Improved Neural Relation Detection for Knowledge Base Question Answering

Yu, Mo; Yin, Wenpeng; Hasan, Kazi Saidul; Santos, Cícero Nogueira dos; Xiang, Bing; Zhou, Bowen

doi:10.18653/v1/p17-1053

Cited by 273 publications

(264 citation statements)

References 26 publications

Supporting

Mentioning

256

Contrasting

Order By: Relevance

“…Yu, M., etc. [25] proposed a hierarchical RNN network by using residual learning to improve the performance in 2017. When there is an input question, it can detect the relation inside the knowledge base.…”

Section: Problem Formulation and Related Workmentioning

confidence: 99%

HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention

Qiming

Liu

2020

Proceedings of the Australasian Computer Science Week Multiconference

View full text Add to dashboard Cite

This paper proposes a chatbot framework that adopts a hybrid model which consists of a knowledge graph and a text similarity model. Based on this chatbot framework, we build HHH, an online question-and-answer (QA) Healthcare Helper system for answering complex medical questions. HHH maintains a knowledge graph constructed from medical data collected from the Internet. HHH also implements a novel text representation and similarity deep learning model, Hierarchical BiLSTM Attention Model (HBAM), to find the most similar question from a large QA dataset. We compare HBAM with other state-of-the-art language models such as bidirectional encoder representation from transformers (BERT) and Manhattan LSTM Model (MaLSTM). We train and test the models with a subset of the Quora duplicate questions dataset in the medical area. The experimental results show that our model is able to achieve a superior performance than these existing methods.

show abstract

Section: Problem Formulation and Related Workmentioning

confidence: 99%

HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention

Qiming

Liu

2020

Proceedings of the Australasian Computer Science Week Multiconference

View full text Add to dashboard Cite

show abstract

“…LSTM [6] 70.9 GRU [11] 71.2 BuboQA [13] 74.9 BiGRU [4] 75.7 Attn. CNN [23] 76.4 HR-BiLSTM [24] 77.0 BiLSTM-CRF [16] all but one of the existing approaches. We suspect that the final score can be further improved by finding better rules for logical form selection, however that is not the goal of this study.…”

Section: Approach Accuracymentioning

confidence: 99%

“…[11] explore building question representations on both word-and character-level. [24] explore relation detection in-depth and propose a hierarchical word-level and symbol-level residual representation. Both [4] and [11] improve upon them by incorporating structural information such as entity type for entity linking.…”

Section: Related Workmentioning

confidence: 99%

Pretrained Transformers for Simple Question Answering over Knowledge Graphs

Lukovnikov

Fischer

Lehmann

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings. It was recently shown that finetuning pretrained transformer networks (e.g. BERT) can outperform previous approaches on various natural language processing tasks. In this work, we investigate how well BERT performs on SIMPLEQUESTIONS and provide an evaluation of both BERT and BiLSTMbased models in limited-data scenarios.

show abstract

“…Adapting the Relation Representation The relation network proposed in Yu et al (2017) has two parts for relation representations: one is at wordlevel and the other is at relation-level. The two parts are fed into the relation network to generate the final relation representation.…”

Section: Relation Detection With the Adaptermentioning

confidence: 99%

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering

Wu¹,

Huang²,

Weng³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Relation detection is a core step in many natural language process applications including knowledge base question answering. Previous efforts show that single-fact questions could be answered with high accuracy. However, one critical problem is that current approaches only get high accuracy for questions whose relations have been seen in the training data. But for unseen relations, the performance will drop rapidly. The main reason for this problem is that the representations for unseen relations are missing. In this paper, we propose a simple mapping method, named representation adapter, to learn the representation mapping for both seen and unseen relations based on previously learned relation embedding. We employ the adversarial objective and the reconstruction objective to improve the mapping performance. We re-organize the popular Sim-pleQuestion dataset to reveal and evaluate the problem of detecting unseen relations. Experiments show that our method can greatly improve the performance of unseen relations while the performance for those seen part is kept comparable to the state-of-the-art. 1

show abstract

Improved Neural Relation Detection for Knowledge Base Question Answering

Cited by 273 publications

References 26 publications

HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention

HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention

Pretrained Transformers for Simple Question Answering over Knowledge Graphs

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering

Contact Info

Product

Resources

About