The Journey of Language Models in Understanding Natural Language

被引：0

作者：

Liu, Yuanrui ^{[1
,2
]}

Zhou, Jingping ^{[3
]}

Sang, Guobiao ^{[2
]}

Huang, Ruilong ^{[1
]}

Zhao, Xinzhe ^{[1
]}

Fang, Jintao ^{[2
]}

Wang, Tiexin ^{[1
]}

Li, Bohan ^{[1
]}

机构：

[1] Nanjing Univ Aeronaut & Astronaut, Coll Artificial Intelligence & Comp Sci & Technol, Nanjing 211106, Peoples R China

[2] Beijing Shenzhou Aerosp Software Technol Co Ltd, Beijing 100094, Peoples R China

[3] Beijing Inst Telemetry, Beijing 100083, Peoples R China

来源：

WEB INFORMATION SYSTEMS AND APPLICATIONS, WISA 2024 | 2024年 / 14883卷

关键词：

Artificial intelligence; Natural language understanding; Vector space model; Topic model; Neural network; Deep learning; VECTOR-SPACE-MODEL;

D O I：

10.1007/978-981-97-7707-5_29

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Since the Turing Test was proposed in the 1950s, humanity began exploring artificial intelligence, with an aim to bridge the interaction gap between machines and human language. This exploration enables machines to comprehend how humans acquire, produce, and understand language, as well as the relationship between linguistic expression and the world. The paper explores the basic principles of natural language representation, the formalization of natural language, and the modeling methods of language models. The paper analyzes, summarizes and compares the mainstream technologies and methods, including vector space-based, topic model-based, graph-based, and neural network-based approaches. And how to improve the development trend and direction of language model understanding ability is predicted and further discussed.

引用

页码：331 / 363

页数：33

共 50 条

[31] Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Ki, Geewook
Lee, Hodong
Kim, Daehee
Jung, Haeji
Park, Sanghee
Kim, Yoonsik
Yun, Sangdoo
Kim, Taeho
Lee, Bado
Park, Seunghyun
2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023), 2023, : 11989 - 12010
[32] Calibration of Natural Language Understanding Models with Venn-ABERS Predictors
Giovannotti, Patrizio
CONFORMAL AND PROBABILISTIC PREDICTION WITH APPLICATIONS, VOL 179, 2022, 179
[33] CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models
Wang, Xingbo
Huang, Renfei
Jin, Zhihua
Fang, Tianqing
Qu, Huamin
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2024, 30 (01) : 273 - 283
[34] Comparison of alignment templates and maximum entropy models for natural language understanding
Bender, O
Macherey, K
Och, FJ
Ney, H
EACL 2003: 10TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2003, : 11 - 18
[35] Evaluation of Sentence Embedding Models for Natural Language Understanding Problems in Russian
Popov, Dmitry
Pugachev, Alexander
Svyatokum, Polina
Svitanko, Elizaveta
Artemova, Ekaterina
ANALYSIS OF IMAGES, SOCIAL NETWORKS AND TEXTS, AIST 2019, 2019, 11832 : 205 - 217
[36] Semi-Supervised Learning of Statistical Models for Natural Language Understanding
Zhou, Deyu
He, Yulan
SCIENTIFIC WORLD JOURNAL, 2014,
[37] Backdoor Learning of Language Models in Natural Language Processing
University of Michigan
1600,
[38] Natural language processing in the era of large language models
Zubiaga, Arkaitz
FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 6
[39] Structuring Natural Language Requirements with Large Language Models
Norheim, Johannes J.
Rebentisch, Eric
32ND INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE WORKSHOPS, REW 2024, 2024, : 68 - 71
[40] Enhancing Language Representation with Constructional Information for Natural Language Understanding
Xu, Lvxiaowei
Wu, Jianwang
Peng, Jiawei
Gong, Zhilin
Cai, Ming
Wang, Tianxiang
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 1, 2023, : 4685 - 4705

← 1 2 3 4 5 →