To open the black box of GNN and investigate these problems, we dissect state-of-the-art GNN modules for QA and analyze their reasoning capability.
We successfully apply our ONSG framework to computational morphogenesis, a representative and challenging class of PDE-constrained optimization problems.
Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation.
Ranked #1 on Question Answering on DROP Test
Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be answered.
Ranked #16 on Question Answering on HotpotQA
Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT.
In this paper, we explore the combination of MLNs and GNNs, and use graph neural networks for variational inference in MLN.
Effectively combining logic reasoning and probabilistic inference has been a long-standing goal of machine learning: the former has the ability to generalize with small training data, while the latter provides a principled framework for dealing with noisy data.
Our model learns to reason with neural embeddings of both knowledge graphs.
Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts.
The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error.
To achieve the best performance, it is often critical to select optimal algorithms and to set appropriate hyperparameters, which requires large computational efforts.
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.