A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
arXiv (Cornell University)Published 22 June 2015Open access
Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell
Citations78
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.
Abstract
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.
Keywords
Computer Science
NatureLearning representations by back-propagating errors
30,885 Citations1986David E. Rumelhart, Geoffrey E. Hinton +1 more
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
8,612 Citations2011John C. Duchi, Elad Hazan +1 more
Recurrent neural network based language model
5,349 Citations2010Tomáš Mikolov, Martin Karafiát +3 more
Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.
A unified architecture for natural language processing
5,204 Citations2008Ronan Collobert, Jason Weston
This work describes a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense using a language model.
Moses
4,868 Citations2007Philipp Koehn, Richard Zens +12 more
An open-source toolkit for statistical machine translation whose novel contributions are support for linguistically motivated factors, confusion network decoding, and efficient data formats for translation models and language models.
METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments
3,723 Citations2005Satanjeev Banerjee, Alon Lavie
METEOR is described, an automatic metric for machine translation evaluation that is based on a generalized concept of unigram matching between the machineproduced translation and human-produced reference translations and can be easily extended to include more advanced matching strategies.
arXiv (Cornell University)Sequence to Sequence Learning with Neural Networks
3,526 Citations2014Ilya Sutskever, Oriol Vinyals +1 more
This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
Minimum error rate training in statistical machine translation
2,766 Citations2003Franz Josef Och
It is shown that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.
Text REtrieval ConferenceOkapi at TREC
2,229 Citations1994Stephen Robertson, Steve Walker +3 more
Much of the work involved investigating plausible methods of applying Okapi-style weighting to phrases, and expansion using terms from the top documents retrieved by a pilot search on topic terms was used.
Learning deep structured semantic models for web search using clickthrough data
2,044 Citations2013Po-Sen Huang, Xiaodong He +4 more
A series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them are developed.
Applied Physics Letters10.1162/153244303322533223
1,771 Citations2000
This work proposes to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences.
Improved backing-off for M-gram language modeling
1,490 Citations2002Reinhard Kneser, Hermann Ney
This paper proposes to use distributions which are especially optimized for the task of back-off, which are quite different from the probability distributions that are usually used for backing-off.
Edinburgh Research Explorer (University of Edinburgh)Noise-contrastive estimation: A new estimation principle for unnormalized statistical models
1,371 Citations2010Michael U. Gutmann, Aapo Hyvärinen
A new estimation principle is presented to perform nonlinear logistic regression to discriminate between the observed data and some artificially generated noise, using the model log-density function in the regression nonlinearity, which leads to a consistent (convergent) estimator of the parameters.
Recurrent Continuous Translation Models
1,345 Citations2013Nal Kalchbrenner, Phil Blunsom
A class of probabilistic continuous translation models called Recurrent Continuous Translation Models that are purely based on continuous representations for words, phrases and sentences and do not rely on alignments or phrasal translation units are introduced.
A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval
682 Citations2014Yelong Shen, Xiaodong He +3 more
A new latent semantic model that incorporates a convolutional-pooling structure over word sequences to learn low-dimensional, semantic vector representations for search queries and Web documents is proposed.
National Research Council Canada (Government of Canada)Data-Driven Response Generation in Social Media
576 Citations2011Alan Ritter, Colin Cherry +1 more
It is found that mapping conversational stimuli onto responses is more difficult than translating between languages, due to the wider range of possible responses, the larger fraction of unaligned words/phrases, and the presence of large phrase pairs whose alignment cannot be further decomposed.
Context dependent recurrent neural network language model
574 Citations2012Tomáš Mikolov, Geoffrey Zweig
This paper improves recurrent neural network language models performance by providing a contextual real-valued input vector in association with each word to convey contextual information about the sentence being modeled by performing Latent Dirichlet Allocation using a block of preceding text.
Computer Speech & LanguageThe Hidden Information State model: A practical framework for POMDP-based spoken dialogue management
491 Citations2009Steve Young, Milica Gašić +5 more
This paper explains how Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialogue systems and describes a form of approximation called the Hidden Information State model which does scale and which can be used to build practical systems.
Fast and Robust Neural Network Joint Models for Statistical Machine Translation
489 Citations2014Jacob Devlin, Rabih Zbib +4 more
A novel formulation for a neural network joint model (NNJM), which augments the NNLM with a source context window, which is purely lexicalized and can be integrated into any MT decoder.
Joint Language and Translation Modeling with Recurrent Neural Networks
259 Citations2013Michael Auli, Michel Galley +2 more
This work presents a joint language and translation model based on a recurrent neural network which predicts target words based on an unbounded history of both source and target words which shows competitive accuracy compared to the traditional channel model features.
Modeling Interestingness with Deep Neural Networks
175 Citations2014Jianfeng Gao, Patrick Pantel +3 more
The results on large-scale, real-world datasets show that the semantics of documents are important for modeling interest-ingness and that the DSSM leads to significant quality improvement on both tasks, outperforming not only the classic document models that do not use semantics but also state-of-the-art topic models.
Talking to machines (statistically speaking)
138 Citations2002Steve Young
This paper reviews spoken dialogue systems from a statistical modelling perspective and samples of existing work are reviewed, including dialogue control and optimisation, semantic interpretation, goal detection, natural language generation and synthesis.
User simulation for spoken dialogue systems: learning and evaluation
126 Citations2006Kallirroi Georgila, James Henderson +1 more
The expected accuracy, expected precision, and expected recall evaluation metrics are proposed as opposed to standard precision and recall used in prior work and discussed why they are more appropriate metrics for evaluating user simulation models compared to their standard counterparts.
Cambridge University Press eBooksNatural Language Generation in Interactive Systems
29 Citations2014Amanda Stent, Amanda Stent +13 more
This guide serves to introduce graduate students and new researchers to the field of natural language processing and artificial intelligence, while inspiring them with ideas for future research on natural language generation and interactive systems.
A trainable generator for recommendations in multimodal dialog
25 Citations2003Marilyn Walker, Rashmi Prasad +1 more
The use of boosting to train a sentence planner to generate recommendations for restaurants in MATCH, a multimodal dialogue system providing entertainment information for New York is described.