Matches in ScholarlyData for { ?s ?p ?o. }
- 290 hasTopic Linguistics.
- 290 isPartOf proceedings.
- 290 keyword "Corpus (creation, annotation, etc.)".
- 290 keyword "Tagging".
- 290 keyword "Validation of LRs".
- 290 title "Validating the Quality of Full Morphological Annotation".
- 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 drahomira-johanka-spoustova.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent pavel-pecina.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent jan-hajic.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent miroslav-spousta.
- item-4 previous item-3.
- 291 creator mark-arehart.
- 291 type InProceedings.
- 291 label "A Ground Truth Dataset for Matching Culturally Diverse Romanized Person Names".
- 291 sameAs 291.
- 291 abstract "This paper describes the development of a ground truth dataset of culturally diverse Romanized names in which approximately 70,000 names are matched against a subset of 700. We ran the subset as queries against the complete list using several matchers, created adjudication pools, adjudicated the results, and compiled two versions of ground truth based on different sets of adjudication guidelines and methods for resolving adjudicator conflicts. The name list, drawn from publicly available sources, was manually seeded with over 1500 name variants. These names include transliteration variation, database fielding errors, segmentation differences, incomplete names, titles, initials, abbreviations, nicknames, typos, OCR errors, and truncated data. These diverse types of matches, along with the coincidental name similarities already in the list, make possible a comprehensive evaluation of name matching systems. We have used the dataset to evaluate several open source and commercial algorithms and provide some of those results.".
- 291 hasAuthorList authorList.
- 291 hasTopic Linguistics.
- 291 isPartOf proceedings.
- 291 keyword "Corpus (creation, annotation, etc.)".
- 291 keyword "Evaluation methodologies".
- 291 keyword "Information Extraction, Information Retrieval".
- 291 title "A Ground Truth Dataset for Matching Culturally Diverse Romanized Person Names".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent mark-arehart.
- 292 creator michael-carl.
- 292 type InProceedings.
- 292 label "Using Log-linear Models for Tuning Machine Translation Output".
- 292 sameAs 292.
- 292 abstract "We describe a set of experiments to explore statistical techniques for ranking and selecting the best translations in a graph of translation hypotheses. In a previous paper (Carl, 2007) we have described how the graph of hypotheses is generated through shallow transfer and chunk permutation rules, where nodes consist of vectors representing morpho-syntactic properties of words and phrases. This paper describes a number of methods to train statistical feature functions from some of the vector s components. The feature functions are trained off-line on different types of text and their log-linear combination is then used to retrieve the best translation paths in the graph. We compare two language modelling toolkits, the CMU and the SRI toolkit and arrive at three results: 1) models of lemma-based feature functions produce better results than token-based models, 2) adding PoS-tag feature function to the lemma models improves the output and 3) weights for lexical translations are suited if the training material is similar to the texts to be translated.".
- 292 hasAuthorList authorList.
- 292 hasTopic Linguistics.
- 292 isPartOf proceedings.
- 292 keyword "Language modelling".
- 292 keyword "Machine Translation, SpeechToSpeech Translation".
- 292 keyword "Statistical methods".
- 292 title "Using Log-linear Models for Tuning Machine Translation Output".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent michael-carl.
- 293 creator alexandre-patry.
- 293 creator philippe-langlais.
- 293 type InProceedings.
- 293 label "MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices".
- 293 sameAs 293.
- 293 abstract "This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a written text as input, MISTRAL translates word lattices produced by automatic speech recognition systems. The lattices are translated in two passes using a phrase-based model. Our experiments reveal an improvement in BLEU when translating lattices instead of sentences returned by a speech recognition system.".
- 293 hasAuthorList authorList.
- 293 hasTopic Linguistics.
- 293 isPartOf proceedings.
- 293 keyword "Machine Translation, SpeechToSpeech Translation".
- 293 keyword "Multilinguality".
- 293 keyword "Tools, systems, applications".
- 293 title "MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices".
- 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 alexandre-patry.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent philippe-langlais.
- item-2 previous item-1.
- 294 creator leo-wanner.
- 294 creator margarita-alonso-ramos.
- 294 creator owen-rambow.
- 294 type InProceedings.
- 294 label "Using Semantically Annotated Corpora to Build Collocation Resources".
- 294 sameAs 294.
- 294 abstract "We present an experiment in extracting collocations from the FrameNet corpus, specifically, support verbs such as direct in Environmentalists directed strong criticism at world leaders. Support verbs do not contribute meaning of their own and the meaning of the construction is provided by the noun; the recognition of support verbs is thus useful in text understanding. Having access to a list of support verbs is also useful in applications that can benefit from paraphrasing, such as generation (where paraphrasing can provide variety). This paper starts with a brief presentation of the notion of lexical function in Meaning-Text Theory, where they fall under the notion of lexical function, and then discusses how relevant information is encoded in the FrameNet corpus. We describe the resource extracted from the FrameNet corpus.".
- 294 hasAuthorList authorList.
- 294 hasTopic Linguistics.
- 294 isPartOf proceedings.
- 294 keyword "Corpus (creation, annotation, etc.)".
- 294 keyword "Lexicon, lexical database".
- 294 keyword "MultiWord Expressions & Collocations".