Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
arXiv (Cornell University)Published 1 November 2017Open access
Anjishnu Kumar, Arpit Gupta, Julian Chan, Sam Tucker, Björn Hoffmeister, Markus Dreyer
Citations56
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) is presented, which was the first Spoken Language Understanding Software Development Kit (SDK) for a virtual digital assistant, as far as the authors are aware.
Abstract
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa. At Amazon, the infrastructure powers over 25,000 skills deployed through the ASK, as well as AWS's Amazon Lex SLU Service. The ASK emphasizes flexibility, predictability and a rapid iteration cycle for third party developers. It imposes inductive biases that allow it to learn robust SLU models from extremely small and sparse datasets and, in doing so, removes significant barriers to entry for software developers and dialogue systems researchers.
Keywords
Computer Science
Glove: Global Vectors for Word Representation
33,769 Citations2014Jeffrey Pennington, Richard Socher +1 more
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Journal of the Royal Statistical Society Series B (Statistical Methodology)Regularization and Variable Selection Via the Elastic Net
20,982 Citations2005Hui Zou, Trevor Hastie
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
The Stanford CoreNLP Natural Language Processing Toolkit
7,238 Citations2014Christopher D. Manning, Mihai Surdeanu +4 more
The design and use of the Stanford CoreNLP toolkit is described, an extensible pipeline that provides core natural language analysis, and it is suggested that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
arXiv (Cornell University)Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
5,634 Citations2016Yonghui Wu, Mike Schuster +29 more
GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.
Kaldi Speech Recognition Toolkit
4,893 Citations2024Daniel Povey
The design of Kaldi is described, a free, open-source toolkit for speech recognition research that provides a speech recognition system based on finite-state automata together with detailed documentation and a comprehensive set of scripts for building complete recognition systems.
Neural Architectures for Named Entity Recognition
4,428 Citations2016Guillaume Lample, Miguel Ballesteros +3 more
Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 of juny 2016.
Computational LinguisticsA maximum entropy approach to natural language processing
3,120 Citations1996Adam Berger, Vincent J. Della Pietra +1 more
A maximum-likelihood approach for automatically constructing maximum entropy models is presented and how to implement this approach efficiently is described, using as examples several problems in natural language processing.
arXiv (Cornell University)MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
1,916 Citations2015Tianqi Chen, Mu Li +8 more
The API design and the system implementation of MXNet are described, and it is explained how embedding of both symbolic expression and tensor operation is handled in a unified fashion.
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
1,725 Citations2016Iulian Vlad Serban, Alessandro Sordoni +3 more
ArXiv.orgFrustratingly Easy Domain Adaptation
1,395 Citations2009Hal Daumé
This work describes an approach to domain adaptation that is appropriate exactly in the case when one has enough “target” data to do slightly better than just using only “source’ data.
Feature hashing for large scale multitask learning
937 Citations2009Kilian Q. Weinberger, Anirban Dasgupta +3 more
This paper provides exponential tail bounds for feature hashing and shows that the interaction between random subspaces is negligible with high probability, and demonstrates the feasibility of this approach with experimental results for a new use case --- multitask learning.
Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
698 Citations2016Bing Liu, Ian Lane
This work proposes an attention-based neural network model for joint intent detection and slot filling, both of which are critical steps for many speech understanding and dialog systems.
Data Recombination for Neural Semantic Parsing
454 Citations2016Robin Jia, Percy Liang
Data recombination improves the accuracy of the RNN model on three semantic parsing datasets, leading to new state-of-the-art performance on the standard GeoQuery dataset for models with comparable supervision.
ACM Computing SurveysAmbient intelligence
356 Citations2011Fariba Sadri
The applications of ambient intelligence are surveyed, including its applications, some of the technologies it uses, and its social and ethical implications; for example planning, learning, event-condition-action rules, temporal reasoning, and agent-oriented technologies.
Scientific Repository (Petra Christian University)The HTK hidden Markov model toolkit: design and philosophy
343 Citations1993SJ Young
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
341 Citations2017J. D. Williams, Kavosh Asadi +1 more
This work introduces Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates, and considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state.
Spoken language understanding using long short-term memory neural networks
333 Citations2014Kaisheng Yao, Baolin Peng +4 more
This paper investigates using long short-term memory (LSTM) neural networks, which contain input, output and forgetting gates and are more advanced than simple RNN, for the word labeling task and proposes a regression model on top of the LSTM un-normalized scores to explicitly model output-label dependence.
Proceedings of the IEEEConversational interfaces: advances and challenges
247 Citations2000Victor W. Zue, James Glass
arXiv (Cornell University)A Deep Reinforcement Learning Chatbot
198 Citations2017Iulian Vlad Serban, Chinnadhurai Sankar +16 more
MILA's MILABOT is capable of conversing with humans on popular small talk topics through both speech and text and consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models.
Bringing contextual information to google speech recognition
96 Citations2015Petar Aleksic, Mohammadreza Ghodsi +6 more
This paper utilizes an on-the-fly rescoring mechanism to adjust the LM weights of a small set of n-grams relevant to the particular context during speech decoding, which handles out of vocabulary words.
Fast and easy language understanding for dialog systems with Microsoft Language Understanding Intelligent Service (LUIS)
62 Citations2015J. D. Williams, Eslam Kamal +4 more
With Language Understanding Intelligent Service (LUIS), developers without machine learning expertise can quickly build and use language understanding models specific to their task, and easily maintain it as usage of their application grows.
Making the Case for Query-by-Voice with EchoQuery
40 Citations2016Gabriel Lyons, Vinh Cao Trần +3 more
This demonstration makes the case for querying database systems using a voice-based interface, a new querying and interaction paradigm the authors call Query-by-Voice (QbV), and demonstrates the practicality and utility of QbV for relational DBMSs using a using a proof-of-concept system called EchoQuery.
Kneser-Ney Smoothing on Expected Counts
23 Citations2014Hui Zhang, David Chiang
A generalization of Kneser-Ney smoothing that operates on fractional counts, or, more precisely, on distributions over counts, that improves performance significantly in language model adaptation and word alignment.
arXiv (Cornell University)Transfer Learning for Neural Semantic Parsing
12 Citations2017Xing Fan, Emilio Monti +2 more
Natural Language Processing with Small Feed-Forward Networks
11 Citations2017Jan A. Botha, Emily Pitler +6 more
It is shown that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models.