Language Acquisition: Learning a Hierarchy of Phrases
نویسنده
چکیده
Current Address: GE Corporate Research and Development Schenectady, New York 12301 The hierarchical lexicon, in contrast to the traditional flat lexicon, enables a linguistic model to perform even in situations of incomplete knowledge: when a specific entry is missing, a more general entry can cover the gap. The question still remains regarding the construction of the lexicon itself. Since the lexicon is organized as a hierarchy, and not as a flat structure, phrases cannot simply be placed in the lexicon: they must be interconnected with other phrases in the hierarchy at the appropriate level of generality. Furthermore, since input examples arc always given in terms of specific phrases, phrases must be propagated up and down the hierarchy, starting at the bottom level. In this paper we describe a learning algorithm which is based on two existing machine-learning models: learning in a version space [Mitchell82], and learning by accumulating specific episodes in a dynamic memory [Kolodner84, Schank82]. The input required by the algorithm is a sequence of specific episodes, or training examples, from which lexical entries at various levels in the hierarchy arc generalized and specialized. The algorithm is embodied by the program RINA [Zernik87b] which models learning English phrases by a second language speaker.
منابع مشابه
Use of Articles in Learning English as a Foreign Language: A Study of Iranian English Undergraduates
The significance of error analysis for the learner, the teacher and the researcher is now widely recognized. Earlier studies of error analysis concentrated on intersystematic comparison of the “native language” and the “target language” and drew the required data largely from intuitions and impressionistic observations. This study was conducted on the basis of the following observations: (1) to...
متن کاملAspects of Culture in Second Language Acquisition and Foreign Language Learning, J. Arabski & A. Wojtaszek (2011), ISBN 9783642202001
متن کامل
Learning Natural Language Filtering under Noisy Conditions
This paper describes a novel AI technique, called plausibility networks, that allows for learning to l-ter natural language phrases according to predeened classes under noisy conditions. We describe the automatic knowledge acquisition for representing the words of natural language phrases using signiicance vectors and the learning of ltering of phrases according to ten diierent domain classes. ...
متن کاملTowards a definition of intake in second language acquisition
Intake is a concept that has long fascinated second language researchers as it provides a window onto the crucial intermediary stage between input and acquisition. A better understanding of this intermediary stage can help us to distinguish between input that is used for immediate (e.g. communicative) purposes only and input that is drawn on for learning. This articl...
متن کاملComparing Experiential Approaches: Structured Language Learning Experiences versus Conversation Partners for Changing Pre-Service Teacher Beliefs
Research has shown that language teachers’ beliefs are often difficult to change through education. Experiential learning may help, but more research is needed to understand how experiential approaches shape perceptions. This study compares two approaches, conversation partners (CONV) and structured language learning experiences (SLLE), integrated into a course in language acquisition. Partici...
متن کامل