DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 22

1
Substructure Substitution: Structured Data Augmentation for NLP ...
BASE
Show details
2
On Generalization in Coreference Resolution ...
BASE
Show details
3
Exemplar-Controllable Paraphrasing and Translation using Bitext ...
BASE
Show details
4
Deep Clustering of Text Representations for Supervision-free Probing of Syntax ...
BASE
Show details
5
Mining Knowledge for Natural Language Inference from Wikipedia Categories ...
BASE
Show details
6
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity ...
BASE
Show details
7
Understanding stories via event sequence modeling
Peng, Haoruo. - 2018
BASE
Show details
8
Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext ...
BASE
Show details
9
A Study of All-Convolutional Encoders for Connectionist Temporal Classification ...
BASE
Show details
10
Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information ...
BASE
Show details
11
Efficient Segmental Cascades for Speech Recognition ...
Tang, Hao; Wang, Weiran; Gimpel, Kevin. - : arXiv, 2016
BASE
Show details
12
Discriminative Segmental Cascades for Feature-Rich Phone Recognition ...
Abstract: Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognition via both lattice rescoring and first-pass decoding. However, such models suffer from slow decoding, hampering the use of computationally expensive features, such as segment neural networks or other high-order features. A typical solution is to use approximate decoding, either by beam pruning in a single pass or by beam pruning to generate a lattice followed by a second pass. In this work, we study discriminative segmental models trained with a hinge loss (i.e., segmental structured SVMs). We show that beam search is not suitable for learning rescoring models in this approach, though it gives good approximate decoding performance when the model is already well-trained. Instead, we consider an approach inspired by structured prediction cascades, which use max-marginal pruning to generate lattices. We obtain a high-accuracy phonetic ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/1507.06073
https://dx.doi.org/10.48550/arxiv.1507.06073
BASE
Hide details
13
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2014
BASE
Show details
14
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2014
BASE
Show details
15
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters ...
Olutobi Owoputi; O'Connor, Brendan; Dyer, Chris. - : Carnegie Mellon University, 2013
BASE
Show details
16
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters ...
Olutobi Owoputi; O'Connor, Brendan; Dyer, Chris. - : Carnegie Mellon University, 2013
BASE
Show details
17
Concavity and Initialization for Unsupervised Dependency Parsing ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2012
BASE
Show details
18
Concavity and Initialization for Unsupervised Dependency Parsing ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2012
BASE
Show details
19
Generative Models of Monolingual and Bilingual Gappy Patterns ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2011
BASE
Show details
20
Generative Models of Monolingual and Bilingual Gappy Patterns ...
Gimpel, Kevin; Smith, Noah A.. - : Carnegie Mellon University, 2011
BASE
Show details

Page: 1 2

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
22
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern