Conceptual metaphor and scripts in Recognizing Textual Entailment

被引:0
|
作者
Murray, William R. [1 ]
机构
[1] Boeing Phamton Works, Seattle, WA 98124 USA
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The power and pervasiveness of conceptual metaphor can be harnessed to expand the class of textual entailments that can be performed in the Recognizing Textual Entailment (RTE) task and thus improve our ability to understand human language and make the kind of textual inferences that people do. RTE is a key component for question understanding and discourse understanding. Although extensive lexicons, such as WordNet, can capture some word senses of conventionalized metaphors, a more general capability is needed to handle the considerable richness of lexical meaning based on metaphoric extensions that is found in common news articles, where writers routinely employ and extend conventional metaphors. We propose adding to RTE systems an ability to recognize a library of common conceptual metaphors, along with scripts. The role of the scripts is to allow entailments from the source to the target domain in the metaphor by describing activities in the source domain that map onto elements of the target domain. An example is the progress of an activity, such as a career or relationship, as measured by the successful or unsuccessful activities in a journey towards its destination. In particular we look at two conceptual metaphors: IDEAS AS PHYSICAL OBJECTS, which is part of the Conduit Metaphor of Communication, and ABSTRACT ACTIVITIES AS JOURNEYS. The first allows inferences that apply to physical objects to (partially) apply to ideas and communication acts (e.g., "he lobbed jibes to the comedian"). The second allows the progress of an abstract activity to be assessed by comparing it to a journey (e.g., "his career was derailed"). We provide a proof of concept where axioms for actions on physical objects, and axioms for how physical objects behave compared to communication objects, are combined to make correct RTE inferences in Prover9 for example text-hypothesis pairs. Similarly, axioms describing different states in a journey are used to infer the current progress of an activity, such as whether it is succeeding (e.g., "steaming ahead"), in trouble (e.g., "off course"), recovering (e.g., "back on track"), or irrevocably failed (e.g., "hijacked").
引用
收藏
页码:127 / 136
页数:10
相关论文
共 50 条
  • [41] Recognizing Textual Entailment with Deep-Shallow Semantic Analysis and Logical Inference
    Wotzlaw, Andreas
    Coote, Ravi
    SEMAPRO 2010: THE FOURTH INTERNATIONAL CONFERENCE ON ADVANCES IN SEMANTIC PROCESSING, 2010, : 118 - 125
  • [42] Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment
    Tsuchiya, Masatoshi
    PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018), 2018, : 1506 - 1511
  • [43] Word2vec Based System for Recognizing Partial Textual Entailment
    Vita, Martin
    Kriz, Vincent
    PROCEEDINGS OF THE 2016 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS), 2016, 8 : 513 - 516
  • [44] Max-Cosine Matching Based Neural Models for Recognizing Textual Entailment
    Xie, Zhipeng
    Hu, Junfeng
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2017), PT I, 2017, 10177 : 295 - 308
  • [45] Ar-SLoTE: A Recognizing Textual Entailment Tool for Arabic Question/Answering Systems
    Ben-Sghaier, Mabrouka
    Bakari, Wided
    Neji, Mahmoud
    2019 7TH INTERNATIONAL CONFERENCE ON ICT & ACCESSIBILITY (ICTA), 2019,
  • [46] Recognizing textual entailment: Rational, evaluation and approaches (vol 15, pg 1, 2009)
    Dagan, Ido
    Dolan, Bill
    Magnini, Bernardo
    Roth, Dan
    NATURAL LANGUAGE ENGINEERING, 2010, 16 : 105 - +
  • [47] A STUDY OF TEXTUAL ENTAILMENT
    Rus, Vasile
    McCarthy, Philip M.
    McNamara, Danielle S.
    Graesser, Arthur C.
    INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2008, 17 (04) : 659 - 685
  • [48] Translators in Textual Entailment
    Javier Castillo, Julio
    DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, 2010, 79 : 193 - 196
  • [49] STCP: An Efficient Model Combining Subject Triples and Constituency Parsing for Recognizing Textual Entailment
    Li, Meiling
    Li, Xiumei
    Sun, Junmei
    He, Xinrui
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2021, PT V, 2021, 12895 : 284 - 296
  • [50] Using Earth Mover's Distance and Word Embeddings for Recognizing Textual Entailment in Arabic
    Boudaa, Tarik
    El Marouani, Mohamed
    Enneya, Nourddine
    COMPUTACION Y SISTEMAS, 2020, 24 (04): : 1499 - 1508