paper-with-me

Papers

AutoEQA: Auto-Encoding Questions for Extractive Question Answering

2021-11-01 · Findings (EMNLP) 2021 11 · Stalin Varanasi, Saadullah Amin, Guenter Neumann

There has been a significant progress in the field of Extractive Question Answering (EQA) in the recent years. However, most of them are reliant on annotations of answer-spans in the corresponding passages. In this work, we address the problem of EQA when no annotations are present for the answer span, i.e., when the dataset contains only questions and corresponding passages. Our method is based on auto-encoding of the question that performs a question answering task during encoding and a question generation task during decoding. We show that our method performs well in a zero-shot setting and can provide an additional loss to boost performance for EQA.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Extractive Question-AnsweringQuestion AnsweringQuestion GenerationQuestion-Generation

Similar Papers 제목 키워드 기반

Unsupervised Question Answering by Cloze Translation

2019-06-12 · ACL 2019 7 · Patrick Lewis, Ludovic Denoyer, Sebastian Riedel

Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high qu…

Natural QuestionsNMTQuestion AnsweringTranslation

Natural Questions in Icelandic

2022-06-01 · LREC 2022 6 · Vésteinn Snæbjarnarson, Hafsteinn Einarsson

We present the first extractive question answering (QA) dataset for Icelandic, Natural Questions in Icelandic (NQiI). Developing such datasets is important for the development and evaluation of Icelandic QA systems. It a…

Extractive Question-AnsweringNatural QuestionsQuestion Answering

GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions

2022-06-16 · Scott McCarley, Mihaela Bornea, Sara Rosenthal, Anthony Ferritto 외

Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We present a multilingual machine reading c…

GPUMachine Reading ComprehensionReading Comprehension

Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models

2021-08-09 · EMNLP (MRQA) 2021 11 · Bogdan Kostić, Julian Risch, Timo Möller

Open-domain extractive question answering works well on textual data by first retrieving candidate texts and then extracting the answer from those candidates. However, some questions cannot be answered by text alone but …

Extractive Question-AnsweringQuestion AnsweringRetrieval

SEMQA: Semi-Extractive Multi-Source Question Answering

2023-11-08 · Tal Schuster, Adam D. Lelkes, Haitian Sun, Jai Gupta 외

Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficu…

AttributeLong Form Question AnsweringQuestion AnsweringText Generation