no code implementations • RANLP 2021 • Prerna Prem, Zishan Ahmad, Asif Ekbal, Shubhashis Sengupta, Sakshi C. Jain, Roshni Ramnani
This task of separating the unknown intent samples from known intents one is challenging as the unknown user intent can range from intents similar to the predefined intents to something completely different.
no code implementations • CONSTRAINT (ACL) 2022 • Megha Sundriyal, Ganeshan Malhotra, Md Shad Akhtar, Shubhashis Sengupta, Andrew Fano, Tanmoy Chakraborty
The current vogue is to employ manual fact-checkers to verify claims to combat this avalanche of misinformation.
no code implementations • NAACL (ACL) 2022 • Sayantan Mitra, Roshni Ramnani, Shubhashis Sengupta
The objective of a Question-Answering system over Knowledge Graph (KGQA) is to respond to natural language queries presented over the KG.
no code implementations • SIGDIAL (ACL) 2022 • Sayantan Mitra, Roshni Ramnani, Sumit Ranjan, Shubhashis Sengupta
Building conversation agents requires a large amount of manual effort in creating training data for intents / entities as well as mapping out extensive conversation flows.
no code implementations • 16 Oct 2022 • Prajwal Gatti, Abhirama Subramanyam Penamakuri, Revant Teotia, Anand Mishra, Shubhashis Sengupta, Roshni Ramnani
To enable both commonsense and factual reasoning in the image search, we present a unified framework, namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT), that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge.
no code implementations • LREC 2022 • Sandhya Singh, Prapti Roy, Nihar Sahoo, Niteesh Mallela, Himanshu Gupta, Pushpak Bhattacharyya, Milind Savagaonkar, Nidhi, Roshni Ramnani, Anutosh Maitra, Shubhashis Sengupta
Since AI solutions are data intensive and there exists no domain specific data to address the problem of biases in scripts, we introduce a new dataset of movie scripts that are annotated for identity bias.
no code implementations • 21 Dec 2021 • Aayushee Gupta, K. M. Annervaz, Ambedkar Dukkipati, Shubhashis Sengupta
The query conversion models and direct models both require specific training data pertaining to the domain of the knowledge graph.
1 code implementation • 19 Aug 2021 • Megha Sundriyal, Parantak Singh, Md Shad Akhtar, Shubhashis Sengupta, Tanmoy Chakraborty
To demarcate between a claim and a non-claim is arduous for both humans and machines, owing to latent linguistic variance between the two and the inadequacy of extensive definition-based formalization.
no code implementations • 18 Apr 2021 • Vivek Khetan, Annervaz K M, Erin Wetherley, Elena Eneva, Shubhashis Sengupta, Andrew E. Fano
The growing quantity and complexity of data pose challenges for humans to consume information and respond in a timely manner.
1 code implementation • 12 Apr 2021 • Rachit Bansal, William Scott Paka, Nidhi, Shubhashis Sengupta, Tanmoy Chakraborty
In this work, we present ENDEMIC, a novel early detection model which leverages exogenous and endogenous signals related to tweets, while learning on limited labeled data.
1 code implementation • 17 Feb 2021 • William Scott Paka, Rachit Bansal, Abhay Kaushik, Shubhashis Sengupta, Tanmoy Chakraborty
As the COVID-19 pandemic sweeps across the world, it has been accompanied by a tsunami of fake news and misinformation on social media.
no code implementations • COLING 2018 • Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, Shubhashis Sengupta
In this paper, we propose a hybrid technique for semantic question matching.
no code implementations • 10 Dec 2020 • Vivek Khetan, Roshni Ramnani, Mayuresh Anand, Shubhashis Sengupta, Andrew E. Fano
Therefore, as expected these methods are more geared towards handling explicit causal relationships leading to limited coverage for implicit relationships and are hard to generalize.
1 code implementation • COLING 2020 • Ajay Chatterjee, Shubhashis Sengupta
In this paper, we present an intent discovery framework that involves 4 primary steps: Extraction of textual utterances from a conversation using a pre-trained domain agnostic Dialog Act Classifier (Data Extraction), automatic clustering of similar user utterances (Clustering), manual annotation of clusters with an intent label (Labeling) and propagation of intent labels to the utterances from the previous step, which are not mapped to any cluster (Label Propagation); to generate intent training data from raw conversations.