Multi-hop Question Answering
56 papers with code • 2 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Multi-hop Question Answering
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Multi-hop Question Answering models and implementations
SPARTQA -
MuSiQue-Ans
ConcurrentQA Benchmark
MultiQ
Most implemented papers
Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning
For a recent large-scale model (XLNet), we show that only 18 points out of its answer F1 score of 72 on HotpotQA are obtained through multifact reasoning, roughly the same as that of a simpler RNN baseline.
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method.
SRLGRN: Semantic Role Labeling Graph Reasoning Network
HLR/SRLGRN
•
•
EMNLP 2020
This work deals with the challenge of learning and reasoning over multi-hop question answering (QA).
Unsupervised Multi-hop Question Answering by Question Generation
teacherpeterpan/Unsupervised-Multi-hop-QA
•
•
NAACL 2021
Obtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
DevinJake/NS-CQA
•
•
Our framework consists of a neural generator and a symbolic executor that, respectively, transforms a natural-language question into a sequence of primitive actions, and executes them over the knowledge base to compute the answer.
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Alab-NII/2wikimultihop
•
•
COLING 2020
The evidence information has two benefits: (i) providing a comprehensive explanation for predictions and (ii) evaluating the reasoning skills of a model.
VisBERT: Hidden-State Visualizations for Transformers
bvanaken/visbert
•
•
At the same time, they are difficult to incorporate into the large, black-box models that achieve state-of-the-art results in a multitude of NLP tasks.
[Re] Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
jishnujayakumar/MLRC2020-EmbedKGQA
•
•
RC 2020
In addition to making the codebase more modular and easy to navigate, we have made changes to incorporate different transformers in the question embedding module.
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
henryzhao5852/BeamDR
•
•
NAACL 2021
Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces.
TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
shijx12/TransferNet
•
•
EMNLP 2021
Multi-hop Question Answering (QA) is a challenging task because it requires precise reasoning with entity relations at every step towards the answer.
