Enabling Interactive Answering of Procedural Questions

A mechanism to enable task oriented procedural question answering system for user assistance in English is presented in this paper. The primary aim is to create an answering “corpus” in a tree-form from unstructured document passages. This corpus is used to respond to the queries interactively to assist in completing a technical task. Reference manuals, documents or webpages are scraped to identify the sections depicting a “procedure” through machine learning techniques and then an integrated task tree with extracted procedural knowledge from text is generated. The automated mechanism breaks the procedural sections into steps, the appropriate “decision points” are identified, the interactive utterances are generated to gain user inputs and the alternative paths are created to complete the tree. Conventional tree traversal mechanism provides step by step guidance to complete a task. Efficacy of the proposed mechanism is tested on documents collected from three different domains and test results are presented.

[1]  Xinya Du,et al.  Be Consistent! Improving Procedural Text Comprehension using Label Consistency , 2019, NAACL.

[2]  Richard G. Baraniuk,et al.  QG-net: a data-driven question generation model for educational content , 2018, L@S.

[3]  Ming Zhou,et al.  Question Generation for Question Answering , 2017, EMNLP.

[4]  Kenneth D. Forbus,et al.  Predicting State Changes in Procedural Text using Analogical Question Answering , 2019 .

[5]  Patrick Saint-Dizier,et al.  Analyzing Argumentative Structures in Procedural Texts , 2008, GoTAL.

[6]  Hervé Déjean,et al.  Introduction to the CoNLL-2001 shared task: clause identification , 2001, CoNLL.

[7]  S. Rigatti.  Random Forest. , 2017, Journal of insurance medicine.

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Patrick Saint-Dizier,et al.  Towards Generating Procedural Texts: An Exploration of their Rhetorical and Argumentative Structure , 2005, ENLG.

[10]  Tibert Verhagen,et al.  Virtual Customer Service Agents: Using Social Presence and Personalization to Shape Online Service Encounters , 2014, J. Comput. Mediat. Commun..

[11]  Patrick Saint-Dizier,et al.  Investigating the Structure of Procedural Texts for Answering How-to Questions , 2008, LREC.

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

[13]  Patrick Saint-Dizier,et al.  Some Challenges of Advanced Question-Answering: an Experiment with How-to Questions , 2008, PACLIC.

[14]  Patrick Saint-Dizier,et al.  Identifying and expanding titles in web texts , 2008, DocEng '08.

[15]  Rajarshi Das,et al.  Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension , 2018, ICLR.

[16]  Wei Xu,et al.  Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

[17]  Dongyan Zhao,et al.  Aspect-based Question Generation , 2018, ICLR.

[18]  Percy Liang,et al.  Simpler Context-Dependent Logical Forms via Model Projections , 2016, ACL.

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.