Automatic genre identification (AGI) is a text classification task focused on genres, ie, text
categories defined by the author's purpose, common function of the text, and the text's …

Massive text collections are the backbone of large language models, the main ingredient of
the current significant progress in artificial intelligence. However, as these collections are …

We investigate the problem of determining the predictive confidence (or, conversely,
uncertainty) of a neural classifier through the lens of low-resource languages. By training …

Abstract We present the Camel Treebank (CAMELTB), a 188K word open-source
dependency treebank of Modern Standard and Classical Arabic. CAMELTB 1.0 includes 13 …

This paper presents a new training dataset for automatic genre identification GINCO, which
is based on 1,125 crawled Slovenian web documents that consist of 650 thousand words …

Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies
project raise the expectation that joint training and dataset comparison is increasingly …

This paper describes the development of a free/open-source finite-state
morphologicaltransducer for Highland Puebla Nahuatl, a Uto-Aztecan language spoken in …

This paper presents a large and systematic assessment of distributional models for Galician.
To this end, we have first trained and evaluated static word embeddings (eg, word2vec …

The last decade in deep learning has brought on increasingly capable systems that are
deployed on a wide variety of applications. In natural language processing, the field has …

Abstract The paper presents ParlaMint-It, a new treebank of Italian parliamentary debates,
linguistically annotated based on the Universal Dependencies (UD) framework. The …