Discourse

In this paper, we present a cross-lingual neural coreference resolution system for a less-resourced language such as Basque. To begin with, we build the first neural coreferenceresolution system for Basque, training it with the relatively small EPEC-KORREF corpus (45,000 words). Next, a cross-lingual coreference resolution system is designed. With this approach, the system learns from a bigger English corpus, using cross-lingual embeddings, to perform the coreference resolution for Basque.

In 2019, we organized the first iteration of a shared task dedicated to the underlying units used in discourse parsing across formalisms: the DISRPT Shared Task on Elementary Discourse Unit Segmentation and Connective Detection. In this paper we review the data included in the task, which cover 2.6 million manually annotated tokens from 15 datasets in 10 languages, survey and compare submit-ted systems and report on system performance on each task for both annotated and plain-tokenized versions of the data.

Lan honek euskararako korreferentzia-ebazpenean egindako lanari jarraipena ematea du helburu, korreferentzia-ebazpenerako neurona-sareetan oinarritutako sistema bat eraikiz. Horretarako polonierarako eraikitako sistema bat hartu da abiapuntutzat, eta euskarara egokitu. EPEC-KORREF corpusetik abiatuta, aipamen-bikoteak eta hauen ezaugarriak erauzi dira eta neurona-sarea entrenatu da aipamen-bikoteak korreferenteak ote diren erabakitzeko. Jarraian, neurona-sarearen iragarpenetatik korreferentzia-klusterrak sortu eta ebaluatu egin dira.

The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation.

Development of discourse parsers to annotate the relational discourse structure of a text is crucial for many downstream tasks. However, most of the existing work focuses on English, assuming a quite large dataset. Discourse data have been annotated for Basque, but training a system on these data is challenging since the corpus is very small. In this paper, we create the first parser based on RST for Basque, and we investigate the use of data in another language to improve the performance of a Basque discourse parser.

Discourse information is crucial for a better understanding of the text structure and it is also necessary to describe which part of an opinionated text is more relevant or to decide how a text span can change the polarity (strengthen or weaken) of other spans by means of coherence relations. This work presents the first results on the annotation of the Basque Opinion Corpus using Rhetorical Structure Theory (RST).