Symbolic, Distributed, and Distributional Representations for Natural Language Processing in the Era of Deep Learning : A Survey
Copyright © 2020 Ferrone and Zanzotto..
Natural language is inherently a discrete symbolic representation of human knowledge. Recent advances in machine learning (ML) and in natural language processing (NLP) seem to contradict the above intuition: discrete symbols are fading away, erased by vectors or tensors called distributed and distributional representations. However, there is a strict link between distributed/distributional representations and discrete symbols, being the first an approximation of the second. A clearer understanding of the strict link between distributed/distributional representations and symbols may certainly lead to radically new deep learning networks. In this paper we make a survey that aims to renew the link between symbolic representations and distributed/distributional representations. This is the right time to revitalize the area of interpreting how discrete symbols are represented inside neural networks.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2019 |
---|---|
Erschienen: |
2019 |
Enthalten in: |
Zur Gesamtaufnahme - volume:6 |
---|---|
Enthalten in: |
Frontiers in robotics and AI - 6(2019) vom: 22., Seite 153 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Ferrone, Lorenzo [VerfasserIn] |
---|
Links: |
---|
Themen: |
Compositional distributional semantic models |
---|
Anmerkungen: |
Date Revised 29.01.2021 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3389/frobt.2019.00153 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM320629937 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM320629937 | ||
003 | DE-627 | ||
005 | 20231225174005.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2019 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3389/frobt.2019.00153 |2 doi | |
028 | 5 | 2 | |a pubmed24n1068.xml |
035 | |a (DE-627)NLM320629937 | ||
035 | |a (NLM)33501168 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Ferrone, Lorenzo |e verfasserin |4 aut | |
245 | 1 | 0 | |a Symbolic, Distributed, and Distributional Representations for Natural Language Processing in the Era of Deep Learning |b A Survey |
264 | 1 | |c 2019 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 29.01.2021 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Copyright © 2020 Ferrone and Zanzotto. | ||
520 | |a Natural language is inherently a discrete symbolic representation of human knowledge. Recent advances in machine learning (ML) and in natural language processing (NLP) seem to contradict the above intuition: discrete symbols are fading away, erased by vectors or tensors called distributed and distributional representations. However, there is a strict link between distributed/distributional representations and discrete symbols, being the first an approximation of the second. A clearer understanding of the strict link between distributed/distributional representations and symbols may certainly lead to radically new deep learning networks. In this paper we make a survey that aims to renew the link between symbolic representations and distributed/distributional representations. This is the right time to revitalize the area of interpreting how discrete symbols are represented inside neural networks | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Review | |
650 | 4 | |a compositional distributional semantic models | |
650 | 4 | |a compositionality | |
650 | 4 | |a concatenative compositionality | |
650 | 4 | |a deep learning (DL) | |
650 | 4 | |a distributed representation | |
650 | 4 | |a natural language processing (NLP) | |
700 | 1 | |a Zanzotto, Fabio Massimo |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Frontiers in robotics and AI |d 2018 |g 6(2019) vom: 22., Seite 153 |w (DE-627)NLM314375058 |x 2296-9144 |7 nnns |
773 | 1 | 8 | |g volume:6 |g year:2019 |g day:22 |g pages:153 |
856 | 4 | 0 | |u http://dx.doi.org/10.3389/frobt.2019.00153 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 6 |j 2019 |b 22 |h 153 |