Learning Tractable Word Alignment Models with Complex Constraints
نویسندگان
چکیده
منابع مشابه
Learning Tractable Word Alignment Models with Complex Constraints
Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Probabilistic models for word alignment present a fundamental trade-off between richness of captured constraints and correlations versus efficiency and tractability of inference. In this article, we use the Posterior Regularization framework (Graça, Ganchev, and Taskar 2007) to incorporate complex cons...
متن کاملTractable Semi-supervised Learning of Complex Structured Prediction Models
• Multi-label Classification (e.g., a document belongs to more than one class finance, politics) • Sequence Learning (e.g, input: a sentence; output: POS Tags) The President Came to the office DT N V P DT N • In this paper, we consider general structures Characteristics: • Exponential number of output combinations for a given input (e.g., 2 in K output multi-label classification problem) • Labe...
متن کاملTowards Representation Learning with Tractable Probabilistic Models
Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be computed in polynomial time, can enable general schemes to extract features from b...
متن کاملOn Complex Word Alignment Configurations
Resources of manual word alignments contain configurations that are beyond the alignment capacity of current translation models, hence the term complex alignment configuration. They have been the matter of some debate in the machine translation community, as they call for more powerful translation models that come with further complications. In this work we investigate instances of complex alig...
متن کاملLearning Tractable Statistical Relational Models
Intractable inference has been a major barrier to the wide adoption of statistical relational models. Existing exact methods suffer from a lack of scalability, and approximate methods tend to be unreliable. Sumproduct networks (SPNs; Poon and Domingos 2011) are a recently-proposed probabilistic architecture that guarantees tractable exact inference, even on many high-treewidth models. SPNs are ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Linguistics
سال: 2010
ISSN: 0891-2017,1530-9312
DOI: 10.1162/coli_a_00007