Helmut Schmid
Dados Biográficos
| ID | 6536964 |
|---|---|
| NOME | Helmut Schmid |
| PRENOMES | Helmut |
| SOBRENOME | Schmid |
| ASSINATURA | SCHMID H |
| AFILIAÇÕES | Ludwig-Maximilians-Universität München |
| ORCID | 0000-0001-8003-7708 |
| VERIFICADO | Sim |
| TOTAL DE OBRAS | 4 |
| TOTAL DE CITAÇÕES | 1 |
| OBRAS COMO AUTOR | 4 |
| OBRAS COMO EDITOR | 0 |
| PRIMEIRO ANO DE PUBLICAÇÃO | 2012 |
| ANO MAIS RECENTE DE PUBLICAÇÃO | 2017 |
| ÍNDICE H | 1 |
LatMor
We present the first large-coverage finite-state open-source morphology for Latin (called LatMor) which parses as well as generates vowel quantity information. LatMor is based on the Berlin Latin Lexicon comprising about 70,000 lemmata of classical Latin compiled by the group of Dietmar Najock in theirwork on concordances of Latin authors (see Rapsch and Najock, 1991) which was recently updated by us. Compared to the well-known Morpheus system of…
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation
In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on mini…
Knowledge Sources for Constituent Parsing of German, a Morphologically Rich and Less-Configurational Language
We study constituent parsing of German, a morphologically rich and less-configurational language. We use a probabilistic context-free grammar treebank grammar that has been adapted to the morphologically rich properties of German by markovization and special features added to its productions. We evaluate the impact of adding lexical knowledge. Then we examine both monolingual and bilingual approaches to parse reranking. Our reranking parser is th…
Statistical Models for Unsupervised, Semi-Supervised, and Supervised Transliteration Mining
We present a generative model that efficiently mines transliteration pairs in a consistent fashion in three different settings: unsupervised, semi-supervised, and supervised transliteration mining. The model interpolates two sub-models, one for the generation of transliteration pairs and one for the generation of non-transliteration pairs (i.e., noise). The model is trained on noisy unlabeled data using the EM algorithm. During training the trans…
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation
In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on mini…
Knowledge Sources for Constituent Parsing of German, a Morphologically Rich and Less-Configurational Language
We study constituent parsing of German, a morphologically rich and less-configurational language. We use a probabilistic context-free grammar treebank grammar that has been adapted to the morphologically rich properties of German by markovization and special features added to its productions. We evaluate the impact of adding lexical knowledge. Then we examine both monolingual and bilingual approaches to parse reranking. Our reranking parser is th…
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation
In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on mini…
LatMor
We present the first large-coverage finite-state open-source morphology for Latin (called LatMor) which parses as well as generates vowel quantity information. LatMor is based on the Berlin Latin Lexicon comprising about 70,000 lemmata of classical Latin compiled by the group of Dietmar Najock in theirwork on concordances of Latin authors (see Rapsch and Najock, 1991) which was recently updated by us. Compared to the well-known Morpheus system of…
Statistical Models for Unsupervised, Semi-Supervised, and Supervised Transliteration Mining
We present a generative model that efficiently mines transliteration pairs in a consistent fashion in three different settings: unsupervised, semi-supervised, and supervised transliteration mining. The model interpolates two sub-models, one for the generation of transliteration pairs and one for the generation of non-transliteration pairs (i.e., noise). The model is trained on noisy unlabeled data using the EM algorithm. During training the trans…
Artificial Intelligence (4 obras) · Computer Science (4 obras) · Natural language processing (4 obras) · Natural Language Processing Techniques (4 obras) · Topic Modeling (4 obras) · Linguistics (2 obras) · Machine learning (2 obras) · Mathematics (2 obras) · Speech recognition (2 obras) · Algorithm (1 obra)