1 code implementation • insights (ACL) 2022 • Vinayshekhar Kumar, Vaibhav Kumar, Mukul Bhutani, Alexander Rudnicky
In this work, we examine the problems associated with neural dialog models under the common theme of compositionality.
no code implementations • 3 Mar 2024 • Arijit Ghosh Chowdhury, Md Mofijul Islam, Faysal Hossain Shezan, Vaibhav Kumar, Vinija Jain, Aman Chadha
Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text.
1 code implementation • 19 Feb 2024 • Abhishek Kuriyal, Vaibhav Kumar
Semantic Segmentation (SS) of LiDAR point clouds is essential for many applications, such as urban planning and autonomous driving.
no code implementations • 28 Jan 2024 • Ahmed Magbool, Vaibhav Kumar, Qingqing Wu, Marco Di Renzo, Mark F. Flanagan
Due to the potential of metasurfaces to enhance both communication and sensing performance, numerous papers have explored the performance gains of using metasurfaces to improve ISAC.
no code implementations • 15 Nov 2023 • Minqian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho, Vaibhav Kumar, Reza Ghanadan, Lifu Huang
Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e. g., consistency and naturalness) to obtain a comprehensive assessment.
no code implementations • 27 Jul 2023 • Abhishek Kuriyal, Vaibhav Kumar, Bharat Lohani
The segmentation of point clouds is also essential for many applications.
no code implementations • 3 Jul 2023 • Ahmed Magbool, Vaibhav Kumar, Mark F. Flanagan
In addition, adjusting the fairness design parameter can yield a favorable trade-off between energy efficiency and user fairness compared to methods that exclusively focus on optimizing one of these metrics.
1 code implementation • 30 May 2023 • Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, Emilio Ferrara
We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity).
no code implementations • 5 May 2023 • Vaibhav Kumar, Marwa Chafii, A. Lee Swindlehurst, Le-Nam Tran, Mark F. Flanagan
Integrated sensing and communication (ISAC) is expected to be offered as a fundamental service in the upcoming sixth-generation (6G) communications standard.
no code implementations • 28 Feb 2023 • Vaibhav Kumar, Anastasios Papazafeiropoulos, Muhammad Fainan Hanif, Le-Nam Tran, Mark F. Flanagan
At the same time, the complexity of the proposed scheme grows linearly with the number of IRS elements while that of the benchmark scheme is proportional to the cube of the number of IRS elements.
no code implementations • 15 Nov 2022 • Ahmed Magbool, Vaibhav Kumar, Mark F. Flanagan
In the first stage, we maximize the energy efficiency, and in the second stage we maximize the fairness subject to a minimum energy efficiency constraint.
no code implementations • 1 Sep 2022 • Anshu Mukherjee, Vaibhav Kumar, Derrick Wing Kwan Ng, Le-Nam Tran
Security and energy efficiency have become crucial features in the modern-era wireless communication.
1 code implementation • 25 Aug 2022 • Vaibhav Kumar, Rui Zhang, Marco Di Renzo, Le-Nam Tran
In this letter, we consider the fundamental problem of jointly designing the transmit beamformers and the phase-shifts of the intelligent reflecting surface (IRS) / reconfigurable intelligent surface (RIS) to minimize the transmit power, subject to quality-of-service constraints at individual users in an IRS-assisted multiuser multiple-input single-output downlink communication system.
1 code implementation • SemEval (NAACL) 2022 • Yash Jakhotiya, Vaibhav Kumar, Ashwin Pathak, Raj Shah
In this paper, we train multiple Large Language Models in both the settings and achieve an F1 score (macro) of 0. 73 for the zero shot setting and an F1 score (macro) of 0. 85 for the one shot setting.
no code implementations • 28 Sep 2021 • Tenzin Singhay Bhotia, Vaibhav Kumar, Tanmoy Chakraborty
Euclidean word embedding models such as GloVe and Word2Vec have been shown to reflect human-like gender biases.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Vaibhav Kumar, Jamie Callan
Given an input question, it uses a BERT-based classifier (trained with weak supervision) to de-contextualize the input by selecting relevant terms from the dialog history.
1 code implementation • EMNLP (NLPOSS) 2020 • Tenzin Singhay Bhotia, Vaibhav Kumar
Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora.
no code implementations • 18 Aug 2020 • Vaibhav Kumar, Vikas Raunak, Jamie Callan
Given a natural language query, teaching machines to ask clarifying questions is of immense utility in practical natural language processing systems.
1 code implementation • ACL 2020 • Vaibhav Kumar, Alan W. black
In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange.
1 code implementation • 2 Jun 2020 • Tenzin Singhay Bhotia, Vaibhav Kumar, Tanmoy Chakraborty
We also propose a new bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections.
no code implementations • 4 Nov 2019 • Vikas Raunak, Vaibhav Kumar, Florian Metze
We investigate two specific manifestations of compositionality in Neural Machine Translation (NMT) : (1) Productivity - the ability of the model to extend its predictions beyond the observed length in training data and (2) Systematicity - the ability of the model to systematically recombine known parts and rules.
2 code implementations • WS 2020 • Vikas Raunak, Vaibhav Kumar, Vivek Gupta, Florian Metze
Word embeddings have become a staple of several natural language processing tasks, yet much remains to be understood about their properties.
no code implementations • ACL 2019 • Yash Kumar Lal, Vaibhav Kumar, Mrinal Dhar, Manish Shrivastava, Philipp Koehn
The Collective Encoder captures the overall sentiment of the sentence, while the Specific Encoder utilizes an attention mechanism in order to focus on individual sentiment-bearing sub-words.
1 code implementation • 19 Jan 2019 • Sourya Dipta Das, Himanshu Ladia, Vaibhav Kumar, Shivansh Mishra
This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases.
no code implementations • 2 Aug 2018 • Vaibhav Kumar, Mrinal Dhar, Dhruv Khattar, Yash Kumar Lal, Abhimanshu Mishra, Manish Shrivastava, Vasudeva Varma
We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture.
no code implementations • COLING 2018 • Mrinal Dhar, Vaibhav Kumar, Manish Shrivastava
With the help of the created parallel corpus, we analyzed the structure of English-Hindi code-mixed data and present a technique to augment run-of-the-mill machine translation (MT) approaches that can help achieve superior translations without the need for specially designed translation systems.
no code implementations • 4 Oct 2017 • Vaibhav Kumar, Dhruv Khattar, Siddhartha Gairola, Yash Kumar Lal, Vasudeva Varma
The application of neural networks for this task has only been explored partially.