Semantic Parsing for Single-Relation Question Answering

Yih, Wen-tau; He, Xiaodong; Meek, Christopher

doi:10.3115/v1/p14-2105

Cited by 329 publications

(125 citation statements)

References 9 publications

Supporting

Mentioning

123

Contrasting

Order By: Relevance

“…Following this principle, a variety of neural net architectures and training approaches have been successfully applied [11], [13], [20], [22], [23], [39], [49], [58], [59], [60], [61], [65], [66]. Particularly, RNNs [22], [23], [49] are also widely used in NLP.…”

Section: Deep Learning Reviewmentioning

confidence: 99%

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Mesnil

Dauphin

Yao

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

471

372

View full text Add to dashboard Cite

Semantic slot filling is one of the most challenging problems in spoken language understanding (SLU). In this paper, we propose to use recurrent neural networks (RNNs) for this task, and present several novel architectures designed to efficiently model past and future temporal dependencies. Specifically, we implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants. To facilitate reproducibility, we implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark. In addition, we compared the approaches on two custom SLU data sets from the entertainment and movies domains. Our results show that the RNN-based models outperform the conditional random field (CRF) baseline by 2% in absolute error reduction on the ATIS benchmark. We improve the state-of-the-art by 0.5% in the Entertainment domain, and 6.7% for the movies domain.Index Terms-Recurrent neural network (RNN), slot filling, spoken language understanding (SLU), word embedding.

show abstract

Section: Deep Learning Reviewmentioning

confidence: 99%

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Mesnil

Dauphin

Yao

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

471

372

View full text Add to dashboard Cite

show abstract

“…Those expression problems make KBQA a further tough task. Previous works (Yih, He, and Meek 2014;Yih et al 2015) adopt letter-trigrams for the diverse expressions, which is similar to character level of Chinese. And the lattices are combinations of words and characters, so with lattices, we can utilize words information at the same time.…”

Section: Introductionmentioning

confidence: 99%

Lattice CNNs for Matching Based Chinese Question Answering

Lai

Feng

et al. 2019

AAAI

View full text Add to dashboard Cite

Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly. In this paper, we propose a novel lattice based CNN model (LCNs) to utilize multi-granularity information inherent in the word lattice while maintaining strong ability to deal with the introduced noisy information for matching based question answering in Chinese. We conduct extensive experiments on both document based question answering and knowledge based question answering tasks, and experimental results show that the LCNs models can significantly outperform the state-of-the-art matching models and strong baselines by taking advantages of better ability to distill rich but discriminative information from the word lattice input. 1

show abstract

“…Recent work in [17], [18] showed that a deep neural network (DNN) can be used to directly encode KGs for semantic parsing. By leveraging our prior work, this paper extends these KG methods in several ways.…”

Section: Introductionmentioning

confidence: 99%

“…By leveraging our prior work, this paper extends these KG methods in several ways. While the approach in [17] is single-relation Question Answering, our approach is large-scale multi-concept (entity, relation, fact) open domain semantic parsing. Our approach is web-scale, learning neural embeddings for all the concepts of Wikipedia in the open source Freebase KG [7].…”

Section: Introductionmentioning

confidence: 99%

Deep learning of knowledge graph embeddings for semantic parsing of Twitter dialogs

Heck

Huang

2014

2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

This paper presents a novel method to learn neural knowledge graph embeddings. The embeddings are used to compute semantic relatedness in a coherence-based semantic parser. The approach learns embeddings directly from structured knowledge representations. A deep neural network approach known as Deep Structured Semantic Modeling (DSSM) is used to scale the approach to learn neural embeddings for all of the concepts (pages) of Wikipedia. Experiments on Twitter dialogs show a 23.6% reduction in semantic parsing errors compared to the state-of-the-art unsupervised approach.

show abstract

Semantic Parsing for Single-Relation Question Answering

Cited by 329 publications

References 9 publications

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Lattice CNNs for Matching Based Chinese Question Answering

Deep learning of knowledge graph embeddings for semantic parsing of Twitter dialogs

Contact Info

Product

Resources

About