paper-with-me

홈 › Papers

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

2021-01-06 · 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.

📄 PDF Abstract BibTeX arXiv:2101.02157

Code (0)

등록된 구현이 없습니다.

Tasks

Extractive Question-AnsweringGPUNatural Language UnderstandingOpen-Domain Question AnsweringQuestion Answering

Similar Papers 제목 키워드 기반

Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension

2018-04-20 · EMNLP 2018 10 · Minjoon Seo, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi 외

We formalize a new modular variant of current question answering tasks by enforcing complete independence of the document encoder from the question encoder. This formulation addresses a key challenge in machine comprehen…

Question AnsweringReading ComprehensionRetrieval

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

2021-01-01 · Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen 외

We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-domain question answering (QA), where systems take natural language questions as input and return natural language answers. The aim…

Open-Domain Question AnsweringQuestion AnsweringRetrieval

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

2021-06-15 · Findings (ACL) 2022 5 · Robin Jia, Mike Lewis, Luke Zettlemoyer

We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Question Answering+1

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Question Answering+1

Learning Dense Representations of Phrases at Scale

2020-12-23 · ACL 2021 5 · Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen

Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019). However, current phrase retrieval models heavily …

Open-Domain Question AnsweringQuestion AnsweringQuestion GenerationReading Comprehension+3