Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385572124> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4385572124 abstract "Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of task generalization since preparing a task-specific example set is costly. To build a system that can quickly and easily generalize to new tasks, task instructions have been adopted as an emerging trend of supervision recently. These instructions give the model the definition of the task and allow the model to output the appropriate answer based on the instructions and inputs. However, task instructions are often expressed in different forms, which can be interpreted from two threads: first, some instructions are short sentences and are pretrained language model (PLM) oriented, such as prompts, while other instructions are paragraphs and are human-oriented, such as those in Amazon MTurk; second, different end-users very likely explain the same task with instructions of different textual expressions. A robust system for task generalization should be able to handle any new tasks regardless of the variability of instructions. However, the system robustness in dealing with instruction-driven task generalization is still unexplored. This work investigates the system robustness when the instructions of new tasks are (i) manipulated, (ii) paraphrased, or (iii) from different levels of conciseness. To our knowledge, this is the first work that systematically studies how robust a PLM is when it is supervised by instructions with different factors of variability." @default.
- W4385572124 created "2023-08-05" @default.
- W4385572124 creator A5026332982 @default.
- W4385572124 creator A5047926973 @default.
- W4385572124 creator A5060976698 @default.
- W4385572124 creator A5061827724 @default.
- W4385572124 creator A5070368916 @default.
- W4385572124 creator A5074828414 @default.
- W4385572124 date "2023-01-01" @default.
- W4385572124 modified "2023-09-27" @default.
- W4385572124 title "Robustness of Learning from Task Instructions" @default.
- W4385572124 doi "https://doi.org/10.18653/v1/2023.findings-acl.875" @default.
- W4385572124 hasPublicationYear "2023" @default.
- W4385572124 type Work @default.
- W4385572124 citedByCount "0" @default.
- W4385572124 crossrefType "proceedings-article" @default.
- W4385572124 hasAuthorship W4385572124A5026332982 @default.
- W4385572124 hasAuthorship W4385572124A5047926973 @default.
- W4385572124 hasAuthorship W4385572124A5060976698 @default.
- W4385572124 hasAuthorship W4385572124A5061827724 @default.
- W4385572124 hasAuthorship W4385572124A5070368916 @default.
- W4385572124 hasAuthorship W4385572124A5074828414 @default.
- W4385572124 hasBestOaLocation W43855721241 @default.
- W4385572124 hasConcept C104317684 @default.
- W4385572124 hasConcept C107457646 @default.
- W4385572124 hasConcept C119857082 @default.
- W4385572124 hasConcept C134306372 @default.
- W4385572124 hasConcept C154945302 @default.
- W4385572124 hasConcept C162324750 @default.
- W4385572124 hasConcept C175154964 @default.
- W4385572124 hasConcept C177148314 @default.
- W4385572124 hasConcept C177264268 @default.
- W4385572124 hasConcept C185592680 @default.
- W4385572124 hasConcept C187736073 @default.
- W4385572124 hasConcept C199360897 @default.
- W4385572124 hasConcept C204321447 @default.
- W4385572124 hasConcept C2780451532 @default.
- W4385572124 hasConcept C33923547 @default.
- W4385572124 hasConcept C41008148 @default.
- W4385572124 hasConcept C55493867 @default.
- W4385572124 hasConcept C63479239 @default.
- W4385572124 hasConceptScore W4385572124C104317684 @default.
- W4385572124 hasConceptScore W4385572124C107457646 @default.
- W4385572124 hasConceptScore W4385572124C119857082 @default.
- W4385572124 hasConceptScore W4385572124C134306372 @default.
- W4385572124 hasConceptScore W4385572124C154945302 @default.
- W4385572124 hasConceptScore W4385572124C162324750 @default.
- W4385572124 hasConceptScore W4385572124C175154964 @default.
- W4385572124 hasConceptScore W4385572124C177148314 @default.
- W4385572124 hasConceptScore W4385572124C177264268 @default.
- W4385572124 hasConceptScore W4385572124C185592680 @default.
- W4385572124 hasConceptScore W4385572124C187736073 @default.
- W4385572124 hasConceptScore W4385572124C199360897 @default.
- W4385572124 hasConceptScore W4385572124C204321447 @default.
- W4385572124 hasConceptScore W4385572124C2780451532 @default.
- W4385572124 hasConceptScore W4385572124C33923547 @default.
- W4385572124 hasConceptScore W4385572124C41008148 @default.
- W4385572124 hasConceptScore W4385572124C55493867 @default.
- W4385572124 hasConceptScore W4385572124C63479239 @default.
- W4385572124 hasLocation W43855721241 @default.
- W4385572124 hasOpenAccess W4385572124 @default.
- W4385572124 hasPrimaryLocation W43855721241 @default.
- W4385572124 hasRelatedWork W1990415753 @default.
- W4385572124 hasRelatedWork W2011670355 @default.
- W4385572124 hasRelatedWork W2162746924 @default.
- W4385572124 hasRelatedWork W2166791242 @default.
- W4385572124 hasRelatedWork W2289004814 @default.
- W4385572124 hasRelatedWork W2346074333 @default.
- W4385572124 hasRelatedWork W286982538 @default.
- W4385572124 hasRelatedWork W3009635394 @default.
- W4385572124 hasRelatedWork W4236554501 @default.
- W4385572124 hasRelatedWork W4291312188 @default.
- W4385572124 isParatext "false" @default.
- W4385572124 isRetracted "false" @default.
- W4385572124 workType "article" @default.