PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics

被引:0
|
作者
Meadows, Jordan [1 ,2 ]
Zhou, Zili [1 ]
Freitas, Andre [1 ,2 ]
机构
[1] Univ Manchester, Dept Comp Sci, Manchester, Lancs, England
[2] Idiap Res Inst, Martigny, Switzerland
基金
瑞士国家科学基金会;
关键词
mathematical text; physics; natural language understanding; discourse coherence;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
In order for language models to aid physics research, they must first encode representations of mathematical and natural language discourse which lead to coherent explanations, with correct ordering and relevance of statements. We present a collection of datasets developed to evaluate the performance of language models in this regard, which measure capabilities with respect to sentence ordering, position, section prediction, and discourse coherence. Analysis of the data reveals equations and sub-disciplines which are most common in physics discourse, as well as the sentence-level frequency of equations and expressions. We present baselines that demonstrate how contemporary language models are challenged by coherence related tasks in physics, even when trained on mathematical natural language objectives.
引用
收藏
页码:4611 / 4619
页数:9
相关论文
共 50 条
  • [1] GRASP: A Novel Benchmark for Evaluating Language GRounding and Situated Physics Understanding in Multimodal Language Models
    Jassimi, Serwan
    Holubar, Mario
    Richter, Annika
    Wolff, Cornelius
    Ohmer, Xenia
    Bruni, Elia
    PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, 2024, : 6297 - 6305
  • [2] Explanation in natural language of λμμ-terms
    Coen, CS
    MATHEMATICAL KNOWLEDGE MANAGEMENT, 2006, 3863 : 234 - 249
  • [3] Natural language proof explanation
    Fiedler, A
    MECHANIZING MATHEMATICAL REASONING: ESSAYS IN HONOUR OF JORG H SIEKMANN ON THE OCCASION OF HIS 60TH BIRTHDAY, 2005, 2605 : 342 - 363
  • [4] The language of thought and natural language understanding
    Knowles, J
    ANALYSIS, 1998, 58 (04) : 264 - 272
  • [5] IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
    Wilie, Bryan
    Vincentio, Karissa
    Winata, Genta Indra
    Cahyawijaya, Samuel
    Li, Xiaohong
    Lim, Zhi Yuan
    Soleman, Sidik
    Mahendra, Rahmad
    Fun, Pascale
    Bahar, Syafri
    Purwarianti, Ayu
    1ST CONFERENCE OF THE ASIA-PACIFIC CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 10TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (AACL-IJCNLP 2020), 2020, : 843 - 857
  • [6] Natural Language Understanding
    Di Sciullo, Anna Maria
    NEW TRENDS IN SOFTWARE METHODOLOGIES, TOOLS AND TECHNIQUES, 2009, 199 : 551 - 563
  • [7] UNDERSTANDING NATURAL LANGUAGE
    WINOGRAD, T
    COGNITIVE PSYCHOLOGY, 1972, 3 (01) : 1 - 191
  • [8] The Journey of Language Models in Understanding Natural Language
    Liu, Yuanrui
    Zhou, Jingping
    Sang, Guobiao
    Huang, Ruilong
    Zhao, Xinzhe
    Fang, Jintao
    Wang, Tiexin
    Li, Bohan
    WEB INFORMATION SYSTEMS AND APPLICATIONS, WISA 2024, 2024, 14883 : 331 - 363
  • [9] Evaluating Natural Language Understanding Services for Conversational Question Answering Systems
    Braun, Daniel
    Mendez, Adrian Hernandez
    Matthes, Florian
    Langen, Manfred
    18TH ANNUAL MEETING OF THE SPECIAL INTEREST GROUP ON DISCOURSE AND DIALOGUE (SIGDIAL 2017), 2017, : 174 - 185
  • [10] UNDERSTANDING NATURAL-LANGUAGE
    PITRAT, J
    RECHERCHE, 1978, 9 (93): : 876 - 881