[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/alexander-o-connor/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Alexander O'Connor

# 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](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/); often with [Henry Elder](https://md.mova.elamur.ai/free/en/docs/papers/authors/henry-elder/), [Jennifer Foster](https://md.mova.elamur.ai/free/en/docs/papers/authors/jennifer-foster/), James Barry.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Alexander+O%27Connor) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Alexander+O%27Connor) · [dblp](https://dblp.org/search?q=Alexander+O%27Connor) · [ACL Anthology](https://aclanthology.org/search/?q=Alexander+O%27Connor) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Alexander+O%27Connor)

Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 1

## Papers

1. **[Shape of Synth to Come: Why We Should Use Synthetic Data for English Surface Realization](https://md.mova.elamur.ai/free/en/docs/papers/elder-2020-shape-synth-come-why-we/)** *(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…
2. **[Designing a Symbolic Intermediate Representation for Neural Surface Realization](https://md.mova.elamur.ai/free/en/docs/papers/elder-2019-designing-symbolic-intermediate-representation-neural/)** *(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.…

## Co-authors (4)

- [Henry Elder](https://md.mova.elamur.ai/free/en/docs/papers/authors/henry-elder/) ×2
- [Jennifer Foster](https://md.mova.elamur.ai/free/en/docs/papers/authors/jennifer-foster/) ×2
- James Barry
- Robert Burke
- [← previous Alexander Koller](https://md.mova.elamur.ai/free/en/docs/papers/authors/alexander-koller/)
- [next → Alexander Tsuetaki](https://md.mova.elamur.ai/free/en/docs/papers/authors/alexander-tsuetaki/)
- [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)