Knowledge-driven Natural Language Understanding of English Text and its Applications

Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) research. An ideal NLU system should process a language in a way that is not exclusive to a single task or a dataset. Keeping this in mind, we have introduced a novel knowledge driven semantic representation approach for English text. By leveraging the VerbNet lexicon, we are able to map syntax tree of the text to its commonsense meaning represented using basic knowledge primitives. The general purpose knowledge represented from our approach can be used to build any reasoning based NLU system that can also provide justification. We applied this approach to construct two NLU applications that we present here: SQuARE (Semantic-based Question Answering and Reasoning Engine) and StaCACK (Stateful Conversational Agent using Commonsense Knowledge). Both these systems work by “truly understanding” the natural language text they process and both provide natural language explanations for their responses while maintaining high accuracy.

[1]  Nikhil Gupta,et al.  Disentangling Language and Knowledge in Task-Oriented Dialogs , 2018, NAACL.

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

[3]  Beth Levin,et al.  English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[4]  Yang Liu,et al.  Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer , 2018, ArXiv.

[5]  Chitta Baral,et al.  Knowledge Representation, Reasoning and Declarative Problem Solving , 2003 .

[6]  Kinjal Basu,et al.  Conversational AI : Open Domain Question Answering and Commonsense Reasoning , 2019, ICLP Technical Communications.

[7]  Michael Gelfond,et al.  Knowledge Representation, Reasoning, and the Design of Intelligent Agents: The Answer-Set Programming Approach , 2014 .

[8]  Manuel Carro,et al.  Constraint Answer Set Programming without Grounding , 2018, Theory and Practice of Logic Programming.

[9]  Gopal Gupta,et al.  An ASP Based Approach to Answering Questions for Natural Language Text , 2019, PADL.

[10]  Pascale Fung,et al.  Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems , 2018, ACL.

[11]  Yuliya Lierler,et al.  Action Languages and Question Answering , 2017, IWCS.

[12]  Kenneth Mark Colby,et al.  Artificial Paranoia , 1975, Artif. Intell..

[13]  Clifton James McFate.  Expanding Verb Coverage in Cyc with VerbNet , 2010, ACL.

[14]  Oren Etzioni,et al.  Open Language Learning for Information Extraction , 2012, EMNLP.

[15]  Kinjal Basu,et al.  SQuARE: Semantics-based Question Answering and Reasoning Engine , 2020, ICLP Technical Communications.

[16]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[17]  Manuel Carro,et al.  Justifications for Goal-Directed Constraint Answer Set Programming , 2020, ICLP Technical Communications.

[18]  Farhad Shakerin,et al.  AQuA: ASP-Based Visual Question Answering , 2020, PADL.

[19]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[20]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

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

[22]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[23]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[24]  Richard Socher,et al.  Ask Me Anything: Dynamic Memory Networks for Natural Language Processing , 2015, ICML.

[25]  David A. Schmidt,et al.  Denotationaisemantics: a methodology for language development , 1986 .