activity
20162026
most citedTransfer Learning for Sequence Labeling Using Source Model and Target Data

16 citations · 48 across the 36 of their papers we have counts for

collaborators
Showing 2021Show all

10 papers · 1 filter

cs.CL2021

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation

Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski +2

Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we re…

cs.CL2021★ 1 cited

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

Siddhant Garg, Alessandro Moschitti

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…

cs.CL2021

Joint Models for Answer Verification in Question Answering Systems

Zeyu Zhang, Thuy Vu, Alessandro Moschitti

This paper studies joint models for selecting correct answer sentences among the top provided by answer sentence selection (AS2) modules, which are core components of retrieval…

cs.CL2021

Answer Generation for Retrieval-based Question Answering Systems

Chao-Chun Hsu, Eric Lind, Luca Soldaini +1

Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence sele…

cs.CL2021★ 4 cited

Efficient pre-training objectives for Transformers

Luca Di Liello, Matteo Gabburo, Alessandro Moschitti

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, R…

cs.CL2021

Reference-based Weak Supervision for Answer Sentence Selection using Web Data

Vivek Krishnamurthy, Thuy Vu, Alessandro Moschitti

Answer sentence selection (AS2) modeling requires annotated data, i.e., hand-labeled question-answer pairs. We present a strategy to collect weakly supervised answers for a questio…