Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4586–4596 August 1–6, 2021. ©2021 Association for Computational Linguistics 4586 Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning Yucheng Zhou1∗, Xiubo Geng2†, Tao Shen3, Jian Pei4, Wenqiang Zhang1, Daxin Jiang2† 1Fudan University, Shanghai, China 2Microsoft, Beijing, China 3Australian AI Institute, School of CS, FEIT, University of Technology Sydney 4Simon Fraser University, Burnaby, Canada {yczhou18,wqzhang}@fudan.edu.cn, {xigeng,djiang}@microsoft.com tao.shen@student.uts.edu.au, jpei@cs.sfu.ca Abstract Script reasoning infers subsequent events from a given event chain, which involves the abil- ity to understand relations between events. A human-labeled script reasoning dataset is usu- ally of small size with limited event relations, which highlights the necessity to leverage ex- ternal eventuality knowledge graphs (KG) con- sisting of numerous triple facts to describe the inferential relation between events. Exist- ing methods adopt a retrieval and integration paradigm to focus merely on the graph triples that have event overlap with a script, but ignore much more supportive triples in the KG with similar inferential patterns, leading to under- exploiting. To fully exploit the KG, we pro- pose a knowledge model to learn the inferen- tial relations between events from the whole eventuality KG and then support downstream models by directly capturing the relation be- tween events in a script. We further present a neural script adapter to extend the knowledge model for inferring the associated relations be- tween an event chain and a subsequent event candidate. We evaluate the proposed approach on a popular multi-choice narrative cloze task for script reasoning and achieve new state-of- the-art accuracy, compared with baselines ei- ther incorporating external KG or not. 1 Introduction Script reasoning (Chambers and Jurafsky, 2008; Li et al., 2018; Lv et al., 2020b) aims at determin- ing the subsequent event or plausible ending for an event chain in a script. For example, a tourism script consist of [“Emily took a plane”, “Emily ar- rived at Oahu”, “Emily went to Waimea Bay”], and the subsequent event is more likely to be “Emily surfed” than “Emily skied”. Script reasoning has attracted more interest in the natural language pro- cessing (NLP) community since it plays essential ∗Work is done during internship at Microsoft. †Corresponding author. Figure 1: Comparison of “retrieval and integration” paradigm (green dot line) with ours (blue dash-dot line). Al- though there is no semantic overlap between the precedent event in the script and the events in the KG, which leads to failed retrieval, our approach still provides supportive evidence by exploiting similar inferential relation patterns. roles in many real-world applications like story- telling (Swanson and Gordon, 2008). Understanding and inferring the correlation be- tween two events are critical for script reasoning. Taking the tourism script as an example, the key to decide the subsequent event is inferring that “A person goes to a beach” is more correlated to “The person surfs” than “The person skies”. An imme- diate idea is to learn event relations from some well-labeled training datasets. Unfortunately, due to labor-intensive labeling, high-quality training data for script …

Content truncated to 500 words