Слабо контролируемая предварительная тренировка

AbstractDeep neural network-based pretraining methods have achieved impressive results in many natural language processing tasks including text classification. However, their applicability to large-scale text classification with numerous categories (e.g., several …...

AbstractThis paper proposes a pre-training based automated Chinese essay scoring method. The method involves three components: weakly supervised pre-training, supervised cross- prompt fine-tuning and supervised target- prompt fine-tuning. An essay …...

In multi-hop QA, answering complex ques- tions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question detection, document retrieval …...