[PDF][PDF] Deciphering foreign language
Deciphering Foreign Language Page 1 Proceedings of the 49th Annual Meeting of the
Association for Computational Linguistics, pages 12–21, Portland, Oregon, June 19-24, 2011 …
Association for Computational Linguistics, pages 12–21, Portland, Oregon, June 19-24, 2011 …
Great question! question quality in community q&a
Asking the right question in the right way is an art (and a science). In a community question-
answering setting, a good question is not just one that is found to be useful by other people …
answering setting, a good question is not just one that is found to be useful by other people …
Automatic intelligibility assessment of dysarthric speech using phonologically-structured sparse linear model
This paper presents a new method for automatically assessing the speech intelligibility of
patients with dysarthria, which is a motor speech disorder impeding the physical production …
patients with dysarthria, which is a motor speech disorder impeding the physical production …
[PDF][PDF] Semantic parsing with bayesian tree transducers
B Jones, M Johnson, S Goldwater - … of the 50th Annual Meeting of …, 2012 - aclanthology.org
Many semantic parsing models use tree transformations to map between natural language
and meaning representation. However, while tree transformations are central to several …
and meaning representation. However, while tree transformations are central to several …
Neural finite-state transducers: Beyond rational relations
We introduce neural finite state transducers (NFSTs), a family of string transduction models
defining joint and conditional probability distributions over pairs of strings. The probability of …
defining joint and conditional probability distributions over pairs of strings. The probability of …
[PDF][PDF] Bayesian inference for Zodiac and other homophonic ciphers
We introduce a novel Bayesian approach for deciphering complex substitution ciphers. Our
method uses a decipherment model which combines information from letter n-gram …
method uses a decipherment model which combines information from letter n-gram …
Semi-supervised URL segmentation with recurrent neural networks pre-trained on knowledge graph entities
Breaking domain names such as openresearch into component words open and research is
important for applications like Text-to-Speech synthesis and web search. We link this …
important for applications like Text-to-Speech synthesis and web search. We link this …
[PDF][PDF] Bayesian word alignment for statistical machine translation
C Mermer, M Saraçlar - Proceedings of the 49th Annual Meeting …, 2011 - aclanthology.org
In this work, we compare the translation performance of word alignments obtained via
Bayesian inference to those obtained via expectation-maximization (EM). We propose a …
Bayesian inference to those obtained via expectation-maximization (EM). We propose a …
Inferred joint multigram models for medical term normalization according to ICD
A Pérez, A Atutxa, A Casillas, K Gojenola… - International journal of …, 2018 - Elsevier
Abstract Background Electronic Health Records (EHRs) are written using spontaneous
natural language. Often, terms do not match standard terminology like the one available …
natural language. Often, terms do not match standard terminology like the one available …
Improving statistical machine translation using Bayesian word alignment and Gibbs sampling
C Mermer, M Saraçlar… - IEEE Transactions on …, 2013 - ieeexplore.ieee.org
We present a Bayesian approach to word alignment inference in IBM Models 1 and 2. In the
original approach, word translation probabilities (ie, model parameters) are estimated using …
original approach, word translation probabilities (ie, model parameters) are estimated using …