Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Fadnis, Kshitij"'
Autor:
Fadnis, Kshitij, Patel, Siva Sankalp, Boni, Odellia, Katsis, Yannis, Rosenthal, Sara, Sznajder, Benjamin, Danilevsky, Marina
Large Language Models (LLM) have become a popular approach for implementing Retrieval Augmented Generation (RAG) systems, and a significant amount of effort has been spent on building good models and metrics. In spite of increased recognition of the
Externí odkaz:
http://arxiv.org/abs/2404.17347
Autor:
Sil, Avirup, Sen, Jaydeep, Iyer, Bhavani, Franz, Martin, Fadnis, Kshitij, Bornea, Mihaela, Rosenthal, Sara, McCarley, Scott, Zhang, Rong, Kumar, Vishwajeet, Li, Yulong, Sultan, Md Arafat, Bhat, Riyaz, Florian, Radu, Roukos, Salim
The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets with leaderboards, and novel algorithms for key components such as retrie
Externí odkaz:
http://arxiv.org/abs/2301.09715
Autor:
Agarwal, Mayank, Barroso, Jorge J., Chakraborti, Tathagata, Dow, Eli M., Fadnis, Kshitij, Godoy, Borja, Pallan, Madhavan, Talamadupula, Kartik
This whitepaper reports on Project CLAI (Command Line AI), which aims to bring the power of AI to the command line interface (CLI). The CLAI platform sets up the CLI as a new environment for AI researchers to conquer by surfacing the command line as
Externí odkaz:
http://arxiv.org/abs/2002.00762
Autor:
Kapanipathi, Pavan, Thost, Veronika, Patel, Siva Sankalp, Whitehead, Spencer, Abdelaziz, Ibrahim, Balakrishnan, Avinash, Chang, Maria, Fadnis, Kshitij, Gunasekara, Chulaka, Makni, Bassem, Mattei, Nicholas, Talamadupula, Kartik, Fokoue, Achille
Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like
Externí odkaz:
http://arxiv.org/abs/1911.02060
Autor:
Fadnis, Kshitij, Talamadupula, Kartik, Kapanipathi, Pavan, Ishfaq, Haque, Roukos, Salim, Fokoue, Achille
In this paper, we introduce the problem of knowledge graph contextualization -- that is, given a specific NLP task, the problem of extracting meaningful and relevant sub-graphs from a given knowledge graph. The task in the case of this paper is the t
Externí odkaz:
http://arxiv.org/abs/1911.02085
Goal-oriented dialog systems, which can be trained end-to-end without manually encoding domain-specific features, show tremendous promise in the customer support use-case e.g. flight booking, hotel reservation, technical support, student advising etc
Externí odkaz:
http://arxiv.org/abs/1907.05792
Autor:
Gunasekara, R. Chulaka, Nahamoo, David, Polymenakos, Lazaros C., Ganhotra, Jatin, Fadnis, Kshitij P.
We propose a novel methodology to address dialog learning in the context of goal-oriented conversational systems. The key idea is to quantize the dialog space into clusters and create a language model across the clusters, thus allowing for an accurat
Externí odkaz:
http://arxiv.org/abs/1812.10356
Autor:
Feng, Song, Gunasekara, R. Chulaka, Shashidhara, Sunil, Fadnis, Kshitij P., Polymenakos, Lazaros C.
We propose a unified Implicit Dialog framework for goal-oriented, information seeking tasks of Conversational Search applications. It aims to enable dialog interactions with domain data without replying on explicitly encoded the rules but utilizing t
Externí odkaz:
http://arxiv.org/abs/1802.04358
Autor:
Chakraborti, Tathagata, Fadnis, Kshitij P., Talamadupula, Kartik, Dholakia, Mishal, Srivastava, Biplav, Kephart, Jeffrey O., Bellamy, Rachel K. E.
In this paper, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human in the loop decision making. Imposing transparency and explainability requirements on such agents is especially important in
Externí odkaz:
http://arxiv.org/abs/1709.04517
Autor:
Chakraborti, Tathagata, Talamadupula, Kartik, Fadnis, Kshitij P., Campbell, Murray, Kambhampati, Subbarao
In this paper, we present UbuntuWorld 1.0 LTS - a platform for developing automated technical support agents in the Ubuntu operating system. Specifically, we propose to use the Bash terminal as a simulator of the Ubuntu environment for a learning-bas
Externí odkaz:
http://arxiv.org/abs/1609.08524