Zobrazeno 1 - 10
of 45
pro vyhledávání: '"P. Chulaka"'
Language models are now deployed in a wide variety of user-facing applications, often for specific purposes like answering questions about documentation or acting as coding assistants. As these models are intended for particular purposes, they should
Externí odkaz:
http://arxiv.org/abs/2410.21597
Autor:
Lee, Young-Suk, Gunasekara, Chulaka, Contractor, Danish, Astudillo, Ramón Fernandez, Florian, Radu
We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT
Externí odkaz:
http://arxiv.org/abs/2409.11500
Autor:
Abdelaziz, Ibrahim, Basu, Kinjal, Agarwal, Mayank, Kumaravel, Sadhana, Stallone, Matthew, Panda, Rameswar, Rizk, Yara, Bhargav, GP, Crouse, Maxwell, Gunasekara, Chulaka, Ikbal, Shajith, Joshi, Sachin, Karanam, Hima, Kumar, Vineet, Munawar, Asim, Neelam, Sumit, Raghu, Dinesh, Sharma, Udit, Soria, Adriana Meza, Sreedhar, Dheeraj, Venkateswaran, Praveen, Unuvar, Merve, Cox, David, Roukos, Salim, Lastras, Luis, Kapanipathi, Pavan
Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challenging benchmarks like SWE-Bench and Agent-Bench. However, to realize the t
Externí odkaz:
http://arxiv.org/abs/2407.00121
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:
Murugesan, Keerthiram, Swaminathan, Sarathkrishna, Dan, Soham, Chaudhury, Subhajit, Gunasekara, Chulaka, Crouse, Maxwell, Mahajan, Diwakar, Abdelaziz, Ibrahim, Fokoue, Achille, Kapanipathi, Pavan, Roukos, Salim, Gray, Alexander
With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metr
Externí odkaz:
http://arxiv.org/abs/2306.10452
Autor:
Gera, Ariel, Friedman, Roni, Arviv, Ofir, Gunasekara, Chulaka, Sznajder, Benjamin, Slonim, Noam, Shnarch, Eyal
Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative. In this work, we argue that due to the g
Externí odkaz:
http://arxiv.org/abs/2305.01628
Autor:
Murthy V, Rudra, Bhat, Riyaz, Gunasekara, Chulaka, Patel, Siva Sankalp, Wan, Hui, Dhamecha, Tejas Indulal, Contractor, Danish, Danilevsky, Marina
In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity
Externí odkaz:
http://arxiv.org/abs/2301.01015
Autor:
Sznajder, Benjamin, Gunasekara, Chulaka, Lev, Guy, Joshi, Sachin, Shnarch, Eyal, Slonim, Noam
Many organizations require their customer-care agents to manually summarize their conversations with customers. These summaries are vital for decision making purposes of the organizations. The perspective of the summary that is required to be created
Externí odkaz:
http://arxiv.org/abs/2203.15590
Autor:
Feigenblat, Guy, Gunasekara, Chulaka, Sznajder, Benjamin, Joshi, Sachindra, Konopnicki, David, Aharonov, Ranit
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP (2021) 245--260
In a typical customer service chat scenario, customers contact a support center to ask for help or raise complaints, and human agents try to solve the issues. In most cases, at the end of the conversation, agents are asked to write a short summary em
Externí odkaz:
http://arxiv.org/abs/2111.11894
Autor:
Gunasekara, Chulaka, Feigenblat, Guy, Sznajder, Benjamin, Joshi, Sachindra, Konopnicki, David
Many conversation datasets have been constructed in the recent years using crowdsourcing. However, the data collection process can be time consuming and presents many challenges to ensure data quality. Since language generation has improved immensely
Externí odkaz:
http://arxiv.org/abs/2106.03337