Filters








228,521 Hits in 3.8 sec

The Comparative Linguistics of Knowledge Representation

Goran Gogic, Henry A. Kautz, Christos H. Papadimitriou, Bart Selman
1995 International Joint Conference on Artificial Intelligence  
We also show that adding new vari ables improves the effective expressibility of certain knowledge representation formalisms.  ...  We develop a methodology for comparing knowledge representation formalisms in terms of their "representational succinctness," that is, their ability to express knowledge situations relatively efficiently  ...  An interesting question thus arises: How is one to evaluate and compare different knowledge representation formalisms?  ... 
dblp:conf/ijcai/GogicKPS95 fatcat:qw4facgmp5darnozenle3dl3pq

Italian Transformers Under the Linguistic Lens

Alessio Miaschi, Gabriele Sarti, Dominique Brunato, Felice Dell'Orletta, Giulia Venturi
2020 Italian Conference on Computational Linguistics  
In this paper we present an in-depth investigation of the linguistic knowledge encoded by the transformer models currently available for the Italian language.  ...  In particular, we investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features.  ...  Contributions To the best of our knowledge, this is the first study aimed at comparing the linguistic knowledge encoded in the representations of multiple non-English pre-trained transformer models.  ... 
dblp:conf/clic-it/MiaschiSBDV20 fatcat:7ebus7afyrftzoa54sfasnczpy

Page 213 of Computational Linguistics Vol. 18, Issue 2 [page]

1992 Computational Linguistics  
Several of the inheritance-based linguistic knowledge representation formalisms that we have introduced in earlier sections are being used for semantic purposes.  ...  to have been made in the 1980s on knowledge representation support for natural language se- mantics.  ... 

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations [article]

Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar
2021 arXiv   pre-print
behaviors in encoding linguistic information in the representations.  ...  Most notably, we observe that ELECTRA tends to encode linguistic knowledge in the deeper layers, whereas XLNet instead concentrates that in the earlier layers.  ...  Based on the accuracy, they found that fine-tuning can affect the linguistic knowledge encoded in the representations.  ... 
arXiv:2109.05958v2 fatcat:fjjjihd2zvd3lfwofd23j4l5pi

METAPHORICAL CONCEPT – THE BEDROCK OF HUMAN BEING

Olesya Cherkhava, Maria Homyak, Władysław Majkowski
2020 Polonia University Scientific Journal  
The modern study of cognitive comparative linguistics is influenced by the development of new cognitive comparative discursive approach in the historical-comparative and typological language investigations  ...  Cognitive paradigm in modern linguistics provoked new understanding of metaphor with broader conceptual view and complex methodology of its analysis.  ...  The comprehensive study of it in the field of cognitive comparative linguistics, the historical-comparative and typological investigations confirmed inequality in the definitions of its adjoining notions  ... 
doi:10.23856/4002 fatcat:nh7k6lwonna6pgmh4ounye3toy

On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers [article]

Marius Mosbach, Anna Khokhlova, Michael A. Hedderich, Dietrich Klakow
2020 arXiv   pre-print
Very little is, however, understood about how fine-tuning affects the representations of pre-trained models and thereby the linguistic knowledge they encode.  ...  At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models.  ...  We would also like to thank the reviewers for their useful comments and feedback, in particular R1.  ... 
arXiv:2010.02616v1 fatcat:2fqphct7hva5jhjxfadolkutwi

Linguistic-Valued Approximate Reasoning With Lattice Ordered Linguistic-Valued Credibility

Li Zou, Yunxia Zhang, Xin Liu
2014 International Journal of Computational Intelligence Systems  
Linguistic terms are often used to represent the truth degree or credibility degree to manage the uncertainty or imprecision as one of popular ways of knowledge representation in the perception-based decision  ...  This approach can better express both comparable and incomparable linguistic valued credibility information in knowledge base representation.  ...  Example 2 and Example 3 illustrate the effectiveness and feasibility of knowledge representation and knowledge reasoning based on linguistic-valued credibility.  ... 
doi:10.1080/18756891.2014.963990 fatcat:zn4jqyxfanfw5ehkhysqznhdf4

Linguistic-Valued Approximate Reasoning With Lattice Ordered Linguistic-Valued Credibility

Li Zou, Yunxia Zhang, Xin Liu
2015 International Journal of Computational Intelligence Systems  
Linguistic terms are often used to represent the truth degree or credibility degree to manage the uncertainty or imprecision as one of popular ways of knowledge representation in the perception-based decision  ...  This approach can better express both comparable and incomparable linguistic valued credibility information in knowledge base representation.  ...  Example 2 and Example 3 illustrate the effectiveness and feasibility of knowledge representation and knowledge reasoning based on linguistic-valued credibility.  ... 
doi:10.2991/ijcis.2015.8.1.5 fatcat:yxdjwijxjzbm7murj6tpa5i5oi

SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge [article]

Pei Ke, Haozhe Ji, Siyang Liu, Xiaoyan Zhu, Minlie Huang
2020 arXiv   pre-print
Most of the existing pre-trained language representation models neglect to consider the linguistic knowledge of texts, which can promote language understanding in NLP tasks.  ...  To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and  ...  Acknowledgments This work was jointly supported by the NSFC projects (key project with No. 61936010 and regular project with No. 61876096), and the Guoqiang Institute of Tsinghua University with Grant  ... 
arXiv:1911.02493v3 fatcat:oxrfksq5pzeldf5arxkemnwkra

Explicit knowledge in dolphins?

Eduardo Mercado, Scott O. Murray
1999 Behavioral and Brain Sciences  
We argue that a comparative approach to investigating knowledge is likely to be more fruitful than one based on linguistic constructs and unobservable phenomena.  ...  Animals other than humans possess knowledge, too, some of which is probably explicit.  ...  D&P attempt to generalize this distinction to the representation or encoding of knowledge.  ... 
doi:10.1017/s0140525x99442189 fatcat:gn5ujwostbdqflrc2kdtvvljzu

Page 179 of Linguistics and Language Behavior Abstracts: LLBA Vol. 26, Issue 1 [page]

1992 Linguistics and Language Behavior Abstracts: LLBA  
A single- logical basis is proposed for the representation of linguistic & problem knowledge as well as concrete object domains in a personal thesaurus. 6 Figures, 12 References. Z.  ...  The productivity of word- formational patterns & formants (affixes) in the derivation of various parts of specch & their meanings in these three languages are compared.  ... 

Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation [article]

Ruichi Yu, Ang Li, Vlad I. Morariu, Larry S. Davis
2017 arXiv   pre-print
To overcome this, we use knowledge of linguistic statistics to regularize visual model learning.  ...  Our experimental results on the Visual Relationship Detection (VRD) and Visual Genome datasets suggest that with this linguistic knowledge distillation, our model outperforms the state-of-the-art methods  ...  Acknowledgement The research was supported by the Office of Naval Research under Grant N000141612713: Visual Common Sense Reasoning for Multi-agent Activity Prediction and Recognition.  ... 
arXiv:1707.09423v2 fatcat:yp6ke2lucnfpbm7bkyludcp6ki

The relationship between priming and linguistic representations is mediated by processing constraints

L. Robert Slevc, Iva Ivanova
2017 Behavioral and Brain Sciences  
Understanding the nature of linguistic representations undoubtedly will benefit from multiple types of evidence, including structural priming.  ...  Here, we argue that successfully gaining linguistic insights from structural priming requires us to better understand (1) the precise mappings between linguistic input and comprehenders' syntactic knowledge  ...  This does not undermine the usefulness of structural priming to shed light on linguistic representations.  ... 
doi:10.1017/s0140525x17000589 pmid:29342736 fatcat:n5nkv7urlbak7j2o5sbp6rv2ya

Building a visual semantics aware object hierarchy [article]

Xiaolei Diao
2022 arXiv   pre-print
The semantic gap is defined as the difference between the linguistic representations of the same concept, which usually leads to misunderstanding between individuals with different knowledge backgrounds  ...  bias of linguistic representations caused by SGP.  ...  and to dissipate the bias of linguistic representations caused by SGP.  ... 
arXiv:2202.13021v1 fatcat:l7tpkyaknrallo42ug7rsyrbja

Probing Linguistic Information for Logical Inference in Pre-trained Language Models

Zeming Chen, Qiyue Gao
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Recent work on probing pre-trained language models uncovered a wide range of linguistic properties encoded in their contextualized representations.  ...  Our probing datasets cover a list of key types of knowledge used by many symbolic inference systems.  ...  Moss and Michael Wollowski for their feedback on earlier drafts of this work.  ... 
doi:10.1609/aaai.v36i10.21294 fatcat:42hns6cv6vcvbiwug65gauwhva
« Previous Showing results 1 — 15 out of 228,521 results