It’s the Meaning That Counts: The State of the Art in NLP and Semantics

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

It’s the Meaning That Counts : The State of the Art in NLP and Semantics. / Hershcovich, Daniel; Donatelli, Lucia.

In: KI - Kunstliche Intelligenz, Vol. 35, No. 3-4, 2021, p. 255-270.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Hershcovich, D & Donatelli, L 2021, 'It’s the Meaning That Counts: The State of the Art in NLP and Semantics', KI - Kunstliche Intelligenz, vol. 35, no. 3-4, pp. 255-270. https://doi.org/10.1007/s13218-021-00726-6

APA

Hershcovich, D., & Donatelli, L. (2021). It’s the Meaning That Counts: The State of the Art in NLP and Semantics. KI - Kunstliche Intelligenz, 35(3-4), 255-270. https://doi.org/10.1007/s13218-021-00726-6

Vancouver

Hershcovich D, Donatelli L. It’s the Meaning That Counts: The State of the Art in NLP and Semantics. KI - Kunstliche Intelligenz. 2021;35(3-4):255-270. https://doi.org/10.1007/s13218-021-00726-6

Author

Hershcovich, Daniel ; Donatelli, Lucia. / It’s the Meaning That Counts : The State of the Art in NLP and Semantics. In: KI - Kunstliche Intelligenz. 2021 ; Vol. 35, No. 3-4. pp. 255-270.

Bibtex

@article{089777eabc3143938b41a649da58090b,
title = "It{\textquoteright}s the Meaning That Counts: The State of the Art in NLP and Semantics",
abstract = "Semantics, the study of meaning, is central to research in Natural Language Processing (NLP) and many other fields connected to Artificial Intelligence. Nevertheless, how semantics is understood in NLP ranges from traditional, formal linguistic definitions based on logic and the principle of compositionality to more applied notions based on grounding meaning in real-world objects and real-time interaction. “Semantic” methods may additionally strive for meaningful representation of language that integrates broader aspects of human cognition and embodied experience, calling into question how adequate a representation of meaning based on linguistic signal alone is for current research agendas. We review the state of computational semantics in NLP and investigate how different lines of inquiry reflect distinct understandings of semantics and prioritize different layers of linguistic meaning. In conclusion, we identify several important goals of the field and describe how current research addresses them.",
author = "Daniel Hershcovich and Lucia Donatelli",
year = "2021",
doi = "10.1007/s13218-021-00726-6",
language = "English",
volume = "35",
pages = "255--270",
journal = "KI - K{\"u}nstliche Intelligenz",
issn = "0933-1875",
publisher = "Springer",
number = "3-4",

}

RIS

TY - JOUR

T1 - It’s the Meaning That Counts

T2 - The State of the Art in NLP and Semantics

AU - Hershcovich, Daniel

AU - Donatelli, Lucia

PY - 2021

Y1 - 2021

N2 - Semantics, the study of meaning, is central to research in Natural Language Processing (NLP) and many other fields connected to Artificial Intelligence. Nevertheless, how semantics is understood in NLP ranges from traditional, formal linguistic definitions based on logic and the principle of compositionality to more applied notions based on grounding meaning in real-world objects and real-time interaction. “Semantic” methods may additionally strive for meaningful representation of language that integrates broader aspects of human cognition and embodied experience, calling into question how adequate a representation of meaning based on linguistic signal alone is for current research agendas. We review the state of computational semantics in NLP and investigate how different lines of inquiry reflect distinct understandings of semantics and prioritize different layers of linguistic meaning. In conclusion, we identify several important goals of the field and describe how current research addresses them.

AB - Semantics, the study of meaning, is central to research in Natural Language Processing (NLP) and many other fields connected to Artificial Intelligence. Nevertheless, how semantics is understood in NLP ranges from traditional, formal linguistic definitions based on logic and the principle of compositionality to more applied notions based on grounding meaning in real-world objects and real-time interaction. “Semantic” methods may additionally strive for meaningful representation of language that integrates broader aspects of human cognition and embodied experience, calling into question how adequate a representation of meaning based on linguistic signal alone is for current research agendas. We review the state of computational semantics in NLP and investigate how different lines of inquiry reflect distinct understandings of semantics and prioritize different layers of linguistic meaning. In conclusion, we identify several important goals of the field and describe how current research addresses them.

U2 - 10.1007/s13218-021-00726-6

DO - 10.1007/s13218-021-00726-6

M3 - Journal article

AN - SCOPUS:85107516314

VL - 35

SP - 255

EP - 270

JO - KI - Künstliche Intelligenz

JF - KI - Künstliche Intelligenz

SN - 0933-1875

IS - 3-4

ER -

ID: 300915853