Improved Neural Relation Detection for Knowledge Base Question Answering

By Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, C. D. Santos, Bing Xiang, Bowen Zhou. 2017

322 citations recorded by the source corpus.

Relation detection is a core component of many NLP applications including Knowledge Base Question Answering (KBQA). In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning which detects KB relations given an input question. Our method uses deep residual bidirectional LSTMs to compare questions and relation names via different levels of abstraction. Additionally, we propose a simple KBQA system that integrates entity linking and our proposed relation detector to make the two components enhance each other. Our experimental results show that our approach not only achieves outstanding relation detection performance, but more importantly, it helps our KBQA system achieve state-of-the-art accuracy for both single-relation (SimpleQuestions) and multi-relation (WebQSP) QA benchmarks.

Subfields: Artificial Intelligence, Information Retrieval & Search, Natural Language Processing

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

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, background): “The task is to produce the answer to a question by exploiting resources such as documents (Voorhees, 1999), webpages (Kwok et al., 2001) or structured knowledge bases (Berant et al., 2013; Bordes et al., 2015; Yu et al., 2017).”
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, background): “It serves as a fundamental step for downstream tasks such as search and question answering (Dong et al., 2015; Yu et al., 2017).”
Curriculum-Meta Learning for Order-Robust Continual Relation Extraction (2021, methodology): “With a given basic relation extraction model (Yu et al. 2017) fθ(.”
Sentence Embedding Alignment for Lifelong Relation Extraction (2019, methodology): “(Yu et al., 2017) created a relation detection dataset from SimpleQues-tions that contains samples of question-relation pairs.”
R3: Reinforced Reader-Ranker for Open-Domain Question Answering (2017, background): “The task is to produce the answer to a question by exploiting resources such as documents (Voorhees, 1999), webpages (Kwok et al., 2001) or structured knowledge bases (Berant et al., 2013; Bordes et al., 2015; Yu et al., 2017).”
Meta-Learning Improves Lifelong Relation Extraction (2019, methodology): “Finally, the model parameters are updated to the current task’s adapted parameters (line 19). end for 16: Update task parameters: arachical Residual BiLSTM ( HR-BiLSTM ) model of Yu et al. (2017), which is the same model used by Wang et al. (2019) for their experiments.”
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].”
SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach (2018, unknown): “0 BiLSTM-CRF (Yu et al., 2017) BiLSTM-CRF & BiLSTM (Ours) 78.”
Statistical learning for semantic parsing: A survey (2019, unknown): “[82] with accuracy 78.7%.”
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (2019, result): “Here we do not compare with existing methods that utilize semantic parsing annotations (Yih et al., 2016; Yu et al., 2017).”
Leveraging Domain Context for Question Answering Over Knowledge Graph (2019, background): “[30] discussed relation detection for precise question match with edge descriptions.”
R3: Reinforced Ranker-Reader for Open-Domain Question Answering (2018, background): “The task is to answer a question by exploiting resources such as documents (Voorhees 1999), webpages (Kwok, Etzioni, and Weld 2001; Chen and Van Durme 2017) or structured knowledge bases (Berant et al. 2013; Bordes et al. 2015; Yu et al. 2017).”
Attention Guided Graph Convolutional Networks for Relation Extraction (2019, background): “It plays a signiﬁcant role in a variety of natural language processing applications including biomedical knowledge discovery (Quirk and Poon, 2017), knowledge base population (Zhang et al., 2017) and question answering (Yu et al., 2017).”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, background): “Answering complex natural language questions with multi-hop reasoning steps on incomplete knowledge graphs (KGs) is a fundamental, yet challenging task (KGQA) (Sun et al., 2019a; Saxena et al., 2020; Bordes et al., 2014; Xu et al., 2016; Yu et al., 2017; Liang et al., 2017).”
A Multi-Channel Deep Neural Network for Relation Extraction (2020, unknown): “The residual connection can be used to concatenate highly order features in different level [44], [45].”
FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase (2019, methodology): “Finally, we use FOFE-net (Zhang et al., 2015; Xu et al., 2017) to build a baseline KBQA system on FreebaseQA, which consists of subject detection, entity linking and relation detection in the pipeline.”