Papers › EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System

EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System

6 Jan 2021arXiv:2101.02157archive 2025-07-28

Sofian Chaybouti, Achraf Saghe, Aymen Shabou

State-of-the-art extractive question answering models achieve superhuman performances on the SQuAD benchmark. Yet, they are unreasonably heavy and need expensive GPU computing to answer questions in a reasonable time. Thus, they cannot be used for real-world queries on hundreds of thousands of documents in the open-domain question answering paradigm. In this paper, we explore the possibility to transfer the natural language understanding of language models into dense vectors representing questions and answer candidates, in order to make the task of question-answering compatible with a simple nearest neighbor search task. This new model, that we call EfficientQA, takes advantage from the pair of sequences kind of input of BERT-based models to build meaningful dense representations of candidate answers. These latter are extracted from the context in a question-agnostic fashion. Our model achieves state-of-the-art results in Phrase-Indexed Question Answering (PIQA) beating the previous state-of-art by 1.3 points in exact-match and 1.4 points in f1-score. These results show that dense vectors are able to embed very rich semantic representations of sequences, although these ones were built from language models not originally trained for the use-case. Thus, in order to build more resource efficient NLP systems in the future, training language models that are better adapted to build dense representations of phrases is one of the possibilities.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Extractive Question-AnsweringNatural Language UnderstandingOpen-Domain Question AnsweringQuestion Answering

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQuAD1.1 EfficientQA 125M EM 74.9 #124 of 213 Archive leaderboard report
Question Answering SQuAD1.1 EfficientQA 125M F1 83.1 #124 of 213 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections