Open Domain Question Answering Based on Retriever-Reader Architecture

2021 ◽  
pp. 723-733
Author(s):  
Dequan Zheng ◽  
Jing Yang ◽  
Baishuo Yong
Keyword(s):  
Question Answering ◽  
Open Domain

scholarly journals Don’t Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering

2020 ◽  
Author(s):  
Yuxiang Wu ◽  
Pasquale Minervini ◽  
Pontus Stenetorp ◽  
Sebastian Riedel
Keyword(s):  
Question Answering ◽  
Open Domain ◽  
Adaptive Computation

scholarly journals New Measures for Open-Domain Question Answering Evaluation Within a Time Constraint

2007 ◽  
pp. 540-547
Author(s):  
Elisa Noguera ◽  
Fernando Llopis ◽  
Antonio Ferrández ◽  
Alberto Escapa
Keyword(s):  
Question Answering ◽  
Time Constraint ◽  
Open Domain

scholarly journals R2-D2: A Modular Baseline for Open-Domain Question Answering

2021 ◽  
Author(s):  
Martin Fajcik ◽  
Martin Docekal ◽  
Karel Ondrej ◽  
Pavel Smrz
Keyword(s):  
Question Answering ◽  
Open Domain

scholarly journals Relevance-guided Supervision for OpenQA with ColBERT

2021 ◽  
Vol 9 ◽  
pp. 929-944
Author(s):  
Omar Khattab ◽  
Christopher Potts ◽  
Matei Zaharia
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Training Data ◽  
Coarse Grained ◽  
Retrieval Model ◽  
Open Domain ◽  
Weak Supervision ◽  
Fine Grained ◽  
Vector Representations ◽  
Large Corpus

Abstract Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned component that uses coarse-grained vector representations of questions and passages. We argue that this modeling choice is insufficiently expressive for dealing with the complexity of natural language questions. To address this, we define ColBERT-QA, which adapts the scalable neural retrieval model ColBERT to OpenQA. ColBERT creates fine-grained interactions between questions and passages. We propose an efficient weak supervision strategy that iteratively uses ColBERT to create its own training data. This greatly improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA, and the resulting system attains state-of-the-art extractive OpenQA performance on all three datasets.

Events Automatic Extraction from Arabic Texts

2020 ◽  
pp. 1686-1704
Author(s):  
Emna Hkiri ◽  
Souheyl Mallat ◽  
Mounir Zrigui
Keyword(s):  
Information Retrieval ◽  
Natural Language Processing ◽  
Text Mining ◽  
Machine Translation ◽  
Language Processing ◽  
Question Answering ◽  
Arabic Language ◽  
Event Extraction ◽  
Mining Machine ◽  
Open Domain

The event extraction task consists in determining and classifying events within an open-domain text. It is very new for the Arabic language, whereas it attained its maturity for some languages such as English and French. Events extraction was also proved to help Natural Language Processing tasks such as Information Retrieval and Question Answering, text mining, machine translation etc… to obtain a higher performance. In this article, we present an ongoing effort to build a system for event extraction from Arabic texts using Gate platform and other tools.

Predicting Lexical Answer Types in Open Domain QA

2012 ◽  
Vol 8 (3) ◽  
pp. 74-88 ◽  
Author(s):  
Alfio Massimiliano Gliozzo ◽  
Aditya Kalyanpur
Keyword(s):  
Knowledge Acquisition ◽  
Knowledge Base ◽  
Large Scale ◽  
Question Answering ◽  
General Purpose ◽  
Open Domain ◽  
Lexical Knowledge ◽  
Research Challenge ◽  
Lexical Knowledge Base

Automatic open-domain Question Answering has been a long standing research challenge in the AI community. IBM Research undertook this challenge with the design of the DeepQA architecture and the implementation of Watson. This paper addresses a specific subtask of Deep QA, consisting of predicting the Lexical Answer Type (LAT) of a question. Our approach is completely unsupervised and is based on PRISMATIC, a large-scale lexical knowledge base automatically extracted from a Web corpus. Experiments on the Jeopardy! data shows that it is possible to correctly predict the LAT in a substantial number of questions. This approach can be used for general purpose knowledge acquisition tasks such as frame induction from text.

Sign in / Sign up

Export Citation Format

Share Document