Chirag Jain

Pratik Jayarao, Chirag Jain, Aman Srivastava

Named Entity Recognition (NER), a classic sequence labelling task, is an essential component of natural language understanding (NLU) systems in task-oriented dialog systems for slot filling. For well over a decade, different methods from lookup using gazetteers and domain ontology, classifiers over handcrafted features to end-to-end systems involving neural network architectures have been evaluated mostly in language-independent non-conversational settings. In this paper, we evaluate a modified version of the recent state of the art neural architecture in a conversational setting where messages are often short and noisy. We perform an array of experiments with different combinations of including the previous utterance in the dialogue as a source of additional features and using word and character level embeddings trained on a larger external corpus. All methods are evaluated on a combined dataset formed from two public English task-oriented conversational datasets belonging to travel and restaurant domains respectively. For additional evaluation, we also repeat some of our experiments after adding automatically translated and transliterated (from translated) versions to the English only dataset.

Aniruddha Tammewar, Monik Pamecha, Chirag Jain et al.

In this paper, we present a hybrid model that combines a neural conversational model and a rule-based graph dialogue system that assists users in scheduling reminders through a chat conversation. The graph based system has high precision and provides a grammatically accurate response but has a low recall. The neural conversation model can cater to a variety of requests, as it generates the responses word by word as opposed to using canned responses. The hybrid system shows significant improvements over the existing baseline system of rule based approach and caters to complex queries with a domain-restricted neural model. Restricting the conversation topic and combination of graph based retrieval system with a neural generative model makes the final system robust enough for a real world application.

Subhayan Roy Moulick, Siddharth Arora, Chirag Jain et al.

A semi-blind watermarking scheme is presented based on Singular Value Decomposition (SVD), which makes essential use of the fact that, the SVD subspace preserves significant amount of information of an image and is a one way decomposition. The principal components are used, along with the corresponding singular vectors of the watermark image to watermark the target image. For further security, the semi-blind scheme is extended to an invisible hash based watermarking scheme. The hash based scheme commits a watermark with a key such that, it is incoherent with the actual watermark, and can only be extracted using the key. Its security is analyzed in the random oracle model and shown to be unforgeable, invisible and satisfying the property of non-repudiation.