Event2Mind: Commonsense Inference on Events, Intents, and Reactions

We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event's participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people's intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.

[1]  Kevin Gimpel,et al.  From Paraphrase Database to Compositional Paraphrase Model and Back , 2015, Transactions of the Association for Computational Linguistics.

[2]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[3]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[4]  Peter Blouw,et al.  Using Neural Networks to Generate Inferential Roles for Natural Language , 2018, Front. Psychol..

[5]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

[6]  Janyce Wiebe,et al.  +/-EffectWordNet: Sense-level Lexicon Acquisition for Opinion Inference , 2014, EMNLP.

[7]  Ellen Riloff,et al.  Acquiring Knowledge of Affective Events from Blogs Using Label Propagation , 2016, AAAI.

[8]  Yejin Choi,et al.  Connotation Frames of Power and Agency in Modern Films , 2017, EMNLP.

[9]  Christopher Potts,et al.  Did It Happen? The Pragmatic Complexity of Veridicality Assessment , 2012, CL.

[10]  J. Pennebaker,et al.  The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods , 2010 .

[11]  Rebecca L. Collins,et al.  Content Analysis of Gender Roles in Media: Where Are We Now and Where Should We Go? , 2011 .

[12]  Apoorv Agarwal,et al.  Key Female Characters in Film Have More to Talk About Besides Men: Automating the Bechdel Test , 2015, HLT-NAACL.

[13]  Deborah A. Prentice,et al.  What Women and Men Should Be, Shouldn't be, are Allowed to be, and don't Have to Be: The Contents of Prescriptive Gender Stereotypes , 2002 .

[14]  Martha Palmer,et al.  The VerbCorner Project: Toward an Empirically-Based Semantic Decomposition of Verbs , 2013, EMNLP.

[15]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[16]  Kenneth D. Forbus,et al.  Using narrative functions as a heuristic for relevance in story understanding , 2010, FDG.

[17]  Yoav Goldberg,et al.  A Dataset of Syntactic-Ngrams over Time from a Very Large Corpus of English Books , 2013, *SEMEVAL.

[18]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[19]  Marilyn A. Walker,et al.  Learning Lexico-Functional Patterns for First-Person Affect , 2017, ACL.

[20]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[21]  Ellen Riloff,et al.  Why Is an Event Affective? Classifying Affective Events Based on Human Needs , 2018, AAAI Workshops.

[22]  Mirella Lapata,et al.  Learning to Paraphrase for Question Answering , 2017, EMNLP.

[23]  Shrikanth S. Narayanan,et al.  Linguistic analysis of differences in portrayal of movie characters , 2017, ACL.

[24]  Ellen Riloff,et al.  Weakly Supervised Induction of Affective Events by Optimizing Semantic Consistency , 2018, AAAI.

[25]  Nathanael Chambers,et al.  A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories , 2016, NAACL.

[26]  Tomoki Toda,et al.  Acquiring a Dictionary of Emotion-Provoking Events , 2014, EACL.

[27]  Tommaso Caselli,et al.  SemEval-2015 Task 9: CLIPEval Implicit Polarity of Events , 2015, *SEMEVAL.

[28]  Henry Lieberman,et al.  EventNet: Inferring Temporal Relations Between Commonsense Events , 2005, MICAI.

[29]  Melissa A. Collier‐Meek,et al.  Gender Role Portrayal and the Disney Princesses , 2011 .

[30]  Sameep Mehta,et al.  Analyzing Gender Stereotyping in Bollywood Movies , 2017, ArXiv.

[31]  Francis Ferraro,et al.  Semantic Proto-Roles , 2015, TACL.

[32]  Johan Bos,et al.  Recognising Textual Entailment with Robust Logical Inference , 2005, MLCW.

[33]  Zheng Chen,et al.  Detecting and Explaining Causes From Text For a Time Series Event , 2017, EMNLP.

[34]  Xiang Li,et al.  Commonsense Knowledge Base Completion , 2016, ACL.

[35]  Philip Resnik,et al.  Spin: lexical semantics, transitivity, and the identification of implicit sentiment , 2007 .

[36]  Yejin Choi,et al.  Connotation Frames: A Data-Driven Investigation , 2015, ACL.

[37]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[38]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[39]  Sheng Zhang,et al.  Ordinal Common-sense Inference , 2016, TACL.

[40]  Qin Lu,et al.  A Question Answering Approach for Emotion Cause Extraction , 2017, EMNLP.

[41]  Chris Callison-Burch,et al.  PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification , 2015, ACL.

[42]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[43]  Mirella Lapata,et al.  Movie Script Summarization as Graph-based Scene Extraction , 2015, NAACL.

[44]  Noah A. Smith,et al.  Frame-Semantic Parsing , 2014, CL.

[45]  Sheng Zhang,et al.  Universal Decompositional Semantics on Universal Dependencies , 2016, EMNLP.

[46]  Anna Korhonen,et al.  VerbNet overview, extensions, mappings and applications , 2009, HLT-NAACL.

[47]  Reid Swanson,et al.  StoryUpgrade: Finding Stories in Internet Weblogs , 2008, ICWSM.

[48]  Dana E. Mastro,et al.  Mean Girls? The Influence of Gender Portrayals in Teen Movies on Emerging Adults' Gender-Based Attitudes and Beliefs , 2008 .

[49]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[50]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.