Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles).
#120 best model for Question Answering on SQuAD1.1
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC.
#4 best model for Question Answering on NarrativeQA
Answer sentence selection is the task of identifying sentences that contain the answer to a given question. This is an important problem in its own right as well as in the larger context of open domain question answering.
#3 best model for Question Answering on QASent
In this paper we study the problem of answering cloze-style questions over documents. Our model, the Gated-Attention (GA) Reader, integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader.
#2 best model for Question Answering on Children's Book Test
We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering.
Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches.
#5 best model for Open-Domain Question Answering on SearchQA
In this paper we look at a more practical setting, namely QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. We show that GRAFT-Net is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting.
Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation. However, they have minimal capability to link relevant facts distributed across multiple sentences which is crucial in achieving deeper understanding, such as performing multi-sentence reasoning, co-reference resolution, etc.
#2 best model for Question Answering on NewsQA
A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer.
First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of generating the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.