2 |
The ParlaMint corpora of parliamentary proceedings
|
|
|
|
In: Lang Resour Eval (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Multilingual comparable corpora of parliamentary debates ParlaMint 2.1
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Linguistically annotated multilingual comparable corpora of parliamentary debates ParlaMint.ana 2.1
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Linguistically annotated multilingual comparable corpora of parliamentary debates ParlaMint.ana 2.0
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Multilingual comparable corpora of parliamentary debates ParlaMint 2.0
|
|
|
|
BASE
|
|
Show details
|
|
12 |
A Universal Dependencies Conversion Pipeline for a Penn-format Constituency Treebank ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step ...
|
|
|
|
Abstract:
Previous work on using BiLSTM models for PoS tagging has primarily focused on small tagsets. We evaluate BiLSTM models for tagging Icelandic, a morphologically rich language, using a relatively large tagset. Our baseline BiLSTM model achieves higher accuracy than any previously published tagger not taking advantage of a morphological lexicon. When we extend the model by incorporating such data, we outperform previous state-of-the-art results by a significant margin. We also report on work in progress that attempts to address the problem of data sparsity inherent in morphologically detailed, fine-grained tagsets. We experiment with training a separate model on only the lexical category and using the coarse-grained output tag as an input for the main model. This method further increases the accuracy and reduces the tagging errors by 21.3% compared to previous state-of-the-art results. Finally, we train and test our tagger on a new gold standard for Icelandic. ... : Accepted by RANLP 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/1907.09038 https://dx.doi.org/10.48550/arxiv.1907.09038
|
|
BASE
|
|
Hide details
|
|
|
|