Weakly Supervised Subevent Knowledge Acquisition

Subevents elaborate an event and widely exist in event descriptions. Subevent knowledge is useful for discourse analysis and event-centric applications. Acknowledging the scarcity of subevent knowledge, we propose a weakly supervised approach to extract subevent relation tuples from text and build the first large scale subevent knowledge base. We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents. Then, we collect rich weak supervision using the initial seed subevent pairs to train a contextual classifier using BERT and apply the classifier to identify new subevent pairs. The evaluation showed that the acquired subevent tuples (239K) are of high quality (90.1% accuracy) and cover a wide range of event types. The acquired subevent knowledge has been shown useful for discourse analysis and identifying a range of event-event relations.

[1]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[2]  Mark A. Finlayson,et al.  Detecting Subevents using Discourse and Narrative Features , 2019, ACL.

[3]  Seth Kulick,et al.  From Light to Rich ERE: Annotation of Entities, Relations, and Events , 2015, EVENTS@HLP-NAACL.

[4]  Taylor Cassidy,et al.  Dense Event Ordering with a Multi-Pass Architecture , 2014, TACL.

[5]  Mehwish Riaz,et al.  Toward a Better Understanding of Causality between Verbal Events: Extraction and Analysis of the Causal Power of Verb-Verb Associations , 2013, SIGDIAL Conference.

[6]  Steven Bethard,et al.  ClearTK-TimeML: A minimalist approach to TempEval 2013 , 2013, *SEMEVAL.

[7]  Neville Ryant,et al.  A large-scale classification of English verbs , 2008, Lang. Resour. Evaluation.

[8]  Yejin Choi,et al.  ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning , 2019, AAAI.

[9]  Zhiyi Song,et al.  Overview of Linguistic Resources for the TAC KBP 2017 Evaluations: Methodologies and Results , 2017, TAC.

[10]  Dan Roth,et al.  Minimally Supervised Event Causality Identification , 2011, EMNLP.

[11]  Jan Snajder,et al.  Constructing Coherent Event Hierarchies from News Stories , 2014, TextGraphs@EMNLP.

[12]  Marie-Francine Moens,et al.  HiEve: A Corpus for Extracting Event Hierarchies from News Stories , 2014, LREC.

[13]  Tommaso Caselli,et al.  Crowdsourcing StoryLines: Harnessing the Crowd for Causal Relation Annotation , 2018, EventStory@Coling.

[14]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[15]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[16]  Christopher R. Johnson,et al.  Background to Framenet , 2003 .

[17]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[18]  Ruihong Huang,et al.  A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing , 2019, EMNLP.

[19]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[20]  Leo Obrst,et al.  The Rich Event Ontology , 2017, NEWS@ACL.

[21]  Roxana Gîrju,et al.  Automatic Detection of Causal Relations for Question Answering , 2003, ACL 2003.

[22]  Teruko Mitamura,et al.  Detecting Subevent Structure for Event Coreference Resolution , 2014, LREC.

[23]  Mark A. Przybocki,et al.  The Automatic Content Extraction (ACE) Program – Tasks, Data, and Evaluation , 2004, LREC.

[24]  Ruihong Huang,et al.  Extracting Subevents via an Effective Two-phase Approach , 2016, EMNLP.

[25]  Rashmi Prasad,et al.  The Penn Discourse Treebank , 2004, LREC.

[26]  Martha Palmer,et al.  Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation , 2016 .

[27]  Mehwish Riaz,et al.  Another Look at Causality: Discovering Scenario-Specific Contingency Relationships with No Supervision , 2010, 2010 IEEE Fourth International Conference on Semantic Computing.

[28]  Estela Saquete Boró,et al.  TIPSem (English and Spanish): Evaluating CRFs and Semantic Roles in TempEval-2 , 2010, *SEMEVAL.

[29]  Benjamin Van Durme,et al.  Annotated Gigaword , 2012, AKBC-WEKEX@NAACL-HLT.

[30]  Xiaoming Liu,et al.  SLPA: Uncovering Overlapping Communities in Social Networks via a Speaker-Listener Interaction Dynamic Process , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[31]  Boleslaw K. Szymanski,et al.  Overlapping community detection in networks: The state-of-the-art and comparative study , 2011, CSUR.

[32]  Yejin Choi,et al.  COMET: Commonsense Transformers for Knowledge Graph Construction , 2019 .

[33]  Vincent Ng,et al.  Classifying Temporal Relations with Rich Linguistic Knowledge , 2013, NAACL.

[34]  Paramita Mirza,et al.  CATENA: CAusal and TEmporal relation extraction from NAtural language texts , 2016, COLING.

[35]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[36]  James H. Martin,et al.  Learning Semantic Links from a Corpus of Parallel Temporal and Causal Relations , 2008, ACL.

[37]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[38]  Paramita Mirza,et al.  An Analysis of Causality between Events and its Relation to Temporal Information , 2014, COLING.