Ideal WordsA Vector-Based Formalisation of Semantic Competence

被引:0
|
作者
Aurélie Herbelot
Ann Copestake
机构
[1] University of Trento,Department of Information Engineering and Computer Science, Center for Mind/Brain Sciences
[2] University of Cambridge,Department of Computer Science and Technology
来源
KI - Künstliche Intelligenz | 2021年 / 35卷
关键词
Formal semantics; Distributional semantics; Competence;
D O I
暂无
中图分类号
学科分类号
摘要
In this theoretical paper, we consider the notion of semantic competence and its relation to general language understanding—one of the most sough-after goals of Artificial Intelligence. We come back to three main accounts of competence involving (a) lexical knowledge; (b) truth-theoretic reference; and (c) causal chains in language use. We argue that all three are needed to reach a notion of meaning in artificial agents and suggest that they can be combined in a single formalisation, where competence develops from exposure to observable performance data. We introduce a theoretical framework which translates set theory into vector-space semantics by applying distributional techniques to a corpus of utterances associated with truth values. The resulting meaning space naturally satisfies the requirements of a causal theory of competence, but it can also be regarded as some ‘ideal’ model of the world, allowing for extensions and standard lexical relations to be retrieved.
引用
收藏
页码:271 / 290
页数:19
相关论文
共 50 条
  • [1] Ideal Words A Vector-Based Formalisation of Semantic Competence
    Herbelot, Aurelie
    Copestake, Ann
    KUNSTLICHE INTELLIGENZ, 2021, 35 (3-4): : 271 - 290
  • [2] Vector-Based Semantic Scenario Search for Vehicular Traffic
    Bhoomika, A. P.
    Srinivasa, Srinath
    Indla, Vijaya Sarathi
    Mukherjee, Saikat
    BIG DATA ANALYTICS IN ASTRONOMY, SCIENCE, AND ENGINEERING, BDA 2023, 2024, 14516 : 160 - 171
  • [3] Towards Geological Knowledge Discovery Using Vector-Based Semantic Similarity
    Enkhsaikhan, Majigsuren
    Liu, Wei
    Holden, Eun-Jung
    Duuring, Paul
    ADVANCED DATA MINING AND APPLICATIONS, ADMA 2018, 2018, 11323 : 224 - 237
  • [4] IntelliGO: a new vector-based semantic similarity measure including annotation origin
    Benabderrahmane, Sidahmed
    Smail-Tabbone, Malika
    Poch, Olivier
    Napoli, Amedeo
    Devignes, Marie-Dominique
    BMC BIOINFORMATICS, 2010, 11
  • [5] IntelliGO: a new vector-based semantic similarity measure including annotation origin
    Sidahmed Benabderrahmane
    Malika Smail-Tabbone
    Olivier Poch
    Amedeo Napoli
    Marie-Dominique Devignes
    BMC Bioinformatics, 11
  • [7] Vector-based semantic analysis using random indexing for cross-lingual query expansion
    Sahlgren, M
    Karlgren, J
    EVLAUATION OF CROSS-LANGUAGE INFORMATION RETRIEVAL SYSTEMS, 2002, 2406 : 169 - 176
  • [8] An integrative measure of graph- and vector-based semantic similarity using information content distance
    Hu, Qiaoli
    Cho, Young-Rae
    PROCEEDINGS 2015 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2015, : 517 - 522
  • [9] Vector-based pedestrian navigation in cities
    Bongiorno, Christian
    Zhou, Yulun
    Kryven, Marta
    Theurel, David
    Rizzo, Alessandro
    Santi, Paolo
    Tenenbaum, Joshua
    Ratti, Carlo
    NATURE COMPUTATIONAL SCIENCE, 2021, 1 (10): : 678 - 685
  • [10] Viral Vector-Based Gene Therapy
    Li, Xuedan
    Le, Yang
    Zhang, Zhegang
    Nian, Xuanxuan
    Liu, Bo
    Yang, Xiaoming
    INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2023, 24 (09)