Infusing Finetuning with Semantic Dependencies
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10441618" target="_blank" >RIV/00216208:11320/21:10441618 - isvavai.cz</a>
Výsledek na webu
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=.a8a-gSDHQ" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=.a8a-gSDHQ</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1162/tacl_a_00363" target="_blank" >10.1162/tacl_a_00363</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Infusing Finetuning with Semantic Dependencies
Popis výsledku v původním jazyce
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained'' on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia). On the other hand, the lack of grounded supervision calls into question how well these representations can ever capture meaning (Bender and Koller, 2020). We apply novel probes to recent language models-specifically focusing on predicate-argument structure as operationalized by semantic dependencies (Ivanova et al., 2012)-and find that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning, yielding benefits to natural language understanding (NLU) tasks in the GLUE benchmark. This approach demonstrates the potential for general-purpose (rather than task-specific) linguistic supervision, above and beyond conventional pretraining and finetuning. Several diagnostics help to localize the benefits of our approach.(1)
Název v anglickém jazyce
Infusing Finetuning with Semantic Dependencies
Popis výsledku anglicky
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained'' on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia). On the other hand, the lack of grounded supervision calls into question how well these representations can ever capture meaning (Bender and Koller, 2020). We apply novel probes to recent language models-specifically focusing on predicate-argument structure as operationalized by semantic dependencies (Ivanova et al., 2012)-and find that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning, yielding benefits to natural language understanding (NLU) tasks in the GLUE benchmark. This approach demonstrates the potential for general-purpose (rather than task-specific) linguistic supervision, above and beyond conventional pretraining and finetuning. Several diagnostics help to localize the benefits of our approach.(1)
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2021
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Transactions of the Association for Computational Linguistics [online]
ISSN
2307-387X
e-ISSN
—
Svazek periodika
9
Číslo periodika v rámci svazku
11.03.2021
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
17
Strana od-do
226-242
Kód UT WoS článku
000751952200014
EID výsledku v databázi Scopus
2-s2.0-85107894350