Matches in ScholarlyData for { ?s ?p ?o. }
- 117 sameAs 117.
- 117 abstract "WCTAnalyze is a tool for storing, accessing and visually analyzing huge collections of temporally indexed data. It is motivated by applications in media analysis, business intelligence etc. where higher level analysis is performed on top of linguistically and statistically processed unstructured textual data. WCTAnalyze combines fast access with economically storage behaviour and appropriates a lot of built in visualization options for result presentation in detail as well as in contrast. So it enables an efficient and effective way to explore chronological text patterns of word forms, their co-occurrence sets and co-occurrence set intersections. Digging deep into co-occurrences of the same semantic or syntactic describing wordforms, some entities can be recognized as to be temporal related, whereas other differ significantly. This behaviour motivates approaches in interactive discovering events based on co-occurrence subsets.".
- 117 hasAuthorList authorList.
- 117 hasTopic Linguistics.
- 117 isPartOf proceedings.
- 117 keyword "LR Infrastructures and Architectures".
- 117 keyword "Text mining".
- 117 keyword "Tools, systems, applications".
- 117 title "Tapping Huge Temporally Indexed Textual Resources with WCTAnalyze".
- 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 sebastian-gottwald.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent matthias-richter.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent gerhard-heyer.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent gerik-scheuermann.
- item-4 previous item-3.
- 119 creator carlos-d-martinez-hinarejos.
- 119 creator vicent-tamarit.
- 119 type InProceedings.
- 119 label "Evaluation of Different Segmentation Techniques for Dialogue Turns".
- 119 sameAs 119.
- 119 abstract "In dialogue systems, it is necessary to decode the user input into semantically meaningful units. These semantical units, usually Dialogue Acts (DA), are used by the system to produce the most appropriate response. The user turns can be segmented into utterances, which are meaningful segments from the dialogue viewpoint. In this case, a single DA is associated to each utterance. Many previous works have used DA assignation models on segmented dialogue corpora, but only a few have tried to perform the segmentation and assignation at the same time. The knowledge of the segmentation of turns into utterances is not common in dialogue corpora, and knowing the quality of the segmentations provided by the models that simultaneously perform segmentation and assignation would be interesting. In this work, we evaluate the accuracy of the segmentation offered by this type of model. The evaluation is done on a Spanish dialogue system on a railway information task. The results reveal that one of these techniques provides a high quality segmentation for this corpus.".
- 119 hasAuthorList authorList.
- 119 hasTopic Linguistics.
- 119 isPartOf proceedings.
- 119 keyword "Dialogue & Natural Interactivity".
- 119 keyword "Statistical methods".
- 119 keyword "Tools, systems, applications".
- 119 title "Evaluation of Different Segmentation Techniques for Dialogue Turns".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent carlos-d-martinez-hinarejos.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent vicent-tamarit.
- item-2 previous item-1.
- 120 creator barbara-plank.
- 120 creator khalil-sima-an.
- 120 type InProceedings.
- 120 label "Subdomain Sensitive Statistical Parsing using Raw Corpora".
- 120 sameAs 120.
- 120 abstract "Modern statistical parsers are trained on large annotated corpora (treebanks). These treebanks usually consist of sentences addressing different subdomains (e.g. sports, politics, music), which implies that the statistics gathered by current statistical parsers are mixtures of subdomains of language use. In this paper we present a method that exploits raw subdomain corpora gathered from the web to introduce subdomain sensitivity into a given parser. We employ statistical techniques for creating an ensemble of domain sensitive parsers, and explore methods for amalgamating their predictions. Our experiments show that introducing domain sensitivity by exploiting raw corpora can improve over a tough, state-of-the-art baseline.".
- 120 hasAuthorList authorList.
- 120 hasTopic Linguistics.
- 120 isPartOf proceedings.
- 120 keyword "Acquisition, Machine Learning".
- 120 keyword "Parsing Systems".
- 120 keyword "Statistical methods".
- 120 title "Subdomain Sensitive Statistical Parsing using Raw Corpora".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent barbara-plank.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent khalil-sima-an.
- item-2 previous item-1.
- 121 creator beata-megyesi.
- 121 creator bengt-dahlqvist.
- 121 creator eva-pettersson.
- 121 creator joakim-nivre.
- 121 type InProceedings.
- 121 label "Swedish-Turkish Parallel Treebank".
- 121 sameAs 121.
- 121 abstract "In this paper, we describe our work on building a parallel treebank for a less studied and typologically dissimilar language pair, namely Swedish and Turkish. The treebank is a balanced syntactically annotated corpus containing both fiction and technical documents. In total, it consists of approximately 160,000 tokens in Swedish and 145,000 in Turkish. The texts are linguistically annotated using different layers from part of speech tags and morphological features to dependency annotation. Each layer is automatically processed by using basic language resources for the involved languages. The sentences and words are aligned, and partly manually corrected. We create the treebank by reusing and adjusting existing tools for the automatic annotation, alignment, and their correction and visualization. The treebank was developed within the project supporting research environment for minor languages aiming at to create representative language resources for language pairs dissimilar in language structure. Therefore, efforts are put on developing a general method for formatting and annotation procedure, as well as using tools that can be applied to other language pairs easily.".
- 121 hasAuthorList authorList.
- 121 hasTopic Linguistics.
- 121 isPartOf proceedings.
- 121 keyword "Corpus (creation, annotation, etc.)".
- 121 keyword "Multilinguality".
- 121 keyword "Syntax".
- 121 title "Swedish-Turkish Parallel Treebank".
- 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.