Results 1 - 10
of
298
Learning bilingual word representations by marginalizing alignments
- In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL
, 2014
"... We present a probabilistic model that si-multaneously learns alignments and dis-tributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic con-text than prior work relying on hard align-ments. The advantage of this approach is demonstrated ..."
Abstract
-
Cited by 7 (0 self)
- Add to MetaCart
We present a probabilistic model that si-multaneously learns alignments and dis-tributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic con-text than prior work relying on hard align-ments. The advantage of this approach
An Autoencoder Approach to Learning Bilingual Word Representations
"... ∗ Both authors contributed equally Cross-language learning allows one to use training data from one language to build models for a different language. Many approaches to bilingual learning re-quire that we have word-level alignment of sentences from parallel corpora. In this work we explore the use ..."
Abstract
- Add to MetaCart
∗ Both authors contributed equally Cross-language learning allows one to use training data from one language to build models for a different language. Many approaches to bilingual learning re-quire that we have word-level alignment of sentences from parallel corpora. In this work we explore the use
2015. BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
- In Proceedings of the 32nd International Conference on Machine Learning, ICML
"... We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel train-ing data. Instead it trains direct ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel train-ing data. Instead it trains
Bilingual Word Representations with Monolingual Quality in Mind
"... Recent work in learning bilingual repre-sentations tend to tailor towards achiev-ing good performance on bilingual tasks, most often the crosslingual document clas-sification (CLDC) evaluation, but to the detriment of preserving clustering struc-tures of word representations monolin-gually. In this ..."
Abstract
- Add to MetaCart
Recent work in learning bilingual repre-sentations tend to tailor towards achiev-ing good performance on bilingual tasks, most often the crosslingual document clas-sification (CLDC) evaluation, but to the detriment of preserving clustering struc-tures of word representations monolin
HM-BiTAM: Bilingual topic exploration, word alignment, and translation
, 2008
"... We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via a hidden Markov Bilingual Topic AdMixture (HM-BiTAM). In this paradigm, parallel sentence-pairs from a parallel document ..."
Abstract
-
Cited by 15 (2 self)
- Add to MetaCart
document-pair are coupled via a certain semantic-flow, to ensure coherence of topical context in the alignment of mapping words between languages, likelihood-based training of topic-dependent translational lexicons, as well as in the inference of topic representations in each language. The learned HM
cdec: A decoder, alignment, and learning framework for finite-state and context-free translation models
- In Proceedings of ACL System Demonstrations
, 2010
"... We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation for translat ..."
Abstract
-
Cited by 134 (53 self)
- Add to MetaCart
We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation
From Bilingual Dictionaries to Interlingual Document Representations
"... Mapping documents into an interlingual representation can help bridge the language barrier of a cross-lingual corpus. Previous approaches use aligned documents as training data to learn an interlingual representation, making them sensitive to the domain of the training data. In this paper, we learn ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
an interlingual representation in an unsupervised manner using only a bilingual dictionary. We first use the bilingual dictionary to find candidate document alignments and then use them to find an interlingual representation. Since the candidate alignments are noisy, we develop a robust learning algorithm
Learning tractable word alignment models with complex constraints
- Computational Linguistics
, 2010
"... Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Proba ..."
Abstract
-
Cited by 11 (6 self)
- Add to MetaCart
Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Proba
Free viewpoint action recognition using motion history volumes. CVIU
, 2006
"... Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematogra-phy and understanding of social interaction. Yet, most current work in gesture or action interpretation remains rooted in view-dependent r ..."
Abstract
-
Cited by 170 (2 self)
- Add to MetaCart
in a variety of viewpoints. Alignment and comparisons are performed eciently using Fourier transforms in cylindrical co-ordinates around the vertical axis. Results indicate that this representation can be used to learn and recognize basic human action classes, independently of gender, body size
Multilingual distributed representations without word alignment. ICLR
, 2014
"... Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not available in discrete representations, distributed representati ..."
Abstract
-
Cited by 11 (1 self)
- Add to MetaCart
-level representations across languages. We combine these two approaches by proposing a method for learning distributed representations in a multilingual setup. Our model learns to assign similar embed-dings to aligned sentences and dissimilar ones to sentence which are not aligned while not requiring word alignments
Results 1 - 10
of
298