Diego Martín

Diego Martín, Jordi Sanchez, Xavier Vizcaíno

This study investigates different approaches to classify human interactions in an artificial intelligence-based environment, specifically for Applus+ IDIADA's intelligent agent AIDA. The main objective is to develop a classifier that accurately identifies the type of interaction received (Conversation, Services, or Document Translation) to direct requests to the appropriate channel and provide a more specialized and efficient service. Various models are compared, including LLM-based classifiers, KNN using Titan and Cohere embeddings, SVM, and artificial neural networks. Results show that SVM and ANN models with Cohere embeddings achieve the best overall performance, with superior F1 scores and faster execution times compared to LLM-based approaches. The study concludes that the SVM model with Cohere embeddings is the most suitable option for classifying human interactions in the AIDA environment, offering an optimal balance between accuracy and computational efficiency.

Julián Urbano, Mónica Marrero, Diego Martín et al.

The third Information Retrieval Education through EXperimentation track (EIREX 2012) was run at the University Carlos III of Madrid, during the 2012 spring semester. EIREX 2012 is the third in a series of experiments designed to foster new Information Retrieval (IR) education methodologies and resources, with the specific goal of teaching undergraduate IR courses from an experimental perspective. For an introduction to the motivation behind the EIREX experiments, see the first sections of [Urbano et al., 2011a]. For information on other editions of EIREX and related data, see the website at http://ir.kr.inf.uc3m.es/eirex/. The EIREX series have the following goals: a) to help students get a view of the Information Retrieval process as they would find it in a real-world scenario, either industrial or academic; b) to make students realize the importance of laboratory experiments in Computer Science and have them initiated in their execution and analysis; c) to create a public repository of resources to teach Information Retrieval courses; d) to seek the collaboration and active participation of other Universities in this endeavor. This overview paper summarizes the results of the EIREX 2012 track, focusing on the creation of the test collection and the analysis to assess its reliability.

Julián Urbano, Diego Martín, Mónica Marrero et al.

The second Information Retrieval Education through EXperimentation track (EIREX 2011) was run at the University Carlos III of Madrid, during the 2011 spring semester. EIREX 2011 is the second in a series of experiments designed to foster new Information Retrieval (IR) education methodologies and resources, with the specific goal of teaching undergraduate IR courses from an experimental perspective. For an introduction to the motivation behind the EIREX experiments, see the first sections of [Urbano et al., 2011a]. For information on other editions of EIREX and related data, see the website at http://ir.kr.inf.uc3m.es/eirex/. The EIREX series have the following goals: a) to help students get a view of the Information Retrieval process as they would find it in a real-world scenario, either industrial or academic; b) to make students realize the importance of laboratory experiments in Computer Science and have them initiated in their execution and analysis; c) to create a public repository of resources to teach Information Retrieval courses; d) to seek the collaboration and active participation of other Universities in this endeavor. This overview paper summarizes the results of the EIREX 2011 track, focusing on the creation of the test collection and the analysis to assess its reliability.