Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Alikhani, Malihe"'
Autor:
Kennington, Casey, Alikhani, Malihe, Pon-Barry, Heather, Atwell, Katherine, Bisk, Yonatan, Fried, Daniel, Gervits, Felix, Han, Zhao, Inan, Mert, Johnston, Michael, Korpan, Raj, Litman, Diane, Marge, Matthew, Matuszek, Cynthia, Mead, Ross, Mohan, Shiwali, Mooney, Raymond, Parde, Natalie, Sinapov, Jivko, Stewart, Angela, Stone, Matthew, Tellex, Stefanie, Williams, Tom
The ability to interact with machines using natural human language is becoming not just commonplace, but expected. The next step is not just text interfaces, but speech interfaces and not just with computers, but with all machines including robots. I
Externí odkaz:
http://arxiv.org/abs/2404.01158
Addressing the critical shortage of mental health resources for effective screening, diagnosis, and treatment remains a significant challenge. This scarcity underscores the need for innovative solutions, particularly in enhancing the accessibility an
Externí odkaz:
http://arxiv.org/abs/2402.08837
Effective interlocutors account for the uncertain goals, beliefs, and emotions of others. But even the best human conversationalist cannot perfectly anticipate the trajectory of a dialogue. How well can language models represent inherent uncertainty
Externí odkaz:
http://arxiv.org/abs/2402.03284
Autor:
Sicilia, Anthony, Alikhani, Malihe
The ingrained principles of fairness in a dialogue system's decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. Absence of equitable and inclusive principles can hinder the formation of
Externí odkaz:
http://arxiv.org/abs/2307.04303
Autor:
Hassan, Sabit, Alikhani, Malihe
Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in our lives
Externí odkaz:
http://arxiv.org/abs/2305.17013
While demographic factors like age and gender change the way people talk, and in particular, the way people talk to machines, there is little investigation into how large pre-trained language models (LMs) can adapt to these changes. To remedy this ga
Externí odkaz:
http://arxiv.org/abs/2305.14195
Content moderation is the process of flagging content based on pre-defined platform rules. There has been a growing need for AI moderators to safeguard users as well as protect the mental health of human moderators from traumatic content. While prior
Externí odkaz:
http://arxiv.org/abs/2302.09618
Autor:
Kim, Hyunwoo, Hessel, Jack, Jiang, Liwei, West, Peter, Lu, Ximing, Yu, Youngjae, Zhou, Pei, Bras, Ronan Le, Alikhani, Malihe, Kim, Gunhee, Sap, Maarten, Choi, Yejin
Data scarcity has been a long standing issue in the field of open-domain social dialogue. To quench this thirst, we present SODA: the first publicly available, million-scale high-quality social dialogue dataset. By contextualizing social commonsense
Externí odkaz:
http://arxiv.org/abs/2212.10465
Autor:
Sicilia, Anthony, Alikhani, Malihe
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical underst
Externí odkaz:
http://arxiv.org/abs/2210.07777
Using style-transfer models to reduce offensiveness of social media comments can help foster a more inclusive environment. However, there are no sizable datasets that contain offensive texts and their inoffensive counterparts, and fine-tuning pretrai
Externí odkaz:
http://arxiv.org/abs/2209.08207