Alexander O'Connor

2 paper cards in Mova's library · 2019–2020

Alexander O'Connor wrote 2 of the papers Mova reads, in 2019–2020, most of them on Machine translation; often with Henry Elder, Jennifer Foster, James Barry.

Papers

Shape of Synth to Come: Why We Should Use Synthetic Data for English Surface Realization (2020)
Surface realization turns a UD-like tree of lemmas back into a sentence with word order and inflection. The system is a bidirectional LSTM encoder-decoder trained on the English EWT data of the 2018 shared task (12,375 training sentences, 1,978 dev, 2,062 test). Three changes (several random linearisations per tree…
Designing a Symbolic Intermediate Representation for Neural Surface Realization (2019)
Neural generators often hallucinate, repeat or contradict the input. The paper proposes a symbolic intermediate representation between the content and the text. First a model turns each reference sentence of the E2E restaurant data into this representation, and then a second neural model realises the text from it.…