Learning to Disambiguate Syntactic Relations
Natural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models base...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
Bern Open Publishing
2003-12-01
|
| Series: | Linguistik Online |
| Online Access: | https://bop.unibe.ch/linguistik-online/article/view/789 |
| Summary: | Natural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models based on Maximum-Likelihood Estimation (MLE) can support a highly developed linguistic grammar in the disambiguation process.
|
|---|---|
| ISSN: | 1615-3014 |