| 1. |
- Kucher, Kostiantyn, Dr. 1989-, et al.
(author)
-
An Interdisciplinary Perspective on Evaluation and Experimental Design for Visual Text Analytics : Position Paper
- 2022
-
In: Proceedings of the 2022 IEEE Workshop on Evaluation and Beyond — Methodological Approaches to Visualization (BELIV '22). - : IEEE. - 9798350396294 - 9798350396300 ; , s. 28-37
-
Conference paper (peer-reviewed)abstract
- Appropriate evaluation and experimental design are fundamental for empirical sciences, particularly in data-driven fields. Due to the successes in computational modeling of languages, for instance, research outcomes are having an increasingly immediate impact on end users. As the gap in adoption by end users decreases, the need increases to ensure that tools and models developed by the research communities and practitioners are reliable, trustworthy, and supportive of the users in their goals. In this position paper, we focus on the issues of evaluating visual text analytics approaches. We take an interdisciplinary perspective from the visualization and natural language processing communities, as we argue that the design and validation of visual text analytics include concerns beyond computational or visual/interactive methods on their own. We identify four key groups of challenges for evaluating visual text analytics approaches (data ambiguity, experimental design, user trust, and "big picture" concerns) and provide suggestions for research opportunities from an interdisciplinary perspective.
|
|
| 2. |
- Hall, Johan, et al.
(author)
-
A Dependency-Driven Parser for German Dependency and Constituency Representations
- 2008
-
In: Proceedings of the ACL-08: HLT Workshop on Parsing German (PaGe-08). - Stroudsburg, PA : Association for Computational Linguistics (ACL),Stroudsburg. - 9781932432152 ; , s. 47-54
-
Conference paper (peer-reviewed)abstract
- We present a dependency-driven parser that parses both dependency structures and constituent structures. Constituency representations are automatically transformed into dependency representations with complex arc labels, which makes it possible to recover the constituent structure with both constituent labels and grammatical functions. We report a labeled attachment score close to 90% for dependency versions of the TIGER and TüBa-D/Z treebanks. Moreover, the parser is able to recover both constituent labels and grammatical functions with an F-Score over 75% for TüBa-D/Z and over 65% for TIGER.
|
|
| 3. |
- Loukanova, Roussanka
(author)
-
Underspecified Relations with a Formal Language of Situation Theory
- 2015
-
In: Proceedings of the 7th International Conference on Agents and Artificial Intelligence. - : SciTePress. - 9789897580734 ; , s. 298-309
-
Conference paper (peer-reviewed)abstract
- The paper is an introduction to a formal language of Situation Theory. The language provides algorithmic processing of situated information. We introduce specialized, restricted variables that are recursively constrained to satisfy type-theoretic conditions by restrictions and algorithmic assignments. The restricted variables designate recursively connected networks of memory locations for `saving' parametric information that depends on situations and restrictions over objects. The formal definitions introduce richly informative typed language for classification and representation of underspecified, parametric, and partial information that is dependent on situations.
|
|
| 4. |
- Nilsson, Jens, et al.
(author)
-
Dependency Parsing by Transformation and Combination
- 2008
-
In: 6th International Conference on Natural Language Processing, GoTAL 2008. - Berlin / Heidelberg : Springer, Gothenburg, Sweden. ; , s. 348–359-, s. 348-359
-
Conference paper (peer-reviewed)abstract
- This study presents new language and treebank independent graph transformations that improve accuracy in data-driven dependency parsing. We show that individual generic graph transformations can increase accuracy across treebanks, but especially when they are combined using established parser combination techniques. The combination experiments also indicate that the presumed best way to combine parsers, using the highest scoring parsers, is not necessarily the best approach.
|
|
| 5. |
- Nivre, Joakim, et al.
(author)
-
Characterizing the Errors of Data-Driven Dependency Parsing Models
- 2007
-
In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. - : Association for Computational Linguistics. ; , s. 122-131
-
Conference paper (peer-reviewed)
|
|
| 6. |
- Nivre, Joakim
(author)
-
Incremental Non-Projective Dependency Parsing
- 2007
-
In: Proceedings of Human Language Technologies. - : Association for Computational Linguistics. ; , s. 396-403, s. 396-403
-
Conference paper (peer-reviewed)
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Nivre, Joakim, et al.
(author)
-
Cultivating a Swedish Treebank
- 2008
-
In: Resourceful Language Technology. - Uppsala : Acta Universitatis Upsaliensis, Uppsala. - 9789155472269 ; , s. 111-120, s. 111-120
-
Book chapter (pop. science, debate, etc.)
|
|
| 10. |
- Stymne, Sara, 1977-
(author)
-
Compound Processing for Phrase-Based Statistical Machine Translation
- 2009
-
Licentiate thesis (other academic/artistic)abstract
- In this thesis I explore how compound processing can be used to improve phrase-based statistical machine translation (PBSMT) between English and German/Swedish. Both German and Swedish generally use closed compounds, which are written as one word without spaces or other indicators of word boundaries. Compounding is both common and productive, which makes it problematic for PBSMT, mainly due to sparse data problems.The adopted strategy for compound processing is to split compounds into their component parts before training and translation. For translation into Swedish and German the parts are merged after translation. I investigate the effect of different splitting algorithms for translation between English and German, and of different merging algorithms for German. I also apply these methods to a different language pair, English--Swedish. Overall the studies show that compound processing is useful, especially for translation from English into German or Swedish. But there are improvements for translation into English as well, such as a reduction of unknown words.I show that for translation between English and German different splitting algorithms work best for different translation directions. I also design and evaluate a novel merging algorithm based on part-of-speech matching, which outperforms previous methods for compound merging, showing the need for information that is carried through the translation process, rather than only external knowledge sources such as word lists. Most of the methods for compound processing were originally developed for German. I show that these methods can be applied to Swedish as well, with similar results.
|
|
