no code implementations • 3 Jun 2023 • Minh Van Nguyen, Kishan Kc, Toan Nguyen, Thien Huu Nguyen, Ankit Chadha, Thuy Vu
In this paper, we propose to improve the candidate scoring by explicitly incorporating the dependencies between question-context and answer-context into the final representation of a candidate.
no code implementations • NeurIPS Workshop DBAI 2021 • Nic Jedema, Thuy Vu, Manish Gupta, Alessandro Moschitti
While transformers demonstrate impressive performance on many knowledge intensive (KI) tasks, their ability to serve as implicit knowledge bases (KBs) remains limited, as shown on several slot-filling, question-answering (QA), fact verification, and entity-linking tasks.
no code implementations • 16 Feb 2022 • Roshni G. Iyer, Thuy Vu, Alessandro Moschitti, Yizhou Sun
This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems.
no code implementations • 16 Jan 2022 • Zeyu Zhang, Thuy Vu, Alessandro Moschitti
Recent work has shown that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering.
no code implementations • 16 Jan 2022 • Zeyu Zhang, Thuy Vu, Alessandro Moschitti
Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of possible candidates, i. e., sentences, extracted from the retrieved text.
no code implementations • ACL 2021 • Zeyu Zhang, Thuy Vu, Alessandro Moschitti
This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems.
no code implementations • NAACL 2021 • Thuy Vu, Alessandro Moschitti
We introduce AVA, an automatic evaluation approach for Question Answering, which given a set of questions associated with Gold Standard answers (references), can estimate system Accuracy.
no code implementations • Findings (EMNLP) 2021 • Vivek Krishnamurthy, Thuy Vu, Alessandro Moschitti
Answer sentence selection (AS2) modeling requires annotated data, i. e., hand-labeled question-answer pairs.
1 code implementation • 20 Feb 2021 • Thuy Vu, Alessandro Moschitti
Machine translation (MT) systems, especially when designed for an industrial setting, are trained with general parallel data derived from the Web.
no code implementations • 20 Feb 2021 • Thuy Vu, Alessandro Moschitti
We present a study on the design of multilingual Answer Sentence Selection (AS2) models, which are a core component of modern Question Answering (QA) systems.
no code implementations • EACL 2021 • Thuy Vu, Alessandro Moschitti
We introduce a Content-based Document Alignment approach (CDA), an efficient method to align multilingual web documents based on content in creating parallel training data for machine translation (MT) systems operating at the industrial level.
no code implementations • 2 May 2020 • Thuy Vu, Alessandro Moschitti
This allows for effectively measuring the similarity between the reference and an automatic answer, biased towards the question semantics.
2 code implementations • AAAI 2020 2019 • Siddhant Garg, Thuy Vu, Alessandro Moschitti
Additionally, we show that the transfer step of TANDA makes the adaptation step more robust to noise.
Ranked #2 on Question Answering on TrecQA (using extra training data)