed that training on very large data can make remarkable improvements for Story Cloze Test.”