zunia.vn

Tuyển sinh 2024 dành cho Gen-Z

zunia.vn

» Luận Văn - Báo Cáo

» Báo cáo khoa học

Báo cáo khoa học: "Computational Modeling of Human Language Acquisition"

Chia sẻ: Hongphan_1 Hongphan_1 | Ngày: | Loại File: PDF | Số trang:1

Báo xấu

68
lượt xem 2
download

Download Vui lòng tải xuống để xem tài liệu đầy đủ

The nature and amount of information needed for learning a natural language, and the underlying mechanisms involved in this process, are the subject of much debate: is it possible to learn a language from usage data only, or some sort of innate knowledge and/or bias is needed to boost the process? This is a topic of interest to (psycho)linguists who study human language acquisition, as well as computational linguists who develop the knowledge sources necessary for largescale natural language processing systems. ...

Chủ đề:

Bình luận(0) Đăng nhập để gửi bình luận!

Lưu

Nội dung Text: Báo cáo khoa học: "Computational Modeling of Human Language Acquisition"

Computational Modeling of Human Language Acquisition Afra Alishahi Department of Computational Linguistics and Phonetics Saarland University, Germany afra@coli.uni-saarland.de 1 Introduction and will review common approaches and tech- niques used in developing such models. Compu- The nature and amount of information needed tational modeling has been vastly applied to dif- for learning a natural language, and the under- ferent domains of language acquisition, including lying mechanisms involved in this process, are word segmentation and phonology, morphology, the subject of much debate: is it possible to syntax, semantics and discourse. However, due to learn a language from usage data only, or some time restrictions, the focus of the tutorial will be sort of innate knowledge and/or bias is needed on the acquisition of word meaning, syntax, and to boost the process? This is a topic of inter- the relationship between syntax and semantics. est to (psycho)linguists who study human lan- The ﬁrst part of the tutorial focuses on some of guage acquisition, as well as computational lin- the fundamental issues in the study of human lan- guists who develop the knowledge sources nec- guage acquisition, and the role of computational essary for largescale natural language process- modeling in addressing these issues. Speciﬁcally, ing systems. Children are a source of inspira- we discuss language modularity, i.e. the represen- tion for any such study of language learnability. tation and acquisition of various aspects of lan- They learn language with ease, and their acquired guage, and the interaction between these aspects. knowledge of language is ﬂexible and robust. We also review the major arguments on language Human language acquisition has been studied learnability and innateness. We then give a general for centuries, but using computational modeling overview of how computational modeling is used for such studies is a relatively recent trend. How- for investigating different views on each of these ever, computational approaches to language learn- topics, how the theoretical assumptions are inte- ing have become increasing popular, mainly due grated into computational models, and how such to the advances in developing machine learning models are evaluated based on the experimental techniques, and the availability of vast collections observations. of experimental data on child language learning In the second part of the tutorial, we will take and child-adult interaction. Many of the existing a closer look at some of the existing models of computational models attempt to study the com- language learning. We discuss general trends in plex task of learning a language under the cogni- computational modeling over the past decades, in- tive plausibility criteria (such as memory and pro- cluding symbolic, connectionist, and probabilistic cessing limitations that humans face), as well as modeling. We review a number of more inﬂuential to explain the developmental patterns observed in models of the acquisition of syntax and semantics, children. Such computational studies can provide and the link between the two. Finally, we explore insight into the plausible mechanisms involved in some of the available tools and resources for im- human language acquisition, and be a source of plementing and evaluating computational models inspiration for developing better language models of language acquisition. and techniques. 2 Content Overview This tutorial will discuss the main research ques- tions that the researchers in the ﬁeld of compu- tational language acquisition are concerned with, 4 Tutorial Abstracts of ACL-IJCNLP 2009, page 4, Suntec, Singapore, 2 August 2009. c 2009 ACL and AFNLP

CÓ THỂ BẠN MUỐN DOWNLOAD

LV.11: Bộ Luận Văn Tốt Nghiệp Chuyên Ngành Tài Chính Ngân Hàng

172 tài liệu

845 lượt tải

THÔNG TIN

TRỢ GIÚP

HỖ TRỢ KHÁCH HÀNG

Theo dõi chúng tôi

Chịu trách nhiệm nội dung:

Nguyễn Công Hà - Giám đốc Công ty TNHH TÀI LIỆU TRỰC TUYẾN VI NA

LIÊN HỆ

Địa chỉ: P402, 54A Nơ Trang Long, Phường 14, Q.Bình Thạnh, TP.HCM

Hotline: 093 303 0098

Email: support@tailieu.vn

Giấy phép Mạng Xã Hội số: 670/GP-BTTTT cấp ngày 30/11/2015 Copyright © 2022-2032 TaiLieu.VN. All rights reserved.