Skip to search formSkip to main contentSkip to account menu
Practical Very Large Scale CRFs
TLDR
This paper addresses the issue of training very large CRFs, containing up to hundreds output labels and several billion features, and indicates that efficiency stems here from the sparsity induced by the use of a l penalty term.
View on ACL
Normalizing SMS: are Two Metaphors Better than One ?
TLDR
This paper presents an comparative study of systems aiming at normalizing the orthography of French SMS messages, one drawing inspiration from the Machine Translation task; the other using techniques that are commonly used in automatic speech recognition devices.
View on ACL
Text segmentation via topic modeling: an analytical study
TLDR
The use of latent Dirichlet allocation (LDA) topic model to segment a text into semantically coherent segments is investigated and yields significantly better performance than most of the available unsupervised methods on a benchmark dataset.
View on ACM
Inference and evaluation of the multinomial mixture model for text clustering
View PDF on arXiv
Structured Output Layer neural network language model
TLDR
A new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM, able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs.
View on IEEE
Structured Output Layer Neural Network Language Models for Speech Recognition
TLDR
A novel neural network language model (NNLM) which relies on word clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM is extended, able to handle arbitrarily-sized vocabularies, hence dispensing with the need for shortlists that are commonly used in NNLMs.
View on IEEE
Continuous Space Translation Models with Neural Networks
TLDR
Several continuous space translation models are explored, where translation probabilities are estimated using a continuous representation of translation units in lieu of standard discrete representations, jointly computed using a multi-layer neural network with a SOUL architecture.
View on ACL
Using Monolingual Data in Neural Machine Translation: a Systematic Study
TLDR
This paper conducts a systematic study of back-translation, comparing alternative uses of monolingual data, as well as multiple data generation procedures and introduces new data simulation techniques that are almost as effective, yet much cheaper to implement.
View on ACL
Variable-length sequence matching for phonetic transcription using joint multigrams
View via Publisher
Grapheme-to-Phoneme Conversion using Multiple Unbounded Overlapping Chunks
TLDR
An original extension of two data-driven algorithms for the transcription of a sequence of graphemes into the corresponding sequence of phonemes is presented, concluding that both approaches fail to offer a proper model of the analogical processes involved in reading aloud.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License