Recent advances in natural language processing via large pre-trained language models: A survey
Large, pre-trained language models (PLMs) such as BERT and GPT have drastically
changed the Natural Language Processing (NLP) field. For numerous NLP tasks …
changed the Natural Language Processing (NLP) field. For numerous NLP tasks …
Answer generation for retrieval-based question answering systems
Recent advancements in transformer-based models have greatly improved the ability of
Question Answering (QA) systems to provide correct answers; in particular, answer sentence …
Question Answering (QA) systems to provide correct answers; in particular, answer sentence …
Will this question be answered? question filtering via answer model distillation for efficient question answering
S Garg, A Moschitti - arXiv preprint arXiv:2109.07009, 2021 - arxiv.org
In this paper we propose a novel approach towards improving the efficiency of Question
Answering (QA) systems by filtering out questions that will not be answered by them. This is …
Answering (QA) systems by filtering out questions that will not be answered by them. This is …
Answer sentence selection using local and global context in transformer models
I Lauriola, A Moschitti - European Conference on Information Retrieval, 2021 - Springer
An essential task for the design of Question Answering systems is the selection of the
sentence containing (or constituting) the answer from documents relevant to the asked …
sentence containing (or constituting) the answer from documents relevant to the asked …
BAS: an answer selection method using BERT language model
In recent years, Question Answering systems have become more popular and widely used
by users. Despite the increasing popularity of these systems, the their performance is not …
by users. Despite the increasing popularity of these systems, the their performance is not …
Cross-lingual knowledge distillation for answer sentence selection in low-resource languages
While impressive performance has been achieved on the task of Answer Sentence Selection
(AS2) for English, the same does not hold for languages that lack large labeled datasets. In …
(AS2) for English, the same does not hold for languages that lack large labeled datasets. In …
PerAnSel: A Novel Deep Neural Network‐Based System for Persian Question Answering
Question answering (QA) systems have attracted considerable attention in recent years.
They receive the user's questions in natural language and respond to them with precise …
They receive the user's questions in natural language and respond to them with precise …
FocusQA: Open-domain question answering with a context in focus
We introduce question answering with a cotext in focus, a task that simulates a free
interaction with a QA system. The user reads on a screen some information about a topic …
interaction with a QA system. The user reads on a screen some information about a topic …
Ensemble transformer for efficient and accurate ranking tasks: an application to question answering systems
Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but
their high computational costs prevent their use in many real-world applications. In this …
their high computational costs prevent their use in many real-world applications. In this …
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 …