On Memory Limitations in Natural Language Processing

This paper proposes a welcome hypothesis: a computationally simple device is sufficient for processing natural language. Traditionally it has been argued that processing natural language syntax requires very powerful machinery. Many engineers have come to this rather grim conclusion: almost all wo...

Full description

Bibliographic Details
Main Author: Church, Kenneth Ward
Other Authors: Szolovits, Peter
Published: 2023
Online Access:https://hdl.handle.net/1721.1/149526
_version_ 1826211907741155328
author Church, Kenneth Ward
author2 Szolovits, Peter
author_facet Szolovits, Peter
Church, Kenneth Ward
author_sort Church, Kenneth Ward
collection MIT
description This paper proposes a welcome hypothesis: a computationally simple device is sufficient for processing natural language. Traditionally it has been argued that processing natural language syntax requires very powerful machinery. Many engineers have come to this rather grim conclusion: almost all working parsers are actually Turing Machines (TM). For example, Woods specifically designed his Augmented Transition Networks (ATNs) to be Turing Equivalent.
first_indexed 2024-09-23T15:13:20Z
id mit-1721.1/149526
institution Massachusetts Institute of Technology
last_indexed 2024-09-23T15:13:20Z
publishDate 2023
record_format dspace
spelling mit-1721.1/1495262023-03-30T03:16:30Z On Memory Limitations in Natural Language Processing Church, Kenneth Ward Szolovits, Peter This paper proposes a welcome hypothesis: a computationally simple device is sufficient for processing natural language. Traditionally it has been argued that processing natural language syntax requires very powerful machinery. Many engineers have come to this rather grim conclusion: almost all working parsers are actually Turing Machines (TM). For example, Woods specifically designed his Augmented Transition Networks (ATNs) to be Turing Equivalent. 2023-03-29T15:04:34Z 2023-03-29T15:04:34Z 1980-09 https://hdl.handle.net/1721.1/149526 7006245 MIT-LCS-TR-245 application/pdf
spellingShingle Church, Kenneth Ward
On Memory Limitations in Natural Language Processing
title On Memory Limitations in Natural Language Processing
title_full On Memory Limitations in Natural Language Processing
title_fullStr On Memory Limitations in Natural Language Processing
title_full_unstemmed On Memory Limitations in Natural Language Processing
title_short On Memory Limitations in Natural Language Processing
title_sort on memory limitations in natural language processing
url https://hdl.handle.net/1721.1/149526
work_keys_str_mv AT churchkennethward onmemorylimitationsinnaturallanguageprocessing