Question Answering over Freebase with Multi-Column Convolutional Neural Networks
By Li Dong, Furu Wei, M. Zhou, Ke Xu. 2015
456 citations recorded by the source corpus.
Answering natural language questions over a knowledge base is an important and challenging task. Most of existing systems typically rely on hand-crafted features and rules to conduct question understanding and/or answer ranking. In this paper, we introduce multi-column convolutional neural networks (MCCNNs) to understand questions from three different aspects (namely, answer path, answer context, and answer type) and learn their distributed representations. Meanwhile, we jointly learn low-dimensional embeddings of entities and relations in the knowledge base. Question-answer pairs are used to train the model to rank candidate answers. We also leverage question paraphrases to train the column networks in a multi-task learning manner. We use FREEBASE as the knowledge base and conduct extensive experiments on the WEBQUESTIONS dataset. Experimental results show that our method achieves better or comparable performance compared with baseline systems. In addition, we develop a method to compute the salience scores of question words in different column networks. The results help us intuitively understand what MCCNNs learn.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Mohit Bansal
- Percy Liang
- Jianfeng Gao
- Yejin Choi
- Zhiyuan Liu
- Quoc V. Le
- Graham Neubig
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Luc Van Gool
- Trevor Darrell
- Xiaogang Wang
- Yi Yang
- Cordelia Schmid
- Bernt Schiele
- Andrew Zisserman
In Question Answering & Reading Comprehension
Citations in the corpus
- RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “ercial KGs, such as NELL1, DBpedia2, Google Knowledge Graph3 and Microsoft Satori4. These knowledge graphs are successfully applied in many applications such as KG completion [13], question answering [7], word embedding [33], and text classification [29]. Inspired by the success of applying KG in a ”
- DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “Recently, the knowledge graph has also been used in many applications, such as movie recommendation[52], top-N recommendation [33], machine reading[51], text classification[46] embedding[49], and question answering [10].”
- Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, background): “It serves033 as a fundamental step for downstream tasks such as034 search and question answering (Dong et al., 2015;035 Yu et al., 2017).”
- Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “…“the president of ” from the given sentence “Newton served as the president of the Royal Society”, which could serve as external resource for various downstream applications (Dong et al., 2015; Xiong et al., 2017; Schlichtkrull et al., ∗ indicates equal contribution † Corresponding author 2018).”
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering (2016, background): “, 2014), convolution neural networks (Yih et al., 2014; Dong et al., 2015; Yin et al., 2015), attention models (Hermann et al.”
- BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, methodology): “Knowledge bases (KBs) (such as Freebase (Dong et al., 2015; Xu et al., 2016; Yao and Van Durme, 2014) or DBpedia (Lopez et al.”
- Question Answering as Global Reasoning Over Semantic Abstractions (2018, background): “This generalization to multiple semantic abstractions poses two key technical challenges: (a) unlike clean knowledge-bases (e.g., Dong et al. (2015)) used in many QA systems, abstractions generated from NLP tools (e.g., SRL) are noisy; and (b) even if perfect, using their output for QA requires…”
- Condition Aware and Revise Transformer for Question Answering (2020, background): “Recently, neural approaches are exploited to represent questions and external information using continuous vectors so that the inference can be performed in a hidden semantic space [4, 8, 18, 23, 26, 32, 34, 35].”
- Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks (2016, background): “, 2015) and other related tasks (Dong et al., 2015; Shen et al., 2014), so we expect them to be effective at isolating the relevant topic semantics for”
- Expert Finding for Community-Based Question Answering via Ranking Metric Network Learning (2016, background): “Elkahky et al. [Elkahky et al., 2015] develop the deep cross-domain model for recommendation .”
- LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, methodology): “Another line of KGQA meth-ods (Xu et al., 2016; Dong et al., 2015; Miller et al., 2016) aim to retrieve information from the KG using RL agent (Xiong et al., 2017; Qiu et al., 2020a; Lin et al., 2018; Das et al., 2018) or graph nets (Sun et al., 2018a; 2019a; Xiong et al., 2019), however, these…”
- HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding (2018, background): “KGs have been found to be useful for a variety of tasks, viz., Information Retrieval (Kotov and Zhai, 2012; Xiong and Callan, 2015), Question Answering (Dong et al., 2015; Bordes et al., 2015; Yao and Durme, 2014), among others.”
- A Survey of the Usages of Deep Learning for Natural Language Processing (2020, background): “[236] to automatically analyze questions from multiple viewpoints.”