| 1. |
- Adesam, Yvonne, 1975-
(författare)
-
The Multilingual Forest : Investigating High-quality Parallel Corpus Development
- 2012
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis explores the development of parallel treebanks, collections of language data consisting of texts and their translations, with syntactic annotation and alignment, linking words, phrases, and sentences to show translation equivalence. We describe the semi-manual annotation of the SMULTRON parallel treebank, consisting of 1,000 sentences in English, German and Swedish. This description is the starting point for answering the first of two questions in this thesis.What issues need to be considered to achieve a high-quality, consistent,parallel treebank?The units of annotation and the choice of annotation schemes are crucial for quality, and some automated processing is necessary to increase the size. Automatic quality checks and evaluation are essential, but manual quality control is still needed to achieve high quality.Additionally, we explore improving the automatically created annotation for one language, using information available from the annotation of the other languages. This leads us to the second of the two questions in this thesis.Can we improve automatic annotation by projecting information available in the other languages?Experiments with automatic alignment, which is projected from two language pairs, L1–L2 and L1–L3, onto the third pair, L2–L3, show an improvement in precision, in particular if the projected alignment is intersected with the system alignment. We also construct a test collection for experiments on annotation projection to resolve prepositional phrase attachment ambiguities. While majority vote projection improves the annotation, compared to the basic automatic annotation, using linguistic clues to correct the annotation before majority vote projection is even better, although more laborious. However, some structural errors cannot be corrected by projection at all, as different languages have different wording, and thus different structures.
|
|
| 2. |
- Ballesteros, Miguel, et al.
(författare)
-
Going to the Roots of Dependency Parsing
- 2013
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - : MIT Press. - 0891-2017 .- 1530-9312. ; 39:1, s. 5-13
-
Tidskriftsartikel (refereegranskat)abstract
- Dependency trees used in syntactic parsing often include a root node representing a dummy word prefixed or suffixed to the sentence, a device that is generally considered a mere technical convenience and is tacitly assumed to have no impact on empirical results. We demonstrate that this assumption is false and that the accuracy of data-driven dependency parsers can in fact be sensitive to the existence and placement of the dummy root node. In particular, we show that a greedy, left-to-right, arc-eager transition-based parser consistently performs worse when the dummy root node is placed at the beginning of the sentence (following the current convention in data-driven dependency parsing) than when it is placed at the end or omitted completely. Control experiments with an arc-standard transition-based parser and an arc-factored graph-based parser reveal no consistent preferences but nevertheless exhibit considerable variation in results depending on root placement. We conclude that the treatment of dummy root nodes in data-driven dependency parsing is an underestimated source of variation in experiments and may also be a parameter worth tuning for some parsers.
|
|
| 3. |
|
|
| 4. |
- Bengoetxea, Kepa, et al.
(författare)
-
On WordNet Semantic Classes and Dependency Parsing
- 2014
-
Ingår i: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). ; , s. 649-655
-
Konferensbidrag (refereegranskat)
|
|
| 5. |
|
|
| 6. |
- Bunt, Harry, et al.
(författare)
-
Grammars, Parsers and Recognizers
- 2014
-
Ingår i: Journal of Logic and Computation. - : Oxford Journals. ; 24:2, s. 309-
-
Tidskriftsartikel (refereegranskat)
|
|
| 7. |
- de Marneffe, Marie-Catherine, et al.
(författare)
-
Universal Stanford Dependencies : A Cross-Linguistic Typology
- 2014
-
Ingår i: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC). - 9782951740884 ; , s. 4585-4592
-
Konferensbidrag (refereegranskat)abstract
- Revisiting the now de facto standard Stanford dependency representation, we propose an improved taxonomy to capture grammatical relations across languages, including morphologically rich ones. We suggest a two-layered taxonomy: a set of broadly attested universal grammatical relations, to which language-specific relations can be added. We emphasize the lexicalist stance of the Stanford Dependencies, which leads to a particular, partially new treatment of compounding, prepositions, and morphology. We show how existing dependency schemes for several languages map onto the universal taxonomy proposed here and close with consideration of practical implications of dependency representation choices for NLP applications, in particular parsing.
|
|
| 8. |
- Dubremetz, Marie, 1988-, et al.
(författare)
-
Extraction of Nominal Multiword Expressions in French
- 2014
-
Ingår i: Proceedings of the 10th Workshop on Multiword Expressions (MWE). - Gothenburg, Sweden : Association for Computational Linguistics. ; , s. 72-76
-
Konferensbidrag (refereegranskat)
|
|
| 9. |
|
|
| 10. |
- Gomez-Rodriguez, Carlos, et al.
(författare)
-
Divisible Transition Systems and Multiplanar Dependency Parsing
- 2013
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - 0891-2017 .- 1530-9312. ; 39:4, s. 799-845
-
Tidskriftsartikel (refereegranskat)abstract
- Transition-based parsing is a widely used approach for dependency parsing that combines high efficiency with expressive feature models. Many different transition systems have been proposed, often formalized in slightly different frameworks. In this article, we show that a large number of the known systems for projective dependency parsing can be viewed as variants of the same stack-based system with a small set of elementary transitions that can be composed into complex transitions and restricted in different ways. We call these systems divisible transition systems and prove a number of theoretical results about their expressivity and complexity. In particular, we characterize an important subclass called efficient divisible transition systems that parse planar dependency graphs in linear time. We go on to show, first, how this system can be restricted to capture exactly the set of planar dependency trees and, secondly, how the system can be generalized to k-planar trees by making use of multiple stacks. Using the first known efficient test for k-planarity, we investigate the coverage of k-planar trees in available dependency treebanks and find a very good fit for 2-planar trees. We end with an experimental evaluation showing that our 2-planar parser gives significant improvements in parsing accuracy over the corresponding 1-planar and projective parsers for data sets with non-projective dependency trees and performs on a par with the widely used arc-eager pseudo-projective parser.
|
|
| 11. |
- Hardmeier, Christian, et al.
(författare)
-
Anaphora Models and Reordering for Phrase-Based SMT
- 2014
-
Ingår i: Proceedings of the Ninth Workshop on Statistical Machine Translation. - : Association for Computational Linguistics. - 9781941643174 ; , s. 122-129
-
Konferensbidrag (refereegranskat)abstract
- We describe the Uppsala University systems for WMT14. We look at the integration of a model for translating pronominal anaphora and a syntactic dependency projection model for English–French. Furthermore, we investigate post-ordering and tunable POS distortion models for English–German.
|
|
| 12. |
- Hardmeier, Christian
(författare)
-
Discourse in Statistical Machine Translation
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis addresses the technical and linguistic aspects of discourse-level processing in phrase-based statistical machine translation (SMT). Connected texts can have complex text-level linguistic dependencies across sentences that must be preserved in translation. However, the models and algorithms of SMT are pervaded by locality assumptions. In a standard SMT setup, no model has more complex dependencies than an n-gram model. The popular stack decoding algorithm exploits this fact to implement efficient search with a dynamic programming technique. This is a serious technical obstacle to discourse-level modelling in SMT.From a technical viewpoint, the main contribution of our work is the development of a document-level decoder based on stochastic local search that translates a complete document as a single unit. The decoder starts with an initial translation of the document, created randomly or by running a stack decoder, and refines it with a sequence of elementary operations. After each step, the current translation is scored by a set of feature models with access to the full document context and its translation. We demonstrate the viability of this decoding approach for different document-level models.From a linguistic viewpoint, we focus on the problem of translating pronominal anaphora. After investigating the properties and challenges of the pronoun translation task both theoretically and by studying corpus data, a neural network model for cross-lingual pronoun prediction is presented. This network jointly performs anaphora resolution and pronoun prediction and is trained on bilingual corpus data only, with no need for manual coreference annotations. The network is then integrated as a feature model in the document-level SMT decoder and tested in an English–French SMT system. We show that the pronoun prediction network model more adequately represents discourse-level dependencies for less frequent pronouns than a simpler maximum entropy baseline with separate coreference resolution.By creating a framework for experimenting with discourse-level features in SMT, this work contributes to a long-term perspective that strives for more thorough modelling of complex linguistic phenomena in translation. Our results on pronoun translation shed new light on a challenging, but essential problem in machine translation that is as yet unsolved.
|
|
| 13. |
- Hardmeier, Christian, et al.
(författare)
-
Docent : A Document-Level Decoder for Phrase-Based Statistical Machine Translation
- 2013
-
Ingår i: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. - : Association for Computational Linguistics. ; , s. 193-198
-
Konferensbidrag (refereegranskat)abstract
- We describe Docent, an open-source decoder for statistical machine translation that breaks with the usual sentence-by-sentence paradigm and translates complete documents as units. By taking translation to the document level, our decoder can handle feature models with arbitrary discourse-wide dependencies and constitutes an essential infrastructure component in the quest for discourse-aware SMT models.
|
|
| 14. |
- Hardmeier, Christian, et al.
(författare)
-
Document-Wide Decoding for Phrase-Based Statistical Machine Translation
- 2012
-
Ingår i: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. - : Association for Computational Linguistics. ; , s. 1179-1190
-
Konferensbidrag (refereegranskat)abstract
- Independence between sentences is an assumption deeply entrenched in the models and algorithms used for statistical machine translation (SMT), particularly in the popular dynamic programming beam search decoding algorithm. This restriction is an obstacle to research on more sophisticated discourse-level models for SMT. We propose a stochastic local search decoding method for phrase-based SMT, which permits free document-wide dependencies in the models. We explore the stability and the search parameters of this method and demonstrate that it can be successfully used to optimise a document-level semantic language model.
|
|
| 15. |
- Hardmeier, Christian, et al.
(författare)
-
Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction
- 2013
-
Ingår i: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. - : Association for Computational Linguistics. ; , s. 380-391
-
Konferensbidrag (refereegranskat)abstract
- This paper addresses the task of predicting the correct French translations of third-person subject pronouns in English discourse, a problem that is relevant as a prerequisite for machine translation and that requires anaphora resolution. We present an approach based on neural networks that models anaphoric links as latent variables and show that its performance is competitive with that of a system with separate anaphora resolution while not requiring any coreference-annotated training data. This demonstrates that the information contained in parallel bitexts can successfully be used to acquire knowledge about pronominal anaphora in an unsupervised way.
|
|
| 16. |
- Hardmeier, Christian, et al.
(författare)
-
Translating Pronouns with Latent Anaphora Resolution
- 2014
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- We discuss the translation of anaphoric pronouns in statistical machine translation from English into French. Pronoun translation requires resolving the antecedents of the pronouns in the input, a classic discourse processing problem that is usually approached through supervised learning from manually annotated data. We cast cross-lingual pronoun prediction as a classification task and present a neural network architecture that incorporates the links between anaphors and potential antecedents as latent variables, allowing us to train the classifier on parallel text without explicit supervision for the anaphora resolver. We demonstrate that our approach works just as well for classification as using an external coreference resolver whereas its impact in a practical translation experiment is more limited.
|
|
| 17. |
- Hardmeier, Christian, et al.
(författare)
-
Tree Kernels for Machine Translation Quality Estimation
- 2012
-
Ingår i: Proceedings of the 7th Workshop on Statistical Machine Translation. - : Association for Computational Linguistics. - 9781937284206 - 1937284204 ; , s. 109-113
-
Konferensbidrag (refereegranskat)abstract
- This paper describes Uppsala University’s submissions to the Quality Estimation (QE) shared task at WMT 2012. We present a QE system based on Support Vector Machine regression, using a number of explicitly defined features extracted from the Machine Translation input, output and models in combination with tree kernels over constituency and dependency parse trees for the input and output sentences. We confirm earlier results suggesting that tree kernels can be a useful tool for QE system construction especially in the early stages of system design.
|
|
| 18. |
|
|
| 19. |
- Kuhlmann, Marco, 1977-, et al.
(författare)
-
Transition-Based Techniques for Non-Projective Dependency Parsing
- 2010
-
Ingår i: Northern European Journal of Language Technology (NEJLT). - Linköping, Sweden : Linkoping University Electronic Press. - 2000-1533. ; 2:1, s. 1-19
-
Tidskriftsartikel (refereegranskat)abstract
- We present an empirical evaluation of three methods for the treatment of non-projective structures in transition-based dependency parsing: pseudo-projective parsing, non-adjacent arc transitions, and online reordering. We compare both the theoretical coverage and the empirical performance of these methods using data from Czech, English and German. The results show that although online reordering is the only method with complete theoretical coverage, all three techniques exhibit high precision but somewhat lower recall on non-projective dependencies and can all improve overall parsing accuracy provided that non-projective dependencies are frequent enough. We also find that the use of non-adjacent arc transitions may lead to a drop in accuracy on projective dependencies in the presence of long-distance non-projective dependencies, an effect that is not found for the two other techniques.
|
|
| 20. |
- McDonald, Ryan, et al.
(författare)
-
Analyzing and Integrating Dependency Parsers
- 2011
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - 0891-2017 .- 1530-9312. ; 37:1, s. 197-230
-
Tidskriftsartikel (refereegranskat)abstract
- There has been a rapid increase in the volume of research on data-driven dependency parsers in the past five years. This increase has been driven by the availability of treebanks in a wide variety of languages-due in large part to the CoNLL shared tasks-as well as the straightforward mechanisms by which dependency theories of syntax can encode complex phenomena in free word order languages. In this article, our aim is to take a step back and analyze the progress that has been made through an analysis of the two predominant paradigms for data-driven dependency parsing, which are often called graph-based and transition-based dependency parsing. Our analysis covers both theoretical and empirical aspects and sheds light on the kinds of errors each type of parser makes and how they relate to theoretical expectations. Using these observations, we present an integrated system based on a stacking learning framework and show that such a system can learn to overcome the shortcomings of each non-integrated system.
|
|
| 21. |
- McDonald, Ryan, et al.
(författare)
-
Analyzing and Integrating Dependency Parsers
- 2011
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - 0891-2017 .- 1530-9312. ; 37:1, s. 197-230
-
Tidskriftsartikel (refereegranskat)
|
|
| 22. |
- Megyesi, Beáta, 1971-, et al.
(författare)
-
The English-Swedish-Turkish Parallel Treebank
- 2010
-
Ingår i: Proceedings of Language Resources and Evaluation (LREC 2010).
-
Konferensbidrag (refereegranskat)abstract
- We describe a syntactically annotated parallel corpus containing typologically partly different languages, namely English, Swedish and Turkish. The corpus consists of approximately 300 000 tokens in Swedish, 160 000 in Turkish and 150 000 in English, containing both fiction and technical documents. We build the corpus by using the Uplug toolkit for automatic structural markup, such as tokenization and sentence segmentation, as well as sentence and word alignment. In addition, we use basic language resource kits for the linguistic analysis of the languages involved. The annotation is carried on various layers from morphological and part of speech analysis to dependency structures. The tools used for linguistic annotation, e.g. HunPos tagger and MaltParser, are freely available data-driven resources, trained on existing corpora and treebanks for each language. The parallel treebank is used in teaching and linguistic research to study the relationship between the structurally different languages. In order to study the treebank, several tools have been developed for the visualization of the annotation and alignment, allowing search for linguistic patterns.
|
|
| 23. |
- Nilsson, Mattias, et al.
(författare)
-
A Survival Analysis of Fixation Times in Reading
- 2011
-
Ingår i: Proceedings of the 2nd Workshop on Cognitive Modeling and Computational Linguistics (ACL 2011). - : Association for Computational Linguistics. ; , s. 107-115
-
Konferensbidrag (refereegranskat)
|
|
| 24. |
- Nilsson, Mattias
(författare)
-
Computational Models of Eye Movements in Reading : A Data-Driven Approach to the Eye-Mind Link
- 2012
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis investigates new methods for understanding eye movement behavior in reading based on the use of eye tracking corpora and data-driven modeling. Eye movement behavior is characterized by two basic, generally unconscious, decisions: where and when to move the eyes. We explore the idea that empirical eye movement data carries rich information about the processes that guide these decisions. Two methods are investigated, each addressing a different aspect of eye movements in reading. The role of prediction in eye movement modeling is emphasized, and new evaluation methods for assessing the predictive accuracy of models are proposed. The decision of where to move the eyes is approached using standard machine learning methods. The model proposed learns where to move the eyes under different conditions associated with the words being read. Applied to new text, the model moves the eyes in ways it has learnt, showing characteristics similar to human readers. Furthermore, we propose the use of entropy to measure the similarity between observed and predicted eye movement behavior on held-out data. The main contribution is a flexible model, with few fixed parameters, that can be used to investigate decisions about where the eyes move during reading. The decision of when to move the eyes is approached using time-to-event modeling (survival analysis). The model proposed learns the timing of eye movements under different conditions associated with the words being read. Applied to new text, the model estimates the probability that a fixation survives for any given length of time. We propose an entropy-related measure to assess the probabilistic temporal predictions of the model. The main contribution is the use of Cox hazards modeling to address questions about the strength, as well as the timing, of processes that influence the decision of when to move the eyes during reading.
|
|
| 25. |
|
|
| 26. |
- Nilsson, Mattias, et al.
(författare)
-
Proportional Hazards Modeling of Saccadic Response Times During Reading
- 2013
-
Ingår i: Topics in Cognitive Science. - : John Wiley & Sons. - 1756-8757 .- 1756-8765. ; 5:3, s. 541-563
-
Tidskriftsartikel (refereegranskat)abstract
- In this article we use proportional hazards models to examine how low-level processes affect the probability of making a saccade over time, through the period of fixation, during reading. We apply the Cox proportional hazards model to investigate how launch distance (relative to word beginning), fixation location (relative to word center), and word frequency affect the hazard of a saccadic response. This model requires that covariates have a constant impact on the hazard over time, the assumption of proportional hazards. We show that this assumption is not supported. The impact of the covariates changes with the time passed since fixation onset. To account for the non-proportional hazards we fit step functions of time, resulting in a model with time-varying effects on the hazard. We evaluate the ability to predict the timing of saccades on held-out fixation data. The model with time-varying effects performs better in predicting the timing of saccades for fixations as short as 100 ms and as long as 500 ms, when compared both to a baseline model without covariates and a model which assumes constant covariate effects. This result suggests that the time-varying effects model better recovers the time course of low-level processes that influence the decision to move the eyes.
|
|
| 27. |
|
|
| 28. |
|
|
| 29. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
A Transition-Based Parser for 2-Planar Dependency Structures
- 2010
-
Ingår i: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. - : Association for Computational Linguistics. - 9781932432664 ; , s. 1492-1501
-
Konferensbidrag (refereegranskat)
|
|
| 30. |
|
|
| 31. |
|
|
| 32. |
- Nivre, Joakim, et al.
(författare)
-
Arc-Eager Parsing with the Tree Constraint
- 2014
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - 0891-2017 .- 1530-9312. ; 40:2, s. 259-267
-
Tidskriftsartikel (refereegranskat)abstract
- The arc-eager system for transition-based dependency parsing is widely used in natural language processing despite the fact that it does not guarantee that the output is a well-formed dependency tree. We propose a simple modification to the original system that enforces the tree constraint without requiring any modification to the parser training procedure. Experiments on multiple languages show that the method on average achieves 72% of the error reduction possible and consistently outperforms the standard heuristic in current use.
|
|
| 33. |
- Nivre, Joakim, 1962-
(författare)
-
Bare-Bones Dependency Parsing
- 2012
-
Ingår i: Security and Intelligent Information Systems. - : Springer Berlin/Heidelberg. - 9783642252600 ; , s. 20-32
-
Konferensbidrag (refereegranskat)abstract
- If all we want from a syntactic parser is a dependency tree, what do we gain by first computing a different representation such as a phrase structure tree? The principle of parsimony suggests that a simpler model should be preferred over a more complex model, all other things being equal, and the simplest model is arguably one that maps a sentence directly to a dependency tree a bare-bones dependency parser. In this paper, I characterize the parsing problem faced by such a system, survey the major parsing techniques currently in use, and begin to examine whether the simpler model can in fact rival the performance of more complex systems. Although the empirical evidence is still limited, I conclude that bare-bones dependency parsers can achieve state-of-the-art parsing accuracy and often excel in terms of efficiency.
|
|
| 34. |
|
|
| 35. |
|
|
| 36. |
|
|
| 37. |
|
|
| 38. |
- Nivre, Joakim, et al.
(författare)
-
Constrained Arc-Eager Dependency Parsing
- 2014
-
Ingår i: Computational linguistics - Association for Computational Linguistics (Print). - 0891-2017 .- 1530-9312. ; 40:2, s. 249-257
-
Tidskriftsartikel (refereegranskat)abstract
- Arc-eager dependency parsers process sentences in a single left-to-right pass over the input and have linear time complexity with greedy decoding or beam search. We show how such parsers can be constrained to respect two different types of conditions on the output dependency graph: span constraints, which require certain spans to correspond to subtrees of the graph, and arc constraints, which require certain arcs to be present in the graph. The constraints are incorporated into the arc-eager transition system as a set of preconditions for each transition and preserve the linear time complexity of the parser.
|
|
| 39. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
Cross-Framework Evaluation for Statistical Parsing
- 2012
-
Ingår i: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL). - : Association for Computational Linguistics. - 9781937284190
-
Konferensbidrag (refereegranskat)
|
|
| 40. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
Current Trends in Parsing Technology
- 2010
-
Ingår i: Trends in Parsing Technology. - Dordrecht : Springer. - 9789048193516 ; , s. 1-17
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)
|
|
| 41. |
- Nivre, Joakim, 1962-
(författare)
-
Dependency Parsing
- 2010
-
Ingår i: Language and Linguistics Compass. - Oxford : Blackwell. - 1749-818X. ; 4:3, s. 138-152
-
Tidskriftsartikel (refereegranskat)
|
|
| 42. |
|
|
| 43. |
|
|
| 44. |
|
|
| 45. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
Improving Dependency Parsing with Semantic Classes
- 2011
-
Ingår i: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. - : Association for Computational Linguistics. ; , s. 699-703
-
Konferensbidrag (refereegranskat)
|
|
| 46. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
Joint Evaluation of Morphological Segmentation and Syntactic Parsing
- 2012
-
Ingår i: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). - : Association for Computational Linguistics. - 9781937284251 ; , s. 6-10
-
Konferensbidrag (refereegranskat)
|
|
| 47. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
MaltOptimizer: A System for MaltParser Optimization.
- 2012
-
Ingår i: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC). - : European Language Resources Association. - 9782951740877
-
Konferensbidrag (refereegranskat)
|
|
| 48. |
- Nivre, Joakim, 1962-, et al.
(författare)
-
MaltOptimizer: An Optimization Tool for MaltParser
- 2012
-
Ingår i: Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL). - : Association for Computational Linguistics. - 9781937284190 ; , s. 58-62
-
Konferensbidrag (refereegranskat)
|
|
| 49. |
|
|
| 50. |
|
|
