Arianna Bisazza

3 paper cards in Mova's library · 2021–2026

Arianna Bisazza wrote 3 of the papers Mova reads, in 2021–2026, most of them on Discourse analysis, Dependency parsing, Part-of-speech tagging; often with Xiulin Yang, Ahnaf Samin, Arjan van Eerden.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

CAIT: A Syntactic Parsing Toolkit for Child–Adult InTeractions (2026)
The authors train a biaffine dependency parser (SuPar, with RoBERTa-large) on the gold part of UD-English-CHILDES, about 48k manually corrected sentences, and add a POS tagger and an utterance-level construction tagger.
Slaapte or Sliep? Extending Neural-Network Simulations of English Past Tense Learning to Dutch and German (2023)
The paper repeats Kirov and Cotterell's (2018) study of past-tense learning with a BiLSTM encoder-decoder, on English, Dutch and German.
Evaluating Text Generation from Discourse Representation Structures (2021)
The paper generates English from DRSs with a standard bi-LSTM sequence-to-sequence model, using a linearised DRS input and comparing a character-level decoder with a word-level one.