Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 hasContent pavel-rychly.
- item-2 previous item-1.
- 482 creator valia-kordoni.
- 482 creator yi-zhang.
- 482 type InProceedings.
- 482 label "Robust Parsing with a Large HPSG Grammar".
- 482 sameAs 482.
- 482 abstract "In this paper we propose a partial parsing model which achieves robust parsing with a large HPSG grammar. Constraint-based precision grammars, like the HPSG grammar we are using for the experiments reported in this paper, typically lack robustness, especially when applied to real world texts. To maximally recover the linguistic knowledge from an unsuccessful parse, a proper selection model must be used. Also, the efficiency challenges usually presented by the selection model must be answered. Building on the work reported in (Zhang et al., 2007), we further propose a new partial parsing model that splits the parsing process into two stages, both of which use the bottom-up chart-based parsing algorithm. The algorithm is implemented and a preliminary experiment shows promising results.".
- 482 hasAuthorList authorList.
- 482 hasTopic Linguistics.
- 482 isPartOf proceedings.
- 482 keyword "Grammars".
- 482 keyword "Parsing Systems".
- 482 keyword "Syntax".
- 482 title "Robust Parsing with a Large HPSG Grammar".
- 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 yi-zhang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent valia-kordoni.
- item-2 previous item-1.
- 483 creator jesus-gimenez.
- 483 creator lluis-marquez.
- 483 type InProceedings.
- 483 label "Towards Heterogeneous Automatic MT Error Analysis".
- 483 sameAs 483.
- 483 abstract "This work studies the viability of performing heterogeneous automatic MT error analyses. Error analysis is, undoubtly, one of the most crucial stages in the development cycle of an MT system. However, often not enough attention is paid to this process. The reason is that performing an accurate error analysis requires intensive human labor. In order to speed up the error analysis process, we suggest partially automatizing it by having automatic evaluation metrics play a more active role. For that purpose, we have compiled a large and heterogeneous set of features at different linguistic levels and at different levels of granularity. Through a practical case study, we show how these features provide an effective means of ellaborating interpretable and detailed automatic reports of translation quality.".
- 483 hasAuthorList authorList.
- 483 hasTopic Linguistics.
- 483 isPartOf proceedings.
- 483 keyword "Evaluation methodologies".
- 483 keyword "Machine Translation, SpeechToSpeech Translation".
- 483 keyword "Tools, systems, applications".
- 483 title "Towards Heterogeneous Automatic MT Error Analysis".
- 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 jesus-gimenez.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent lluis-marquez.
- item-2 previous item-1.
- 484 creator joerg-tiedemann.
- 484 type InProceedings.
- 484 label "Synchronizing Translated Movie Subtitles".
- 484 sameAs 484.
- 484 abstract "This paper addresses the problem of synchronizing movie subtitles, which is necessary to improve alignment quality when building a parallel corpus out of translated subtitles. In particular, synchronization is done on the basis of aligned anchor points. Previous studies have shown that cognate filters are useful for the identification of such points. However, this restricts the approach to related languages with similar alphabets. Here, we propose a dictionary-based approach using automatic word alignment. We can show an improvement in alignment quality even for related languages compared to the cognate-based approach.".
- 484 hasAuthorList authorList.
- 484 hasTopic Linguistics.
- 484 isPartOf proceedings.
- 484 keyword "Corpus (creation, annotation, etc.)".
- 484 keyword "Multilinguality".
- 484 title "Synchronizing Translated Movie Subtitles".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent joerg-tiedemann.
- 486 creator ingunn-amdal.
- 486 creator joern-almberg.
- 486 creator ole-morten-strand.
- 486 creator torbjoern-svendsen.
- 486 type InProceedings.
- 486 label "RUNDKAST: an Annotated Norwegian Broadcast News Speech Corpus".
- 486 sameAs 486.
- 486 abstract "This paper describes the Norwegian broadcast news speech corpus RUNDKAST. The corpus contains recordings of approximately 77 hours of broadcast news shows from the Norwegian broadcasting company NRK. The corpus covers both read and spontaneous speech as well as spontaneous dialogues and multipart discussions, including frequent occurrences of non-speech material (e.g. music, jingles). The recordings have large variations in speaking styles, dialect use and recording/transmission quality. RUNDKAST has been annotated for research in speech technology. The entire corpus has been manually segmented and transcribed using hierarchical levels. A subset of one hour of read and spontaneous speech from 10 different speakers has been manually annotated using broad phonetic labels. We provide a description of the database content, the annotation tools and strategies, and the conventions used for the different levels of annotation. A corpus of this kind has up to this point not been available for Norwegian, but is considered a necessary part of the infrastructure for language technology research in Norway. The RUNDKAST corpus is planned to be included in a future national Norwegian language resource bank.".
- 486 hasAuthorList authorList.
- 486 hasTopic Linguistics.
- 486 isPartOf proceedings.
- 486 keyword "Corpus (creation, annotation, etc.)".
- 486 keyword "Phonetic Databases, Phonology".
- 486 keyword "Speech resource/database".
- 486 title "RUNDKAST: an Annotated Norwegian Broadcast News Speech Corpus".
- 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 ingunn-amdal.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent ole-morten-strand.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent joern-almberg.
- item-3 next item-4.
- item-3 previous item-2.