Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104508700> ?p ?o ?g. }
- W3104508700 abstract "To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners." @default.
- W3104508700 created "2020-11-23" @default.
- W3104508700 creator A5001961716 @default.
- W3104508700 creator A5043538173 @default.
- W3104508700 creator A5048075454 @default.
- W3104508700 creator A5080725225 @default.
- W3104508700 date "2020-01-01" @default.
- W3104508700 modified "2023-09-27" @default.
- W3104508700 title "Continual Adaptation for Efficient Machine Communication" @default.
- W3104508700 cites W1597739853 @default.
- W3104508700 cites W179875071 @default.
- W3104508700 cites W1861492603 @default.
- W3104508700 cites W1889081078 @default.
- W3104508700 cites W1895577753 @default.
- W3104508700 cites W1964951887 @default.
- W3104508700 cites W1982249382 @default.
- W3104508700 cites W1989549063 @default.
- W3104508700 cites W2016986418 @default.
- W3104508700 cites W2020073413 @default.
- W3104508700 cites W2026681882 @default.
- W3104508700 cites W2028423696 @default.
- W3104508700 cites W2031522244 @default.
- W3104508700 cites W2041388215 @default.
- W3104508700 cites W2104094955 @default.
- W3104508700 cites W2110930288 @default.
- W3104508700 cites W2116522068 @default.
- W3104508700 cites W2118508845 @default.
- W3104508700 cites W2141038596 @default.
- W3104508700 cites W2142947219 @default.
- W3104508700 cites W2147966321 @default.
- W3104508700 cites W2151315616 @default.
- W3104508700 cites W2163302275 @default.
- W3104508700 cites W2185175083 @default.
- W3104508700 cites W22024230 @default.
- W3104508700 cites W2206117428 @default.
- W3104508700 cites W2250674021 @default.
- W3104508700 cites W2264742718 @default.
- W3104508700 cites W22861983 @default.
- W3104508700 cites W2325526696 @default.
- W3104508700 cites W2373419227 @default.
- W3104508700 cites W2400607496 @default.
- W3104508700 cites W2403524927 @default.
- W3104508700 cites W2525032226 @default.
- W3104508700 cites W2564324149 @default.
- W3104508700 cites W2574790321 @default.
- W3104508700 cites W2579486552 @default.
- W3104508700 cites W2604397416 @default.
- W3104508700 cites W2604763608 @default.
- W3104508700 cites W2762009853 @default.
- W3104508700 cites W2776513784 @default.
- W3104508700 cites W2777660616 @default.
- W3104508700 cites W2798523458 @default.
- W3104508700 cites W2888302696 @default.
- W3104508700 cites W2890485455 @default.
- W3104508700 cites W2897513296 @default.
- W3104508700 cites W2916991563 @default.
- W3104508700 cites W2952316487 @default.
- W3104508700 cites W2952581030 @default.
- W3104508700 cites W2962727507 @default.
- W3104508700 cites W2962846267 @default.
- W3104508700 cites W2963318456 @default.
- W3104508700 cites W2963547174 @default.
- W3104508700 cites W2963938518 @default.
- W3104508700 cites W2964093801 @default.
- W3104508700 cites W2964183327 @default.
- W3104508700 cites W2964193163 @default.
- W3104508700 cites W2964335542 @default.
- W3104508700 cites W2972381305 @default.
- W3104508700 cites W2984375830 @default.
- W3104508700 cites W3004551565 @default.
- W3104508700 cites W3031586704 @default.
- W3104508700 cites W3034540958 @default.
- W3104508700 cites W3035108169 @default.
- W3104508700 cites W3109549099 @default.
- W3104508700 cites W648633 @default.
- W3104508700 cites W2034005901 @default.
- W3104508700 doi "https://doi.org/10.18653/v1/2020.conll-1.33" @default.
- W3104508700 hasPublicationYear "2020" @default.
- W3104508700 type Work @default.
- W3104508700 sameAs 3104508700 @default.
- W3104508700 citedByCount "9" @default.
- W3104508700 countsByYear W31045087002020 @default.
- W3104508700 countsByYear W31045087002021 @default.
- W3104508700 countsByYear W31045087002022 @default.
- W3104508700 countsByYear W31045087002023 @default.
- W3104508700 crossrefType "proceedings-article" @default.
- W3104508700 hasAuthorship W3104508700A5001961716 @default.
- W3104508700 hasAuthorship W3104508700A5043538173 @default.
- W3104508700 hasAuthorship W3104508700A5048075454 @default.
- W3104508700 hasAuthorship W3104508700A5080725225 @default.
- W3104508700 hasBestOaLocation W31045087001 @default.
- W3104508700 hasConcept C107457646 @default.
- W3104508700 hasConcept C119857082 @default.
- W3104508700 hasConcept C120665830 @default.
- W3104508700 hasConcept C121332964 @default.
- W3104508700 hasConcept C13280743 @default.
- W3104508700 hasConcept C137293760 @default.
- W3104508700 hasConcept C139807058 @default.
- W3104508700 hasConcept C154945302 @default.
- W3104508700 hasConcept C162324750 @default.