The Denoised Web Treebank: Evaluating Dependency Parsing under Noisy Input Conditions
| Authors |
|
|---|---|
| Publication date | 2016 |
| Host editors |
|
| Book title | LREC 2016 : Tenth International Conference on Language Resources and Evaluation |
| Book subtitle | May 23-28, 2016, Grand Hotel Bernardin Conference Center, Portorož, Slovenia |
| ISBN (electronic) |
|
| Event | Language Resources and Evaluation Conference (LREC 2016) |
| Pages (from-to) | 649-653 |
| Publisher | Paris: European Language Resources Association (ELRA) |
| Organisations |
|
| Abstract | We introduce the Denoised Web Treebank: a treebank including a normalization layer and a corresponding evaluation metric for dependency parsing of noisy text, such as Tweets. This benchmark enables the evaluation of parser robustness as well as text normalization methods, including normalization as machine translation and unsupervised lexical normalization, directly on syntactic trees. Experiments show that text normalization together with a combination of domain-specific and generic part-of-speech taggers can lead to a significant improvement in parsing accuracy on this test set. |
| Document type | Conference contribution |
| Language | English |
| Published at | http://www.lrec-conf.org/proceedings/lrec2016/summaries/86.html |
| Other links | http://www.lrec-conf.org/proceedings/lrec2016/index.html |
| Downloads |
86_Paper
(Final published version)
|
| Permalink to this page | |