1 |
Multilingual Surface Realization Using Universal Dependency Trees
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Proceedings of the 6th Workshop on Vision and Language (VL'17)
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Effect of Data Annotation, Feature Selection and Model Choice on Spatial Description Generation in French
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Proceedings of the 2016 Workshop on Vision and Language (VL’16)
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Weakly supervised construction of a repository of iconic images
|
|
|
|
Abstract:
We present a first attempt at semi-automatically harvesting a dataset of iconic images, namely images that depict objects or scenes, which arouse associations to abstract topics. Our method starts with representative topic-evoking images from Wikipedia, which are labeled with relevant concepts and entities found in their associated captions. These are used to query an online image repository (i.e., Flickr), in order to further acquire additional examples of topic-specific iconic relations. To this end, we leverage a combination of visual similarity measures, image clustering and matching algorithms to acquire clusters of iconic images that are topically connected to the original seed images, while also allowing for various degrees of diversity. Our first results are promising in that they indicate the feasibility of the task and that we are able to build a first version of our resource with minimal supervision.
|
|
Keyword:
004 Informatik
|
|
URL: https://madoc.bib.uni-mannheim.de/37061/ http://www.aclweb.org/anthology/W14-5410
|
|
BASE
|
|
Hide details
|
|
7 |
Proceedings of UCNLG+Eval: Language Generation and Evaluation
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Unsupervised alignment of comparable data and text resources
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Discrete vs. continuous rating scales for language evaluation in NLP
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Comparing rating scales and preference judgements in language evaluation
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Assessing the trade-off between system building cost and output quality in data-to-text generation
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Construction of bilingual multimodal corpora of referring expressions in collaborative problem solving
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Finding common ground: towards a surface realisation shared task
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Generating referring expressions in context: the GREC shared task evaluation challenges
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Extracting parallel fragments from comparable corpora for data-to-text generation
|
|
|
|
BASE
|
|
Show details
|
|
17 |
The GREC named entity generation challenge 2009; Overview and evaluation results
|
|
|
|
BASE
|
|
Show details
|
|
19 |
The GREC main subject reference generation challenge 2009: Overview and evaluation results
|
|
|
|
BASE
|
|
Show details
|
|
20 |
An investigation into the validity of some metrics for automatically evaluating Natural Language Generation systems
|
|
|
|
BASE
|
|
Show details
|
|
|
|