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
  • [21] 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
  • [22] Natural Language Understanding for Grading Essay Questions in Persian Language
    Mokhtari-Fard, Iman
    CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA, 2013, 8208 : 144 - 153
  • [23] Shortcut Learning of Large Language Models in Natural Language Understanding
    Du, Mengnan
    He, Fengxiang
    Zou, Na
    Tao, Dacheng
    Hu, Xia
    COMMUNICATIONS OF THE ACM, 2024, 67 (01) : 110 - 120
  • [24] Evaluating natural language processing systems
    King, M
    COMMUNICATIONS OF THE ACM, 1996, 39 (01) : 73 - 79
  • [25] AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
    Ebrahimi, Abteen
    Mager, Manuel
    Oncevay, Arturo
    Chaudhary, Vishrav
    Chiruzzo, Luis
    Fan, Angela
    Ortega, John E.
    Ramos, Ricardo
    Rios, Annette
    Meza-Ruiz, Ivan
    Gimenez-Lugo, Gustavo A.
    Mager, Elisabeth
    Neubig, Graham
    Palmer, Alexis
    Coto-Solano, Rolando
    Ngoc Thang Vu
    Kann, Katharina
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 6279 - 6299
  • [26] Challenges in natural language processing and natural language understanding by considering both technical and natural domains
    Ardehkhani, Pouya
    Vahedi, Amir
    Aghababa, Hossein
    2023 6TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS, IPRIA, 2023,
  • [27] UNDERSTANDING NATURAL LANGUAGE - WINOGRAD,T
    BROWN, JS
    BEHAVIORAL SCIENCE, 1973, 18 (06): : 448 - 449
  • [28] UNDERSTANDING NATURAL LANGUAGE - WINOGRAD,T
    JONES, KS
    INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1974, 6 (02): : 279 - 281
  • [29] MODELS OF NATURAL-LANGUAGE UNDERSTANDING
    BATES, M
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1995, 92 (22) : 9977 - 9982
  • [30] Natural-language understanding at BBN
    Weischedel, R
    IEEE ANNALS OF THE HISTORY OF COMPUTING, 2006, 28 (01) : 46 - 55