Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent juan-jose-rodriguez.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent juan-carlos-luengo.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent sebastian-sanchez.
- item-5 previous item-4.
- 583 creator ines-rehbein.
- 583 creator sandra-kuebler.
- 583 creator wolfgang-maier.
- 583 creator yannick-versley.
- 583 type InProceedings.
- 583 label "How to Compare Treebanks".
- 583 sameAs 583.
- 583 abstract "Recent years have seen an increasing interest in developing standards for linguistic annotation, with a focus on the interoperability of the resources. This effort, however, requires a profound knowledge of the advantages and disadvantages of linguistic annotation schemes in order to avoid importing the flaws and weaknesses of existing encoding schemes into the new standards. This paper addresses the question how to compare syntactically annotated corpora and gain insights into the usefulness of specific design decisions. We present an exhaustive evaluation of two German treebanks with crucially different encoding schemes. We evaluate three different parsers trained on the two treebanks and compare results using EvalB, the Leaf-Ancestor metric, and a dependency-based evaluation. Furthermore, we present TePaCoC, a new testsuite for the evaluation of parsers on complex German grammatical constructions. The testsuite provides a well thought-out error classification, which enables us to compare parser output for parsers trained on treebanks with different encoding schemes and provides interesting insights into the impact of treebank annotation schemes on specific constructions like PP attachment or non-constituent coordination.".
- 583 hasAuthorList authorList.
- 583 hasTopic Linguistics.
- 583 isPartOf proceedings.
- 583 keyword "Evaluation methodologies".
- 583 keyword "Parsing Systems".
- 583 keyword "Syntax".
- 583 title "How to Compare Treebanks".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasLastItem item-4.
- item-1 type ListItem.
- item-1 hasContent sandra-kuebler.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent wolfgang-maier.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent ines-rehbein.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent yannick-versley.
- item-4 previous item-3.
- 584 creator alessio-brutti.
- 584 creator luca-cristoforetti.
- 584 creator lutz-marquardt.
- 584 creator maurizio-omologo.
- 584 creator walter-kellermann.
- 584 type InProceedings.
- 584 label "WOZ Acoustic Data Collection for Interactive TV".
- 584 sameAs 584.
- 584 abstract "This paper describes a multichannel acoustic data collection recorded under the European DICIT project, during the Wizard of Oz (WOZ) experiments carried out at FAU and FBK-irst laboratories. The scenario is a distant-talking interface for interactive control of a TV. The experiments involve the acquisition of multichannel data for signal processing front-end and were carried out due to the need to collect a database for testing acoustic pre-processing algorithms. In this way, realistic scenarios can be simulated at a preliminary stage, instead of real-time implementations, allowing for repeatable experiments. To match the project requirements, the WOZ experiments were recorded in three languages: English, German and Italian. Besides the user inputs, the database also contains non-speech related acoustic events, room impulse response measurements and video data, the latter used to compute 3D labels. Sessions were manually transcribed and segmented at word level, introducing also specific labels for acoustic events.".
- 584 hasAuthorList authorList.
- 584 hasTopic Linguistics.
- 584 isPartOf proceedings.
- 584 keyword "Corpus (creation, annotation, etc.)".
- 584 keyword "Dialogue & Natural Interactivity".
- 584 keyword "Speech resource/database".
- 584 title "WOZ Acoustic Data Collection for Interactive TV".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent alessio-brutti.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent luca-cristoforetti.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent walter-kellermann.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent lutz-marquardt.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent maurizio-omologo.
- item-5 previous item-4.
- 586 creator arne-joensson.
- 586 creator linus-sellberg.
- 586 type InProceedings.
- 586 label "Using Random Indexing to improve Singular Value Decomposition for Latent Semantic Analysis".
- 586 sameAs 586.
- 586 abstract "In this paper we present results from using Random indexing for Latent Semantic Analysis to handle Singular Value Decomposition tractability issues. In the paper we compare Latent Semantic Analysis, Random Indexing and Latent Semantic Analysis on Random Indexing reduced matrices. Our results show that Latent Semantic Analysis on Random Indexing reduced matrices provide better results on Precision and Recall than Random Indexing only. Furthermore, computation time for Singular Value Decomposition on a Random indexing reduced matrix is almost halved compared to Latent Semantic Analysis.".
- 586 hasAuthorList authorList.
- 586 hasTopic Linguistics.
- 586 isPartOf proceedings.
- 586 keyword "Information Extraction, Information Retrieval".