Neelamadhav Gantayat

The synergy between voting and acceptance of answers on stackoverflow, or the lack thereof

StackOverflows primary goal is to serve as a platform for users to solicit answers regarding programming questions, though its archives are often used by other users who face similar issues and thus it serves a secondary purpose of documenting common problems. The two driving mechanisms for filtering out low quality posts and highlighting the best answers are community votes and the mark of acceptance by the original question asker. But does the askers choice always match the popular vote? If so, is the askers choice influenced by the community vote or is the community vote biased towards the accepted answer? And if the asker and community disagree, then can we determine any particular characteristics of posts that influence the choice of the asker and community differently, such as its size, readability, presence of code snippets and external links as well as similarity to the original question? In this paper, we explore the answers to these questions by studying a data-set of all posts on StackOverflow from its launch in September 2008 to September 2014.

A cognitive system for business and technical support: A case study

Business and technical support has traditionally been labor based. In this paper, we introduce a cognitive system for business and technical support. This cognitive system is aimed at answering, for example, “how to” and “how do I fix” questions that represent more than half of support help-desk queries. The standard method to build cognitive systems involves collecting the user questions, collecting and curating the domain knowledge, creating ground truth for learning, training, and testing, and continuous learning from user interactions and feedback. However, the lack of actual user questions, quality, and coverage of available enterprise knowledge, ambiguity in user communication, and user expectations on coverage and accuracy pose a challenge in applying the standard method to the domain of technical support. We address this by extracting and modeling users’ support intents and questions from sources, such as help-desk tickets, discussion forums, and enterprise knowledge—extracting and using a domain knowledge graph to allow the cognitive system to have intent-disambiguating conversations with the user, and including a pool of human experts as a fall-back option to increase the effectiveness and acceptance of the solution (and as a source of learning). Users who participated in initial technology pilots found the system useful.

Intelligent Math Tutor: Problem-Based Approach to Create Cognizance

Mathematical word problems (or story problems) allow students to apply their mathematical problem solving ability to other subjects and real-world situations. Word problems build higher-order thinking, critical problem-solving, and reasoning skills. Generally solving a word problem is associated with mathematical modeling of a real word situation or a concept of another subject which is embedded in the problem. Manually creating word problems require knowledge of other topics a student is learning in parallel. Besides this, modeling mathematics with some other dissociated concept is a time-consuming and labor-intensive task. Due to lack of this integrated knowledge of other topics being taught, the substantive breadth of word problems is often very narrow and is limited to very few concepts. To address this limitation, we built a tool called Intelligent Math Tutor (IMT), which automatically generates mathematical word problems such that teachings from other subjects from a given curriculum can also be incorporated. Our tool thus widens the scope of word problems and uses this problem-solving based approach to indirectly create cognizance in its students. To the best of our knowledge, our tool is the first of its kind tool which explicitly blends knowledge from multiple dissociated subjects and uses it to enhance the cognizance of its learners.

DARVIZ: deep abstract representation, visualization, and verification of deep learning models

Traditional software engineering programming paradigms are mostly object or procedure oriented, driven by deterministic algorithms. With the advent of deep learning and cognitive sciences there is an emerging trend for data-driven programming, creating a shift in the programming paradigm among the software engineering communities. Visualizing and interpreting the execution of a current large scale data-driven software development is challenging. Further, for deep learning development there are many libraries in multiple programming languages such as TensorFlow (Python), CAFFE (C++), Theano (Python), Torch (Lua), and Deeplearning4j (Java), driving a huge need for interoperability across libraries. We propose a model driven development based solution framework, that facilitates intuitive designing of deep learning models in a platform agnostic fashion. This framework could potentially generate library specific code, perform program translation across languages, and debug the training process of a deep learning model from a fault localization and repair perspective. Further we identify open research problems in this emerging domain, and discuss some new software tooling requirements to serve this new age data-driven programming paradigm.