Structural Self-Supervised Objectives for Transformers
L Di Liello - arXiv preprint arXiv:2309.08272, 2023 - arxiv.org
This thesis focuses on improving the pre-training of natural language models using
unsupervised raw data to make them more efficient and aligned with downstream …
unsupervised raw data to make them more efficient and aligned with downstream …
CollabAS2: Enhancing Arabic Answer Sentence Selection Using Transformer-Based Collaborative Models
A Aouichat, A Guessoum - Arabian Journal for Science and Engineering, 2024 - Springer
Accurately identifying pertinent text segments as answers to questions is crucial for
optimizing question-answering systems, underscoring the pivotal role of precision in Answer …
optimizing question-answering systems, underscoring the pivotal role of precision in Answer …
Efficient and Accurate Contextual Re-Ranking for Knowledge Graph Question Answering
The efficacy of neural “retrieve and generate” systems is well established for question
answering (QA) over unstructured text. Recent efforts seek to extend this approach to …
answering (QA) over unstructured text. Recent efforts seek to extend this approach to …
Domain-specific Answer Sentence Selection with Terminology Augmentation and Cascade Attention
X Lyu, D Ma, Y Chen - International Conference on Database Systems for …, 2024 - Springer
The online consulting service has become a popular and convenient channel for people to
seek professional replies. Since the replies are often lengthy, the answer highlighting is …
seek professional replies. Since the replies are often lengthy, the answer highlighting is …