DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5...34
Hits 1 – 20 of 678

1
Emerging Dimension Weights in a Conceptual Spaces Model of Concept Combination ...
Lewis, Martha; Lawry, Jonathan. - : arXiv, 2016
BASE
Show details
2
Syntactic Structures and Code Parameters ...
Shu, Kevin; Marcolli, Matilde. - : arXiv, 2016
BASE
Show details
3
Part-of-Speech Tagging for Historical English ...
Yang, Yi; Eisenstein, Jacob. - : arXiv, 2016
BASE
Show details
4
Resolving Out-of-Vocabulary Words with Bilingual Embeddings in Machine Translation ...
BASE
Show details
5
Connecting Phrase based Statistical Machine Translation Adaptation ...
Wang, Rui; Zhao, Hai; Lu, Bao-Liang. - : arXiv, 2016
BASE
Show details
6
Dual Learning for Machine Translation ...
Xia, Yingce; He, Di; Qin, Tao. - : arXiv, 2016
BASE
Show details
7
BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings ...
Zhang, Biao; Xiong, Deyi; Su, Jinsong. - : arXiv, 2016
BASE
Show details
8
Vocabulary Manipulation for Neural Machine Translation ...
BASE
Show details
9
A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments ...
Abstract: While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to state-of-the-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account. ... : EACL 2017 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.1608.05426
https://arxiv.org/abs/1608.05426
BASE
Hide details
10
Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders ...
BASE
Show details
11
Automatic Construction of Discourse Corpora for Dialogue Translation ...
BASE
Show details
12
Scalable Machine Translation in Memory Constrained Environments ...
Baltescu, Paul. - : arXiv, 2016
BASE
Show details
13
Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing ...
BASE
Show details
14
Neural Name Translation Improves Neural Machine Translation ...
BASE
Show details
15
One Sentence One Model for Neural Machine Translation ...
BASE
Show details
16
Machine Learning Techniques with Ontology for Subjective Answer Evaluation ...
Devi, M. Syamala; Mittal, Himani. - : arXiv, 2016
BASE
Show details
17
Prepositional Attachment Disambiguation Using Bilingual Parsing and Alignments ...
BASE
Show details
18
Language classification from bilingual word embedding graphs ...
BASE
Show details
19
MetaDIG : Engaging Scientists in the Improvement of Metadata and Data ...
BASE
Show details
20
MetaDIG : Engaging Scientists in the Improvement of Metadata and Data ...
BASE
Show details

Page: 1 2 3 4 5...34

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
678
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern