Model-based Offline Multi-Agent Dialogue Policy Learning
June 2020 · Github ↗
Vishwanath Jha
· Akash Singh
Speech and Language Technology Lab, Saarthi.ai
The conventional problem of selecting an action when provided with a state, environment and history (context) falls in the domain of self-play reinforcement learning. Numerous such algorithms learn a dialog policy with the reward function requiring an elaborate design of a comprehensive user simulator and pre-specified user goals. Here, in the implemented method, it is regarded that the user agent can learn with the system agent in a joint/shared fashion. The method involves the concept of role-aware reward decomposition using Hybrid Value Network with the integration of actor-critic framework to maximize the global reward for the policy learner.
Few-shot Unsupervised Discrete Sentence Representation Learning based Dialogue Generation
May 2020 · Github ↗
Vishwanath Jha
· Akash Singh
Speech and Language Technology Lab, Saarthi.ai
An unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialogue model, for interpretable response generation using a minimal amount of data that is not annotated.
A Hybrid Classification Approach using Topic Modeling and Graph Convolutional Networks
Published in ComPE 2020, Shillong
October 2019 · Github ↗
Dr. Thoudam Doren Singh
CNLP Lab, NIT Silchar
A novel multi-class text classification technique that harvests features from two distinct feature extraction methods. Firstly, a structured heterogeneous text graph built based on document-word relations and word co-occurrences is leveraged using a Graph Convolution Network (GCN). Secondly, the documents are topic modeled to use the document-topic score as features into the classification model. The concerned graph is constructed using Point-Wise Mutual Information (PMI) between pair of word co-occurrences and Term Frequency-Inverse Document Frequency (TF-IDF) score for words in the documents for word co-occurrences.
The Paperless
Winner, Hackathon Module
August 2019 · Github ↗
NIT Conclave 2019 (at NIT Rourkela)
PaperLess, an automation PWA, is responsible for auto-filling the required form and forwarding the filled application form to various concerned authorities. The only manual thing in PaperLess is selection of form by the student. After the selection of form, everything is automated including forwarding the application to the concerned authorities. At the end of the process, PaperLess produces the final approved application.
Unsupervised Domain Adaptation for Fingerprint Recognition
July 2019 · Github ↗
Dr. Vivek Kanhangad
Pattern Recognition and Image Analysis Lab, Indian Institute of Technology Indore
The concept of domain adaptation in the absence of labelled training data for a deep learning architecture was implemented by augmenting the given deep neural network with the proposed new gradient reversal layer.
Pore-based Fingerprint Recognition System
July 2019 · Github ↗
Dr. Vivek Kanhangad
Pattern Recognition and Image Analysis Lab, Indian Institute of Technology Indore
A customized deep learning based fingerprint recognition system has been developed using the multitask deep convolutional neural network architecture to extract the fixed length representation of level 1, 2 & 3 features from a high resolution fingerprint image. The recognition system calculates the cosine similarity score between the two representations to generate a distribution of scores (genuine and imposter score distributions) and hence, plot a probability vs matching score graph to study the tradeoff between false match rate (FMR) and false non-match rate (FNMR).
BingScraper
July 2018 · Github ↗
PyPI ↗
· Scholar Citation ↗
The bingscraper is python3 package which extracts the text and images content on Bing (the search engine:- bing.com). The script working in background requests for a search term and creates directory (if not made previously) in the root directory of the script where all the content of the related particular search is stored. This script will be downloading the hypertext and hyperlink to that text and saving it to a .txt file within the directory made by itself. This directory saves the text content as well as the images downloaded using the script.