We present a system that models perception-action coupling through imitation and attention. Our interest is in imitation and in social learning more generally. Through social learning the experience of an agent is governed by the actions of an expert, and the structures that develop within the agent's "brain" are influenced by its social situatedness. We are inspired from biological findings in primates of the existence of mirror neurons, which are believed to be involved in imitation. The visual and motor properties of these neurons suggest a tight perception-action coupling, where affordances could be expressed. Our system is designed to model the functional properties of the mirror neurons and therefore express the functionality of objects. The system builds up perceptual and motoric structures from experience using temporal attention and forms perceptual-motor connections. The experience arises through imitation, where an agent can perceive objects and the interactions upon them. We have successfully applied our system on three different platforms, two in simulation and the third on a real robot learning from a human. The system is able to segment the perceptual-motor experience into distinct structures that can be used to recognize and reproduce the task in each experiment. Some unexpected results showed us that the motoric complexity in these experiments was not high enough to expose the full potential of our system, and we suggest future work that will address these results.
This article presents an investigation of corpus-based methods for the automation of help-desk e-mail responses. Specifically, we investigate this problem along two operational dimensions: (1) information-gathering technique, and (2) granularity of the information. We consider two information-gathering techniques (retrieval and prediction) applied to information represented at two levels of granularity (document-level and sentence-level). Document-level methods correspond to the reuse of an existing response e-mail to address new requests. Sentence-level methods correspond to applying extractive multi-document summarization techniques to collate units of information from more than one e-mail. Evaluation of the performance of the different methods shows that in combination they are able to successfully automate the generation of responses for a substantial portion of e-mail requests in our corpus. We also investigate a meta-selection process that learns to choose one method to address a new inquiry e-mail, thus providing a unified response automation solution.
Introduction. This paper describes the first step in a project for topic identification in help-desk applications. In this step, we apply a clustering mechanism to identify the topics of newsgroup discussions. We have used newsgroup discussions as our testbed, as they provide a good approximation to our target application, while obviating the need for manual tagging of topics.We have found that the postings of individuals who contribute repeatedly to a newsgroup may lead the clustering process astray, in the sense that discussions may be grouped according to their author, rather than according to their topic. To address this problem, we introduce a filtering mechanism, and evaluate it by comparing clustering performance with and without filtering.
The work presented in this paper is the first step in a project which aims to cluster and summarise electronic discussions in the context of help-desk applications. The eventual objective of this project is to use these summaries to assist help-desk users and operators. In this paper, we identify features of electronic discussions that influence the clustering process, and offer a filtering mechanism that removes undesirable influences. We tested the clustering and filtering processes on electronic newsgroup discussions, and evaluated their performance by means of two experiments: coarse-level clustering and simple information retrieval. Our evaluation shows that our filtering mechanism has a significant positive effect on both tasks.
Abstract. We present a corpus-based approach for the automatic analysis and synthesis of email responses to help-desk requests. This approach can be used to automatically deal with repetitive requests of low technical content, thus enabling help-desk operators to focus their effort on more difficult requests. We propose a method for extracting high-precision sentences for inclusion in a response, and a measure for predicting the completeness of a planned response. The idea is that complete, high-precision responses may be sent directly to users, while incomplete responses should be passed to operators. Our results show that a small but significant proportion (14%) of our automatically generated responses have a high degree of precision and completeness, and that our measure can reliably predict the completeness of a response.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.