Investigating Transparency Methods in a Robot Word-Learning System and Their Effects on Human Teaching Behaviors

Author(s):  
Matthias Hirschmanner ◽  
Stephanie Gross ◽  
Setareh Zafari ◽  
Brigitte Krenn ◽  
Friedrich Neubarth ◽  
...  
2007 ◽  
Vol 8 (1) ◽  
pp. 53-81 ◽  
Author(s):  
Luís Seabra Lopes ◽  
Aneesh Chauhan

This paper addresses word learning for human–robot interaction. The focus is on making a robotic agent aware of its surroundings, by having it learn the names of the objects it can find. The human user, acting as instructor, can help the robotic agent ground the words used to refer to those objects. A lifelong learning system, based on one-class learning, was developed (OCLL). This system is incremental and evolves with the presentation of any new word, which acts as a class to the robot, relying on instructor feedback. A novel experimental evaluation methodology, that takes into account the open-ended nature of word learning, is proposed and applied. This methodology is based on the realization that a robot’s vocabulary will be limited by its discriminatory capacity which, in turn, depends on its sensors and perceptual capabilities. The results indicate that the robot’s representations are capable of incrementally evolving by correcting class descriptions, based on instructor feedback to classification results. In successive experiments, it was possible for the robot to learn between 6 and 12 names of real-world office objects. Although these results are comparable to those obtained by other authors, there is a need to scale-up. The limitations of the method are discussed and potential directions for improvement are pointed out.


2016 ◽  
Vol 75 (21) ◽  
pp. 13179-13192 ◽  
Author(s):  
Bong-Hyun Kim ◽  
Ki-Chan Kim ◽  
Sang-Young Oh ◽  
Sung-Eon Hong

2001 ◽  
Vol 24 (6) ◽  
pp. 1110-1111 ◽  
Author(s):  
Frank C. Keil

Bloom makes a strong case that word meaning acquisition does not require a dedicated word learning system. This conclusion, however, does not argue against a dedicated language acquisition system for syntax, morphology, and aspects of semantics. Critical questions are raised as to why word meaning should be so different from other aspects of language in the course of acquisition.


2006 ◽  
Vol 27 (4) ◽  
pp. 599-613 ◽  
Author(s):  
SUSAN E. GATHERCOLE

Because words represent the building blocks upon which the facility to produce and comprehend language at all levels is based, the capacity of a child to learn words has immense impact on his or her developing abilities to communicate and engage properly with the outside world. Both the Keynote Article and the Commentaries in this issue demonstrate that this capacity to acquire vocabulary is neither singular nor simple. Children may fail to learn new words in as rapid and efficient manner as their peers for many reasons: they may, for example, have inadequate environmental experience of either the spoken and printed form of the language (Huttenlocher, Haight, Bryk, Seltzer, & Lyons, 1991), or they may have poor abilities to produce the sound contrasts of the language (Mirak & Rescorla, 1998). The focus of the present discussion lies somewhere in between these extremes of influence, in the intervening perceptual and cognitive processes that constitute the speech processing and word learning system. Here, too, complexities abound. The developing language system is characterized by dependencies between the multiple processes involved in processing and learning language (Bishop, 1997), rarely evincing the dramatic dissociations in adults with acquired language disorders that have served cognitive neuropsychology so well in its bid to identify a modular structure of the language system. Weaknesses in perceptual analysis of the sound structure of the language, in the storage of the resulting mental representations, and in the availability of existing representations that can support the processing of new words, often coexist within an individual. As a consequence, it can be extremely difficult to tease apart the developmental underpinnings of language acquisition. In this article, I argue that real progress toward understanding vocabulary acquisition requires a substantial and systematic body of research evidence designed to provide strong empirical challenges to existing (and new) hypotheses and theories. Whereas mere description is unlikely to lead to major advances, systematic experimental analysis and the specification of detailed theoretical accounts should result in a more complete understanding of the complexities and constraints of new word learning.


2021 ◽  
Author(s):  
Thomas Wilschut ◽  
Florian Sense ◽  
Maarten van der Velde ◽  
Zafeirios Fountas ◽  
Sarah Maass ◽  
...  

Memorising vocabulary is an important aspect of formal foreign-language learning. Advances in cognitive psychology have led to the development of adaptive learning systems that make vocabulary learning more efficient. One way these computer-based systems optimize learning is by measuring learning performance in real time to create optimal repetition schedules for individual learners. While such adaptive learning systems have been successfully applied to word learning using keyboard-based input, they have thus far seen little application in spoken word learning. Here we present a system for adaptive, speech-based word learning using an adaptive model that was developed for and tested with typing-based word learning. We show that typing- and speech-based learning result in similar behavioral patterns that can be used to reliably estimate individual memory processes, and we extend earlier findings demonstrating that a response-time based adaptive learning system outperforms an accuracy-based, Leitner flashcard learning algorithm. In short, we show that adaptive learning benefits transfer from typing-based learning, to speech based learning. Our work provides a basis for the development of language learning applications that use real-time pronunciation assessment software to score the accuracy of the learner's pronunciations. The development of adaptive, speech-based learning applications is important for two reasons. First, by focusing on speech, the model can be applied for individuals whose typing skills are insufficient---as is demonstrated by the successful application of the model in an elderly participant population. Second, speech-based learning models are educationally relevant because they focus on what may be the most important aspect of language learning: to practice speech.


2019 ◽  
Vol 50 (4) ◽  
pp. 461-465 ◽  
Author(s):  
Suzanne M. Adlof

Purpose This prologue introduces the LSHSS Forum: Vocabulary Across the School Grades. The goals of the forum are to provide an overview of the importance of vocabulary to literacy and academic achievement, to review evidence regarding best practices for vocabulary instruction, and to highlight recent research related to word learning with students across different grade levels. Method The prologue provides a foundational overview of vocabulary's role in literacy and introduces the topics of the other ten articles in the forum. These include clinical focus articles, research reviews, and word-learning and vocabulary intervention studies involving students in elementary grades through college. Conclusion Children with language and reading disorders experience specific challenges learning new words, but all students can benefit from high-quality vocabulary instruction. The articles in this issue highlight the characteristics of evidence-based vocabulary interventions for children of different ages, ability levels, and language backgrounds and provide numerous examples of intervention activities that can be modified for use in individual, small-group, or large-group instructional settings.


Sign in / Sign up

Export Citation Format

Share Document