Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Pinhanez, Claudio"'
Autor:
Pinhanez, Claudio, Cavalin, Paulo, Storto, Luciana, Finbow, Thomas, Cobbinah, Alexander, Nogima, Julio, Vasconcelos, Marisa, Domingues, Pedro, Mizukami, Priscila de Souza, Grell, Nicole, Gongora, Majoí, Gonçalves, Isabel
Since 2022 we have been exploring application areas and technologies in which Artificial Intelligence (AI) and modern Natural Language Processing (NLP), such as Large Language Models (LLMs), can be employed to foster the usage and facilitate the docu
Externí odkaz:
http://arxiv.org/abs/2407.12620
In this paper we show that corpus-level aggregation hinders considerably the capability of lexical metrics to accurately evaluate machine translation (MT) systems. With empirical experiments we demonstrate that averaging individual segment-level scor
Externí odkaz:
http://arxiv.org/abs/2407.12832
Representations of AI agents in user interfaces and robotics are predominantly White, not only in terms of facial and skin features, but also in the synthetic voices they use. In this paper we explore some unexpected challenges in the representation
Externí odkaz:
http://arxiv.org/abs/2403.11209
Autor:
Pinhanez, Claudio, Cavalin, Paulo
This work explores the intrinsic limitations of the popular one-hot encoding method in classification of intents when detection of out-of-scope (OOS) inputs is required. Although recent work has shown that there can be significant improvements in OOS
Externí odkaz:
http://arxiv.org/abs/2205.09021
Autor:
Pinhanez, Claudio S., Flores, German H., Vasconcelos, Marisa A., Qiao, Mu, Linck, Nick, de Paula, Rogério, Ong, Yuya J.
How can we best address the dangerous impact that deep learning-generated fake audios, photographs, and videos (a.k.a. deepfakes) may have in personal and societal life? We foresee that the availability of cheap deepfake technology will create a seco
Externí odkaz:
http://arxiv.org/abs/2204.01489
Autor:
Pinhanez, Claudio S.
In this position paper, I argue that the best way to help and protect humans using AI technology is to make them aware of the intrinsic limitations and problems of AI algorithms. To accomplish this, I suggest three ethical guidelines to be used in th
Externí odkaz:
http://arxiv.org/abs/2112.01281
Autor:
Pinhanez, Claudio, Cavalin, Paulo, Ribeiro, Victor, Candello, Heloisa, Nogima, Julio, Appel, Ana, Pichiliani, Mauro, de Bayser, Maira Gatti, Guerra, Melina, Ferreira, Henrique, Malfatti, Gabriel
In this paper we explore the use of meta-knowledge embedded in intent identifiers to improve intent recognition in conversational systems. As evidenced by the analysis of thousands of real-world chatbots and in interviews with professional chatbot cu
Externí odkaz:
http://arxiv.org/abs/2012.09005
To predict the next most likely participant to interact in a multi-party conversation is a difficult problem. In a text-based chat group, the only information available is the sender, the content of the text and the dialogue history. In this paper we
Externí odkaz:
http://arxiv.org/abs/2001.06350
Autor:
Pinhanez, Claudio
This paper argues that a possible way to escape from the limitations of current machine learning (ML) systems is to allow their development directly by domain experts without the mediation of ML experts. This could be accomplished by making ML system
Externí odkaz:
http://arxiv.org/abs/1908.08931
This paper investigates the application of machine learning (ML) techniques to enable intelligent systems to learn multi-party turn-taking models from dialogue logs. The specific ML task consists of determining who speaks next, after each utterance o
Externí odkaz:
http://arxiv.org/abs/1907.02090