Using a Discourse Bank and a Lexicon for the Automatic Identification of Discourse Connectives

Abstract

We describe two new resources that have been prepared for European Portuguese and how they are used for discourse parsing: the Portuguese subpart of the TED-MDB corpus, a multilingual corpus of TED Talks that has been annotated in the PDTB style, and the Lexicon of Discourse Markers for Portuguese (LDM-PT). Both lexicon and corpus are used in a preliminary experiment for discourse connective identification in texts. This includes, in many cases, the difficult task of disambiguating between connective and non-connective uses. We annotated the PT-TED-MDB corpus with POS, lemma and syntactic constituency and focus on the 10 most frequent connectives in the corpus. The best approach considers word-form+POS+syntactic annotation and leads to 85% precision.

TED-MDB Lexicons: Tr-EnConnLex, Pt-EnConnLex

“…Given the availability of TED-MDB, we propose an alternative way of building bilingual DC lexicons, which can be seen as the multilingual extension of extracting DC lexicons from annotated resources as in Mendes and del Río (2018); Das et al (2018).…”