Stop Clickbait: Detecting and preventing clickbaits in online news media
- Abhijnan Chakraborty, Bhargavi Paranjape, Sourya Kakarla, Niloy Ganguly
- Computer ScienceInternational Conference on Advances in Social…
- 18 August 2016
This work attempts to automatically detect clickbait detection and then builds a browser extension which warns the readers of different media sites about the possibility of being baited by such headlines, and offers each reader an option to block clickbaits she doesn't want to see.
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
- Chirag Gupta, Arun Sai Suggala, Prateek Jain
- Computer ScienceInternational Conference on Machine Learning
- 6 August 2017
Several real-world applications require real-time prediction on resource-scarce devices such as an Internet of Things (IoT) sensor. Such applications demand prediction models with small storage and…
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
- Bhargavi Paranjape, Mandar Joshi, John Thickstun, Hannaneh Hajishirzi, Luke Zettlemoyer
- Computer ScienceConference on Empirical Methods in Natural…
- 1 May 2020
This paper shows that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective, and derives a learning objective that allows direct control of mask sparsity levels through a tunable sparse prior.
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
- Dheeraj Mekala, Vivek Gupta, Bhargavi Paranjape, H. Karnick
- Computer ScienceConference on Empirical Methods in Natural…
- 20 December 2016
Through extensive experiments on multi-class and multi-label classification tasks, this work outperforms the previous state-of-the-art method, NTSG and achieves a significant reduction in training and prediction times compared to other representation methods.
Entity Projection via Machine Translation for Cross-Lingual NER
- Alankar Jain, Bhargavi Paranjape, Zachary Chase Lipton
- Computer ScienceConference on Empirical Methods in Natural…
- 31 August 2019
This work proposes a system that improves over prior entity-projection methods by leveraging machine translation systems twice: first for translating sentences and subsequently for translating entities; and matching entities based on orthographic and phonetic similarity; and identifying matches based on distributional statistics derived from the dataset.
FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation
- Kushal Lakhotia, Bhargavi Paranjape, Asish Ghoshal, Wen-tau Yih, Yashar Mehdad, Srini Iyer
- Computer ScienceConference on Empirical Methods in Natural…
- 31 December 2020
FiD-Ex is developed, which introduces sentence markers to eliminate explanation fabrication by encouraging extractive generation, and uses the fusion-in-decoder architecture to handle long input contexts, and intermediate fine-tuning on re-structured open domain QA datasets to improve few-shot performance.
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
- Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Luke Zettlemoyer, Hannaneh Hajishirzi
- Computer ScienceFindings
- 12 June 2021
Inspired by the contrastive nature of human explanations, large pretrained language models are used to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer.
EASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle
- Haoran Li, Arash Einolghozati, Marjan Ghazvininejad
- Computer ScienceNEWSUM
- 2021
EASE is proposed, an Extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary and is shown that the generated summaries are better than strong extractive and extractive-ABstractive baselines.
Predicting the Temporal and Social Dynamics of Curiosity in Small Group Learning
- Bhargavi Paranjape, Zhen Bai, Justine Cassell
- EducationInternational Conference on Artificial…
- 27 June 2018
A model that predicts the temporal and social dynamics of curiosity based on sequences of behaviors exhibited by individuals engaged in group learning is presented, revealing distinct sequential behavior patterns that predict increase and decrease of curiosity in individuals, and convergence to high and low curiosity among group members.
Contextualized Representations for Low-resource Utterance Tagging
- Bhargavi Paranjape, Graham Neubig
- Computer ScienceSIGDIAL Conferences
- 1 September 2019
Unsupervised training of utterance representations from a large corpus of spontaneous dialogue data achieve competitive performance on utterance-level dialogue-act recognition and emotion classification, especially in low-resource settings encountered when analyzing conversations in new domains.
...
...