Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Ganhotra, Jatin"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 375-386 (2019)
Neural end-to-end goal-oriented dialog systems showed promise to reduce the workload of human agents for customer service, as well as reduce wait time for users. However, their inability to handle new user behavior at deployment has limited their usa
Externí odkaz:
https://doaj.org/article/06ee39ed9d7443a3b56f2cbda7b1279c
We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations using a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the
Externí odkaz:
http://arxiv.org/abs/2402.11770
Autor:
Gupta, Ankita, Gunasekara, Chulaka, Wan, Hui, Ganhotra, Jatin, Joshi, Sachindra, Danilevsky, Marina
Dialogue summarization task involves summarizing long conversations while preserving the most salient information. Real-life dialogues often involve naturally occurring variations (e.g., repetitions, hesitations) and existing dialogue summarization m
Externí odkaz:
http://arxiv.org/abs/2311.08705
Autor:
Liu, Si, Ganhotra, Jatin, Rahman, Muntasir Raihan, Nguyen, Son, Gupta, Indranil, Meseguer, José
Publikováno v:
Leibniz Transactions on Embedded Systems, Vol 4, Iss 1, Pp 03:1-03:26 (2017)
The promise of high scalability and availability has prompted many companies to replace traditional relational database management systems (RDBMS) with NoSQL key-value stores. This comes at the cost of relaxed consistency guarantees: key-value stores
Externí odkaz:
https://doaj.org/article/7d16402990b14d9d88cdebda4ebc7fe8
Autor:
Sunder, Vishal, Thomas, Samuel, Kuo, Hong-Kwang J., Ganhotra, Jatin, Kingsbury, Brian, Fosler-Lussier, Eric
Dialog history plays an important role in spoken language understanding (SLU) performance in a dialog system. For end-to-end (E2E) SLU, previous work has used dialog history in text form, which makes the model dependent on a cascaded automatic speech
Externí odkaz:
http://arxiv.org/abs/2204.05169
Autor:
Ganhotra, Jatin, Thomas, Samuel, Kuo, Hong-Kwang J., Joshi, Sachindra, Saon, George, Tüske, Zoltán, Kingsbury, Brian
End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are very much
Externí odkaz:
http://arxiv.org/abs/2108.08405
Autor:
Chen, Hanjie, Feng, Song, Ganhotra, Jatin, Wan, Hui, Gunasekara, Chulaka, Joshi, Sachindra, Ji, Yangfeng
Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting
Externí odkaz:
http://arxiv.org/abs/2104.04488
Autor:
Ganhotra, Jatin, Joshi, Sachindra
In the last few years, the release of BERT, a multilingual transformer based model, has taken the NLP community by storm. BERT-based models have achieved state-of-the-art results on various NLP tasks, including dialog tasks. One of the limitation of
Externí odkaz:
http://arxiv.org/abs/2101.09647
Autor:
Ganhotra, Jatin, Roitman, Haggai, Cohen, Doron, Mills, Nathaniel, Gunasekara, Chulaka, Mass, Yosi, Joshi, Sachindra, Lastras, Luis, Konopnicki, David
A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs. We study the task of predicting the documents that customer care agents can use to facilitate users' needs. We also in
Externí odkaz:
http://arxiv.org/abs/2010.02305
Existing benchmarks used to evaluate the performance of end-to-end neural dialog systems lack a key component: natural variation present in human conversations. Most datasets are constructed through crowdsourcing, where the crowd workers follow a fix
Externí odkaz:
http://arxiv.org/abs/2010.02260