Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering

@inproceedings{Xu2019EnhancingKM,
  title={Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering},
  author={Kun Xu and Yuxuan Lai and Yansong Feng and Zhiguo Wang},
  booktitle={NAACL},
  year={2019}
}
Traditional Key-value Memory Neural Networks (KV-MemNNs) are proved to be effective to support shallow reasoning over a collection of documents in domain specific Question Answering or Reading Comprehension tasks. However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory. In this… Expand
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
TLDR
Neuro-Symbolic Question Answering (NSQA) is proposed, a modular KBQA system that leverages Abstract Meaning Representation (AMR) parses for task-independent question understanding and achieves state-of-the-art performance on two prominentKBQA datasets based on DBpedia. Expand
Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
TLDR
The Neural-Symbolic Complex Question Answering (NS-CQA) model is proposed, a data-efficient reinforcement learning framework for complex question answering by using only a modest number of training samples and outperforms the state-of-the-art models on two datasets. Expand
Memory Graph Networks for Explainable Memory-grounded Question Answering
TLDR
Memory Graph Networks (MGN) is proposed, a novel extension of memory networks to enable dynamic expansion of memory slots through graph traversals, thus able to answer queries in which contexts from multiple linked episodes and external knowledge are required. Expand
Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning
TLDR
A semantic parsing and reasoning-based Neuro-Symbolic Question Answering system that achieves state-of-the-art performance on QALD-9 and LC-QuAD 1.0 and integrates multiple, reusable modules that are trained specifically for their individual tasks and do not require end-to-end training data. Expand
A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
TLDR
The recent advances in complex QA are introduced, the methods of these branches are described, directions for future research are analyzed and the models proposed by the Alime team are introduced. Expand
Dual-Channel Reasoning Model for Complex Question Answering
  • Xing Cao, Yun Liu, Bo Hu, Yu Zhang
  • Computer Science
  • Complexity
  • 2021
TLDR
A dual-channel reasoning architecture is proposed, where two reasoning channels predict the final answer and supporting facts’ sentences, respectively, while sharing the contextual embedding layer. Expand
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
TLDR
The efficacy of the proposed architecture in the multi-passage generative QA is shown, outperforming the state-of-the-art baselines with better syntactically well-formed answers and increased precision in addressing the questions of the AmazonQA review dataset. Expand
Complex Knowledge Base Question Answering: A Survey
TLDR
A review of recent advances on KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. Expand
A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
TLDR
This paper elaborately summarize the typical challenges and solutions for complex KBQA, and presents the two mainstream categories of methods, namely semantic parsing-based (SP-based) methods and information retrieval-based [IR-based] methods. Expand
A Chinese Multi-type Complex Questions Answering Dataset over Wikidata
  • Jianyun Zou, Min Yang, +8 authors Zhou Zhao
  • Computer Science
  • ArXiv
  • 2021
TLDR
This work proposes CLC-QuAD, the first large scale complex Chinese semantic parsing dataset over Wikidata, and presents a text-toSPARQL baseline model, which can effectively answer multi-type complex questions, such as factual questions, dual intent questions, boolean questions, and counting questions, withWikidata as the background knowledge. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 22 REFERENCES
Key-Value Memory Networks for Directly Reading Documents
TLDR
This work introduces a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation. Expand
Question Answering over Knowledge Base using Factual Memory Networks
TLDR
Factual Memory Network is introduced, which learns to answer questions by extracting and reasoning over relevant facts from a Knowledge Base, and improves the run-time efficiency of the model using various computational heuristics. Expand
ReasoNet: Learning to Stop Reading in Machine Comprehension
TLDR
A novel neural network architecture called the Reasoning Network (ReasoNet) for machine comprehension tasks, which makes use of multiple turns to effectively exploit and then reason over the relation among queries, documents, and answers. Expand
Question Answering over Freebase with Multi-Column Convolutional Neural Networks
TLDR
This paper introduces multi-column convolutional neural networks (MCCNNs) to understand questions from three different aspects and learn their distributed representations and develops a method to compute the salience scores of question words in different column networks. Expand
Large-scale Simple Question Answering with Memory Networks
TLDR
This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions. Expand
Constraint-Based Question Answering with Knowledge Graph
TLDR
A novel systematic KBQA approach to solve multi-constraint questions is proposed, which not only obtains comparable results on the two existing benchmark data-sets, but also achieves significant improvements on the ComplexQuestions. Expand
Question Answering over Linked Data (QALD-5)
TLDR
The main objective of the open challenge on question answering over linked data (QALD) is to provide up-to-date, demanding benchmarks that establish a standard against which question answering systems over structured data can be evaluated and compared. Expand
Semantic Parsing on Freebase from Question-Answer Pairs
TLDR
This paper trains a semantic parser that scales up to Freebase and outperforms their state-of-the-art parser on the dataset of Cai and Yates (2013), despite not having annotated logical forms. Expand
More Accurate Question Answering on Freebase
TLDR
This work evaluates their system, called Aqqu, on two standard benchmarks, Free917 and WebQuestions, improving the previous best result for each benchmark considerably and fully addressing the inherent entity recognition problem, which was neglected in recent works. Expand
Lean Question Answering over Freebase from Scratch
TLDR
This work designs efficient data structures to identify question topics organically from 46 million Freebase topic names, without employing any NLP processing tools, and presents a lean QA system that runs in real time. Expand
...
1
2
3
...