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

Heck, Larry; Huang, Hongzhao

doi:10.1109/globalsip.2014.7032187

Cited by 27 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite many years of research, the slot filling task in SLU is still a challenging problem, and this has motivated the recent application of a number of very successful continuous-space, neural net, and deep learning approaches, e.g. [13], [15], [24], [30], [56], [64].…”

mentioning

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

mentioning

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

“…Mapping graph representations into continuous space has been proposed in previous work [134,52]. For this purpose, an autoencoder is often used to learn a compact feature representation for a given input.…”

Section: Graph Embedding Using Autoencodersmentioning

confidence: 99%

“…In [52], the authors use neural embeddings of a semantic knowledge-graph for the purpose of semantic parsing. In [139], the authors propose a 'generalized autoencoder' which extends the traditional autoencoder by taking manifold information into the reconstruction term of the autoencoder training.…”

Section: Previous Workmentioning

confidence: 99%

“…The DNN learner can thus implicitly combine different information sources in the best possible way. While neural graph embeddings have been utilized previously in clustering [134] and in natural language understanding [52], their use in acoustic modeling is to our knowledge novel. In addition, we address the computational issues by landmark-based graph construction, which reduces the cost by orders of magnitude while yielding good performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech Recognition

Liu

Kirchhoff

2016

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Graph-based semi-supervised learning (SSL) is a widely used semi-supervised learning method in which the labeled data and unlabeled data are jointly represented as a weighted graph, and the information is propagated from the labeled data to the unlabeled data. The key assumption that graph-based SSL makes is that data samples lie on a low dimensional manifold, where samples that are close to each other are expected to have the same class label. More importantly, by exploiting the relationship between training and test samples, graph-based SSL implicitly adapts to the test data.In this thesis, we address several key challenges in applying graph-based SSL to acoustic modeling. We first investigate and compare several state-of-the-art graph-based SSL algorithms on a benchmark dataset. In addition, we propose novel graph construction methods that allow graph-based SSL to handle variable-length input features. We next investigate the efficacy of graph-based SSL in context of a fully-fledged DNN-based ASR system. We compare two different integration frameworks for graph-based learning. First, we propose a lattice-based late integration framework that combines graph-based SSL with the DNN-based acoustic modeling and evaluate the framework on continuous word recognition tasks. Second, we propose an early integration framework using neural graph embeddings and compare two different neural graph embedding features that capture the information of the manifold at different levels. The embedding features are used as input to a DNN system and are shown to outperform the conventional acoustic feature inputs on several medium-to-large vocabulary conversational speech recognition tasks.

show abstract

“…Feeding into the input vector is a feature vector which contains linked entities, relations, entity types, and a bag-of-words representation of its description. Entity embeddings can also be extracted from this model once it is trained [51].…”

Section: Entity Recognition and Disambiguationmentioning

confidence: 99%

Improving Dialog Systems Using Knowledge Graph Embeddings

Carignan¹

View full text Add to dashboard Cite

Dialog systems are systems or applications intended to converse with a human user. Recent dialog systems have employed the sequence-to-sequence framework to treat conversation as a translation problem, translating from question to answer in an opendomain. Knowledge graph embedding started as a way to scale question answering to a large, open-domain dataset without the use of hand-crafted rules. This thesis seeks to connect the two, by converting knowledge graph embeddings to word embeddings and evaluating the resulting dialog models.To accomplish the above, an adaptable preprocessing pipeline was developed for the Freebase knowledge graph, which was embedded using TransE and TransH. A baseline method was proposed to convert the resulting embedding to word embeddings, to be compared with GloVe and Word2Vec. The four embedding sets were trained with a sequence-to-sequence model from OpenNMT on a dialog dataset from OpenSubtitles. Each model was trained twice, with embeddings variable and fixed. A beam search post-processing method is proposed to generate more diverse answers. A probable response evaluation method is proposed as a way to compare the top answers from a set of dialog systems.The resulting knowledge graph embeddings were found comparable to the baseline word embedding methods, suggesting they could be used as an alternative for training future dialog systems.iii To my family, thank you for supporting me and helping me get to where I am today. To Professor Anthony White, the feedback and discussions were invaluable from the beginning, thank you.

show abstract

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

Cited by 27 publications

References 20 publications

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech Recognition

Improving Dialog Systems Using Knowledge Graph Embeddings

Contact Info

Product

Resources

About