• Corpus ID: 3925660

Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information

  title={Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information},
  author={Yuanzhe Zhang and Kang Liu and Shizhu He and Guoliang Ji and Zhanyi Liu and Hua Wu and Jun Zhao},
With the rapid growth of knowledge bases (KBs) on the web, how to take full advantage of them becomes increasingly important. [] Key Method Hence, we present a neural attention-based model to represent the questions dynamically according to the different focuses of various candidate answer aspects. In addition, we leverage the global knowledge inside the underlying KB, aiming at integrating the rich KB information into the representation of the answers.

Figures and Tables from this paper

Incremental Knowledge Based Question Answering

A new incremental KBQA learning framework that can progressively expand learning capacity as humans do is proposed, which comprises a margin-distilled loss and a collaborative exemplar selection method, to overcome the catastrophic forgetting problem by taking advantage of knowledge distillation.

Knowledge Base Question Answering Based on Deep Learning Models

This paper proposes a topic entity extraction model (TEEM) to extract topic entities in questions, which does not rely on hand-crafted features or linguistic tools, and applies Deep Structured Semantic Models based on convolutional neural network and bidirectional long short-term memory to match questions and predicates in the candidate knowledge triples.

A Survey of Question Answering over Knowledge Base

A survey of KBQA approaches is given by classifying them in two categories, and current mainstream techniques in KBZA are introduced, and similarities and differences among them are discussed.

Topic enhanced deep structured semantic models for knowledge base question answering

The proposed topic enhanced deep structured semantic model considers the task of KBQA as a matching problem between questions and the subjects and predicates in knowledge base and achieves the third place among the 21 submitted systems.

A Question Answering Framework Based on Hybridization of Deep Learning and Semantic Web Techniques

This research proposes a hybrid of recurrent neural network and semantic-web-based question answering as the (RNNSQA) framework that combines heterogeneous knowledge sources and improves on state-of-the-art query generation mechanisms to allow for integration of comprehensive question-type operations, and set-based operations.


The proposed DNA approach performs the QA system over DBN by applying alternate skip-N gram and negative sampling, which improves the efficiency of relevant word-pair detection without increasing the computational complexity.

FAQ-based Question Answering via Knowledge Anchors

A novel Knowledge Anchor based Question Answering (KAQA) framework for FAQ-based QA that considers entities and triples of KGs in texts as knowledge anchors to precisely capture the core semantics, which brings in higher precision and better interpretability.

Core techniques of question answering systems over knowledge bases: a survey

An overview of the techniques used in current QA systems over KBs is given, which were evaluated on a popular series of benchmarks: Question Answering over Linked Data and WebQuestions.

Chinese Knowledge Base Question Answering by Attention-Based Multi-Granularity Model

A hierarchical matching model for question representation in relation selection tasks, and attention mechanisms are imported for a fine-grained alignment between characters for relation selection in KBQA.

Introduction to neural network‐based question answering over knowledge graphs

This article aims to provide newcomers to the field with a suitable entry point to semantic parsing for KGQA, and ease their process of making informed decisions while creating their own QA systems.



Question Answering over Freebase with Multi-Column Convolutional Neural Networks

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.

Joint Relational Embeddings for Knowledge-based Question Answering

This paper proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space.

Open Question Answering with Weakly Supervised Embedding Models

This paper empirically demonstrate that the model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.

An Introduction to Question Answering over Linked Data

This tutorial gives an introduction to the rapidly developing field of question answering over linked data and gives an overview of the main challenges involved in the interpretation of a user’s information need expressed in natural language with respect to the data that is queried.

Semantic Parsing for Single-Relation Question Answering

A semantic parsing framework based on semantic similarity for open domain question answering (QA) that achieves higher precision across different recall points compared to the previous approach, and can improve F1 by 7 points.

Large-scale Simple Question Answering with Memory Networks

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.

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

This work proposes a novel semantic parsing framework for question answering using a knowledge base that leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem.

Information Extraction over Structured Data: Question Answering with Freebase

It is shown that relatively modest information extraction techniques, when paired with a webscale corpus, can outperform these sophisticated approaches by roughly 34% relative gain.

Question Answering with Subgraph Embeddings

A system which learns to answer questions on a broad range of topics from a knowledge base using few hand-crafted features, using low-dimensional embeddings of words and knowledge base constituents to score natural language questions against candidate answers.

Semantic Parsing on Freebase from Question-Answer Pairs

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.