Conversational Neuro-Symbolic Commonsense Reasoning

One aspect of human commonsense reasoning is the ability to make presumptions about daily experiences, activities and social interactions with others. We propose a new commonsense reasoning benchmark where the task is to uncover commonsense presumptions implied by imprecisely stated natural language commands in the form of if-then-because statements. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker relies on commonsense reasoning of the listener to infer the implicit presumption that it must snow enough to cause traffic slowdowns. Such if-then-because commands are particularly important when users instruct conversational agents. We release a benchmark data set for this task, collected from humans and annotated with commonsense presumptions. We develop a neuro-symbolic theorem prover that extracts multi-hop reasoning chains and apply it to this problem. We further develop an interactive conversational framework that evokes commonsense knowledge from humans for completing reasoning chains.

[1]  Fanglin Chen,et al.  Programming IoT Devices by Demonstration Using Mobile Apps , 2017, IS-EUD.

[2]  Alessandra Russo,et al.  DeepLogic: Towards End-to-End Differentiable Logical Reasoning , 2018, AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering.

[3]  Catherine Havasi,et al.  ConceptNet 3 : a Flexible , Multilingual Semantic Network for Common Sense Knowledge , 2007 .

[4]  Peter Clark,et al.  Domain-Targeted, High Precision Knowledge Extraction , 2017, TACL.

[5]  Markus N. Rabe,et al.  Transformers Generalize to the Semantics of Logics , 2020 .

[6]  Ramanathan V. Guha,et al.  Cyc: toward programs with common sense , 1990, CACM.

[7]  Chong Wang,et al.  Neural Logic Machines , 2019, ICLR.

[8]  Ming Zhou,et al.  Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base , 2018, NeurIPS.

[9]  Amos Azaria,et al.  Instructable Intelligent Personal Agent , 2016, AAAI.

[10]  Marco Gori,et al.  Integrating Learning and Reasoning with Deep Logic Models , 2019, ECML/PKDD.

[11]  Nathanael Chambers,et al.  LSDSem 2017 Shared Task: The Story Cloze Test , 2017, LSDSem@EACL.

[12]  Alain Colmerauer,et al.  An introduction to Prolog III , 1989, CACM.

[13]  Henry Lieberman,et al.  Digital Intuition: Applying Common Sense Using Dimensionality Reduction , 2009, IEEE Intelligent Systems.

[14]  Sameer Singh,et al.  Low-Dimensional Embeddings of Logic , 2014, ACL 2014.

[15]  Chuang Gan,et al.  The Neuro-Symbolic Concept Learner: Interpreting Scenes Words and Sentences from Natural Supervision , 2019, ICLR.

[16]  Gokhan Tur,et al.  Spoken Language Understanding: Systems for Extracting Semantic Information from Speech , 2011 .

[17]  Tom M. Mitchell,et al.  LIA: A Natural Language Programmable Personal Assistant , 2018, EMNLP.

[18]  Shashank Srivastava,et al.  Teaching Machines to Classify from Natural Language Interactions , 2018 .

[19]  Richard Evans,et al.  Learning Explanatory Rules from Noisy Data , 2017, J. Artif. Intell. Res..

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

[21]  Hugo Liu,et al.  ConceptNet — A Practical Commonsense Reasoning Tool-Kit , 2004 .

[22]  William W. Cohen TensorLog: A Differentiable Deductive Database , 2016, ArXiv.

[23]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[24]  Miroslav Janícek,et al.  Abductive Reasoning for Continual Dialogue Understanding , 2011, ESSLLI Student Sessions.

[25]  Yejin Choi,et al.  Counterfactual Story Reasoning and Generation , 2019, EMNLP.

[26]  Dan Roth,et al.  Learning from natural instructions , 2011, Machine Learning.

[27]  Yejin Choi,et al.  Event2Mind: Commonsense Inference on Events, Intents, and Reactions , 2018, ACL.

[28]  Amos Azaria,et al.  SUGILITE: Creating Multimodal Smartphone Automation by Demonstration , 2017, CHI.

[29]  Katsumi Inoue,et al.  Learning Commonsense Knowledge Through Interactive Dialogue , 2018, ICLP.

[30]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[31]  Ulf Leser,et al.  NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language , 2019, ACL.

[32]  Kai-Uwe Kühnberger,et al.  Neural-Symbolic Learning and Reasoning: A Survey and Interpretation , 2017, Neuro-Symbolic Artificial Intelligence.

[33]  Marina Sbisà,et al.  Presupposition, Implicature and Context in Text Understanding , 1999, CONTEXT.

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

[35]  Andrew S. Gordon,et al.  One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology , 2015, AAAI Spring Symposia.

[36]  William Yang Wang,et al.  Learning First-Order Logic Embeddings via Matrix Factorization , 2016, IJCAI.

[37]  Gerhard Weikum,et al.  Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion , 2019, CIKM.

[38]  Luc De Raedt,et al.  DeepProbLog: Neural Probabilistic Logic Programming , 2018, BNAIC/BENELEARN.

[39]  Luc De Raedt,et al.  Neural-Symbolic Learning and Reasoning: Contributions and Challenges , 2015, AAAI Spring Symposia.

[40]  Bernd Finkbeiner,et al.  Teaching Temporal Logics to Neural Networks , 2020, ICLR.

[41]  Yejin Choi,et al.  WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale , 2020, AAAI.

[42]  Abduction, conversational implicature and misleading in human dialogues , 2016, Log. J. IGPL.

[43]  Tim Rocktäschel,et al.  End-to-end Differentiable Proving , 2017, NIPS.

[44]  Nando de Freitas,et al.  Neural Programmer-Interpreters , 2015, ICLR.

[45]  Peter Clark,et al.  Transformers as Soft Reasoners over Language , 2020, ArXiv.

[46]  Thomas Lukasiewicz,et al.  A Review of Winograd Schema Challenge Datasets and Approaches , 2020, ArXiv.

[47]  Hector J. Levesque,et al.  The Winograd Schema Challenge , 2011, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning.

[48]  Zhi-Hua Zhou,et al.  Abductive learning: towards bridging machine learning and logical reasoning , 2019, Science China Information Sciences.

[49]  Ernest Davis,et al.  Commonsense reasoning and commonsense knowledge in artificial intelligence , 2015, Commun. ACM.

[50]  Terry Winograd,et al.  Understanding natural language , 1974 .

[51]  Zornitsa Kozareva,et al.  SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning , 2011, *SEMEVAL.

[52]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[53]  Doug Downey,et al.  Abductive Commonsense Reasoning , 2019, ICLR.

[54]  Erik T. Mueller,et al.  Commonsense Reasoning: An Event Calculus Based Approach , 2006 .

[55]  Siobhan Chapman Logic and Conversation , 2005 .

[56]  Tom M. Mitchell,et al.  APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Natural Language Instructions , 2018, 2018 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC).

[57]  Mandy Simons,et al.  On the Conversational Basis of Some Presuppositions , 2013 .

[58]  Peter Clark,et al.  Learning Knowledge Graphs for Question Answering through Conversational Dialog , 2015, NAACL.

[59]  Henry Lieberman,et al.  AnalogySpace: Reducing the Dimensionality of Common Sense Knowledge , 2008, AAAI.