Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386937984> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386937984 endingPage "425" @default.
- W4386937984 startingPage "414" @default.
- W4386937984 abstract "In the real world, obtaining question-answer pairs for a target domain text is often an expensive process, an approach to tackle the problem is to use automatically generated question-answer pairs from the problem context and large amount of unstructured texts (e.g. Wikipedia). However, current approaches to generate question-answer pairs typically require fine-tuning tens of thousands of examples to achieve good results. Obtaining these instances involves high labor costs, and once the model lacks sufficient training data, the performance of the model with few-shot (< 100 examples) drops dramatically. To address this problem, we propose a method for generating question-answer pairs with few examples, generating answers and questions using the input context, and then filtering the results through a model. By tuning the fine-tuned structure of the model to improve the few-shot performance, we also input different levels of features into the model through granularity decomposition, solving an important issue when data is limited: the inability to perform answer-span detection (or answer generation). We evaluate our method in three aspects: the diversity of generated answers, the quality of generated questions, and the training of a new model entirely using the generated QA pairs. Our experimental results demonstrate that our proposed method can effectively generate question-answer pairs with low resources." @default.
- W4386937984 created "2023-09-22" @default.
- W4386937984 creator A5000363384 @default.
- W4386937984 creator A5027475930 @default.
- W4386937984 date "2023-01-01" @default.
- W4386937984 modified "2023-10-16" @default.
- W4386937984 title "Generating Question-Answer Pairs for Few-Shot Learning" @default.
- W4386937984 cites W2144578941 @default.
- W4386937984 cites W2250425483 @default.
- W4386937984 cites W2949849869 @default.
- W4386937984 cites W2962717047 @default.
- W4386937984 cites W2962970841 @default.
- W4386937984 cites W2963430447 @default.
- W4386937984 cites W2970796366 @default.
- W4386937984 cites W2988421999 @default.
- W4386937984 cites W3034999214 @default.
- W4386937984 cites W3035500185 @default.
- W4386937984 cites W3101007570 @default.
- W4386937984 cites W3153427360 @default.
- W4386937984 cites W3174122384 @default.
- W4386937984 cites W3176119108 @default.
- W4386937984 cites W3198507920 @default.
- W4386937984 cites W3199051863 @default.
- W4386937984 cites W4285310603 @default.
- W4386937984 doi "https://doi.org/10.1007/978-3-031-44213-1_35" @default.
- W4386937984 hasPublicationYear "2023" @default.
- W4386937984 type Work @default.
- W4386937984 citedByCount "0" @default.
- W4386937984 crossrefType "book-chapter" @default.
- W4386937984 hasAuthorship W4386937984A5000363384 @default.
- W4386937984 hasAuthorship W4386937984A5027475930 @default.
- W4386937984 hasConcept C119857082 @default.
- W4386937984 hasConcept C124101348 @default.
- W4386937984 hasConcept C134306372 @default.
- W4386937984 hasConcept C151730666 @default.
- W4386937984 hasConcept C154945302 @default.
- W4386937984 hasConcept C177774035 @default.
- W4386937984 hasConcept C178790620 @default.
- W4386937984 hasConcept C185592680 @default.
- W4386937984 hasConcept C199360897 @default.
- W4386937984 hasConcept C204321447 @default.
- W4386937984 hasConcept C23123220 @default.
- W4386937984 hasConcept C2778344882 @default.
- W4386937984 hasConcept C2779343474 @default.
- W4386937984 hasConcept C33923547 @default.
- W4386937984 hasConcept C36503486 @default.
- W4386937984 hasConcept C41008148 @default.
- W4386937984 hasConcept C86803240 @default.
- W4386937984 hasConcept C98045186 @default.
- W4386937984 hasConceptScore W4386937984C119857082 @default.
- W4386937984 hasConceptScore W4386937984C124101348 @default.
- W4386937984 hasConceptScore W4386937984C134306372 @default.
- W4386937984 hasConceptScore W4386937984C151730666 @default.
- W4386937984 hasConceptScore W4386937984C154945302 @default.
- W4386937984 hasConceptScore W4386937984C177774035 @default.
- W4386937984 hasConceptScore W4386937984C178790620 @default.
- W4386937984 hasConceptScore W4386937984C185592680 @default.
- W4386937984 hasConceptScore W4386937984C199360897 @default.
- W4386937984 hasConceptScore W4386937984C204321447 @default.
- W4386937984 hasConceptScore W4386937984C23123220 @default.
- W4386937984 hasConceptScore W4386937984C2778344882 @default.
- W4386937984 hasConceptScore W4386937984C2779343474 @default.
- W4386937984 hasConceptScore W4386937984C33923547 @default.
- W4386937984 hasConceptScore W4386937984C36503486 @default.
- W4386937984 hasConceptScore W4386937984C41008148 @default.
- W4386937984 hasConceptScore W4386937984C86803240 @default.
- W4386937984 hasConceptScore W4386937984C98045186 @default.
- W4386937984 hasLocation W43869379841 @default.
- W4386937984 hasOpenAccess W4386937984 @default.
- W4386937984 hasPrimaryLocation W43869379841 @default.
- W4386937984 hasRelatedWork W1532213207 @default.
- W4386937984 hasRelatedWork W1577931366 @default.
- W4386937984 hasRelatedWork W1594844924 @default.
- W4386937984 hasRelatedWork W2024555427 @default.
- W4386937984 hasRelatedWork W2143670980 @default.
- W4386937984 hasRelatedWork W2357241418 @default.
- W4386937984 hasRelatedWork W2909382770 @default.
- W4386937984 hasRelatedWork W2961085424 @default.
- W4386937984 hasRelatedWork W4306674287 @default.
- W4386937984 hasRelatedWork W4224009465 @default.
- W4386937984 isParatext "false" @default.
- W4386937984 isRetracted "false" @default.
- W4386937984 workType "book-chapter" @default.