Browse > Natural Language Processing > Question Answering > Open-Domain Question Answering

Open-Domain Question Answering

31 papers with code ยท Natural Language Processing
Subtask of Question Answering

Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.

Leaderboards

Latest papers without code

Context-Based Quotation Recommendation

17 May 2020

Our experiments confirm the strong performance of BERT-based methods on this task, which outperform bag-of-words and neural ranking baselines by more than 30% relative across all ranking metrics.

OPEN-DOMAIN QUESTION ANSWERING

BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA

2 May 2020

Khandelwal et al. (2020) show that a k-nearest-neighbor (kNN) component improves language modeling performance.

LANGUAGE MODELLING OPEN-DOMAIN QUESTION ANSWERING

Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering

7 Apr 2020

Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences.

INFORMATION RETRIEVAL OPEN-DOMAIN QUESTION ANSWERING

Talk to Papers: Bringing Neural Question Answering to Academic Search

4 Apr 2020

We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search.

OPEN-DOMAIN QUESTION ANSWERING

DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

28 Feb 2020

Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT.

OPEN-DOMAIN QUESTION ANSWERING

Open Domain Question Answering Using Web Tables

10 Jan 2020

Tables extracted from web documents can be used to directly answer many web search queries.

OPEN-DOMAIN QUESTION ANSWERING SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY

Contextualized Sparse Representation with Rectified N-Gram Attention for Open-Domain Question Answering

ICLR 2020

A sparse representation is known to be an effective means to encode precise lexical cues in information retrieval tasks by associating each dimension with a unique n-gram-based feature.

INFORMATION RETRIEVAL OPEN-DOMAIN QUESTION ANSWERING

What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge

31 Dec 2019

Open-domain question answering (QA) is known to involve several underlying knowledge and reasoning challenges, but are models actually learning such knowledge when trained on benchmark tasks?

KNOWLEDGE GRAPHS OPEN-DOMAIN QUESTION ANSWERING

Compositional De-Attention Networks

NeurIPS 2019

Attentional models are distinctly characterized by their ability to learn relative importance, i. e., assigning a different weight to input values.

MACHINE TRANSLATION NATURAL LANGUAGE INFERENCE OPEN-DOMAIN QUESTION ANSWERING SENTIMENT ANALYSIS