[PDF][PDF] Findings of the 2011 workshop on statistical machine translation
This paper presents the results of the WMT11 shared tasks, which included a translation
task, a system combination task, and a task for machine translation evaluation metrics. We …
task, a system combination task, and a task for machine translation evaluation metrics. We …
Exploiting semantics in neural machine translation with graph convolutional networks
Semantic representations have long been argued as potentially useful for enforcing
meaning preservation and improving generalization performance of machine translation …
meaning preservation and improving generalization performance of machine translation …
Neural semantic role labeling with dependency path embeddings
This paper introduces a novel model for semantic role labeling that makes use of neural
sequence modeling techniques. Our approach is motivated by the observation that complex …
sequence modeling techniques. Our approach is motivated by the observation that complex …
Syntax-aware semantic role labeling without parsing
R Cai, M Lapata - Transactions of the Association for Computational …, 2019 - direct.mit.edu
In this paper we focus on learning dependency aware representations for semantic role
labeling without recourse to an external parser. The backbone of our model is an LSTM …
labeling without recourse to an external parser. The backbone of our model is an LSTM …
Semi-supervised semantic role labeling with cross-view training
R Cai, M Lapata - Proceedings of the 2019 Conference on …, 2019 - aclanthology.org
The successful application of neural networks to a variety of NLP tasks has provided strong
impetus to develop end-to-end models for semantic role labeling which forego the need for …
impetus to develop end-to-end models for semantic role labeling which forego the need for …
[PDF][PDF] Modeling the translation of predicate-argument structure for smt
Predicate-argument structure contains rich semantic information of which statistical machine
translation hasn't taken full advantage. In this paper, we propose two discriminative, feature …
translation hasn't taken full advantage. In this paper, we propose two discriminative, feature …
Syntax aware LSTM model for semantic role labeling
Abstract In Semantic Role Labeling (SRL) task, the tree structured dependency relation is
rich in syntax information, but it is not well handled by existing models. In this paper, we …
rich in syntax information, but it is not well handled by existing models. In this paper, we …
Semantic role labeling for Amharic text using multiple embeddings and deep neural network
Amharic is morphologically complex and under-resourced language, posing difficulties in
the development of natural language processing applications. This paper presents the …
the development of natural language processing applications. This paper presents the …
Short Sequence Chinese‐English Machine Translation Based on Generative Adversarial Networks of Emotion
H Wang - Computational intelligence and neuroscience, 2022 - Wiley Online Library
With the steady growth of the global economy, the communication between countries in the
world has become increasingly close. Due to its translation efficiency and other problems …
world has become increasingly close. Due to its translation efficiency and other problems …
Alignment-free cross-lingual semantic role labeling
R Cai, M Lapata - Proceedings of the 2020 Conference on …, 2020 - aclanthology.org
Cross-lingual semantic role labeling (SRL) aims at leveraging resources in a source
language to minimize the effort required to construct annotations or models for a new target …
language to minimize the effort required to construct annotations or models for a new target …