26,026 research outputs found
Modelling Pronominal Anaphora in Statistical Machine Translation
Current Statistical Machine Translation (SMT) systems translate texts sentence by sentence without considering any cross-sentential context. Assuming independence between sentences makes it difficult to take certain translation decisions when the necessary information cannot be determined locally. We argue for the necessity to include cross-sentence dependencies in SMT. As a case in point, we study the problem of pronominal anaphora translation by manually evaluating German-English SMT output. We then present a word dependency model for SMT, which can represent links between word pairs in the same or in different sentences. We use this model to integrate the output of a coreference resol- ution system into English-German SMT with a view to improving the translation of anaphoric pronouns
Predicting Pronouns with a Convolutional Network and an N-gram Model
This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model
Using Linguistic Annotations in Statistical Machine Translation of Film Subtitles
Statistical Machine Translation (SMT) has been successfully employed to support translation of film subtitles. We explore the integration of Constraint Grammar corpus annotations into a Swedish-Danish subtitle SMT system in the framework of factored SMT. While the usefulness of the annotations is limited with large amounts of parallel data, we show that linguistic annotations can increase the gains in translation quality when monolingual data in the target language is added to an SMT system based on a small parallel corpus
Pronoun Prediction with Latent Anaphora Resolution
This paper describes the UU-Hardmeier submissions to the WMT 2016 shared task on cross-lingual pronoun prediction. Our model is a system combination of two different approaches, one based on a neural network with latent anaphora resolution and the other one on an n-gram model with an additional dependency on the source pronoun. The combination of the two models results in an improvement over each individual system, but it appears that the contribution of the neural network is more likely due to its context modelling capacities than to the anaphora resolution subnetwork
FBK at WMT 2010 : Word Lattices for Morphological Reduction and Chunk-Based Reordering
FBK participated in the WMT 2010 Machine Translation shared task with phrase-based Statistical Machine Translation systems based on the Moses decoder for English-German and German-English translation. Our work concentrates on exploiting the available language modelling resources by using linear mixtures of large 6-gram language models and on addressing linguistic differences between English and German with methods based on word lattices. In particular, we use lattices to integrate a morphological analyser for German into our system, and we present some initial work on rule-based word reordering
Towards a Christian Philosophy
Author did not sign the LAC Non-Exclusive License form.The relationship between philosophy and Christianity has, of course, a long history, as do the discussions of that relationship. My own position is not dissimilar to that of many of the early Church Fathers, though of course that position must be elaborated differently for various historical and personal reasons, and hopefully enriched by attention to the history of Western philosophy. As with all such relations, one's understanding of this relation has a lot to do with one's understanding of the terms involved. To promote the possibility of "Christian philosophy" is also to comment on that "and" which might be understood to relate two otherwise distinct and irreconcilable terms. In the end I claim this "and" must be understood as that "love" which defines philosophy as the "love of wisdom" (and finally, the wisdom of love), and does so in terms which (almost) merge-with the surprising assistance of such thinkers as Martin Heidegger, Jacques Derrida, and Paul Ricoeur-with those of the Church Fathers cited. On the one hand, I intend nothing but the historical, orthodox, and catholic understanding of Christianity, especially with regard to the central figure of Jesus the Christ, the Trinitarian God whom He embodies, represents, and reveals, and the Scriptures given as The Bible. On the other hand, I present the specifically philosophical pertinence of this unique Person as such emerges from the texts of the "philosophers" considered, and in a manner which I claim does not force the issue by reading into their texts what is not there. Attending to a (Christian) philosophical reflection on (Christian) philosophy also offers elaborations of inherited doctrines, both Christian and philosophical, including a way to read and think unique to the outcome. Such is the adventure of this current work
The Christian Right and US Foreign Policy in the Twenty-first Century
The thesis discusses the role of the Christian Right in the US foreign policy decision making process. The research revealed that the Christian Right has long been fascinated with some international issues in general and US foreign policy in particular. The Christian Right’s interest in international issues increased markedly during years of the George W. Bush presidency. It successfully widened its activities from domestic social conservative issues to foreign policy issues by participating in, articulating and lobbying for its religious version of American foreign policy. In assessing the role of the Christian Right in US foreign policy making, this dissertation examines three aspects of US foreign policy, namely Israel, international religious freedom and global humanitarianism. Based on these aspects, the Christian Right is seen as skilled in framing and defining issues. The Christian Right seems effective in selecting and prioritizing international issues that have a reasonable chance of being selected by foreign policy decision makers, especially in Congress. Moreover, the Christian Right has shown its maturity in seeking engagement and cooperation with other organizations, secular and religious, in order to advance its international goals. Finally, in pursuing and conveying its international agenda, the Christian Right has adopted a more moderate and less overtly religious approach. Instead of using its traditional religious rhetoric, the Christian Right has successfully projected its foreign policy preferences into the conventional realist discourse of American foreign policy that is largely based on the objective of national interest and national security. Nevertheless, this study does not, in any way, conclude that the Christian Right was able to influence or determine the direction of US foreign policy and its outcomes; however, it does suggest that the Christian Right did contribute and have an impact on the formulation of some US foreign policy. As such, the research contends that the role of the Christian Right is similar to other interest group lobbies and that its perceived influence on US foreign policy should not be exaggerated. Finally, the research suggests that the emergence of the Christian Right as an actor in asserting its global agenda through US foreign policy can possibly provide an example of how religious beliefs and values can become a potential source of “soft power”. Together with the “climate of opinion” of the American public during the Bush administration, the “soft power” at domestic level could serve as a valuable new explanatory variable in understanding how the US foreign policy was formulated in the early 21st century
Sabbath, Psalms and Eucharist: Christopher Southgate considers Christian perspectives on the climate emergency
This is the author accepted manuscript. The final version is available from Green Christian via the URL in this record In this brief article I want to explore what resources Christian thought might offer the
climate emergency, and those challenged by the slowness with which the generation
with the power (my own) are addressing the huge challenges that are ever more
evidently unfolding on our planet
Parallel Data Helps Neural Entity Coreference Resolution
Coreference resolution is the task of finding expressions that refer to the same entity in a text. Coreference models are generally trained on monolingual annotated data but annotating coreference is expensive and challenging. Hardmeier et al. (2013) have shown that parallel data contains latent anaphoric knowledge, but it has not been explored in end-to-end neural models yet. In this paper, we propose a simple yet effective model to exploit coreference knowledge from parallel data. In addition to the conventional modules learning coreference from annotations, we introduce an unsupervised module to capture cross-lingual coreference knowledge. Our proposed cross-lingual model achieves consistent improvements, up to 1.74 percentage points, on the OntoNotes 5.0 English dataset using 9 different synthetic parallel datasets. These experimental results confirm that parallel data can provide additional coreference knowledge which is beneficial to coreference resolution tasks
The Uppsala-FBK systems at WMT 2011
This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical lexical reordering, data selection for language modelling, linear transduction grammars for word alignment and syntax-based decoding with monolingual dependency information
- …
