• Publications
  • Influence
ATLAS
TLDR
Se esista un sapere diverso e superiore rispetto alle interpretazioni soggettive, in polemica contro alcuni pensatori precedenti, Platone ritiene che per risolvere adeguatamente qualsiasi problema sia necessaria the garanzia di una conoscenza (epistéme).
Apertium: a free/open-source platform for rule-based machine translation
TLDR
The Apertium platform is summarised: the translation engine, the encoding of linguistic data, and the tools developed around the platform are discussed.
ParaCrawl: Web-scale parallel corpora for the languages of the EU
TLDR
Two projects funded by the Connecting Europe Facility aim at harvesting parallel corpora from the Internet for languages used in the European Union, and releases successive versions of the free/open-source web crawling software used.
An open-source shallow-transfer machine translation engine for the Romance languages of Spain
TLDR
The current status of development of an open-source shallow-transfer machine translation engine for the Romance languages of Spain is presented as part of a larger government-funded project which includes non-Romance languages such as Basque and involving both universities and linguistic technology companies.
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering
We posed the shared task of assigning sentence-level quality scores for a very noisy corpus of sentence pairs crawled from the web, with the goal of sub-selecting 1% and 10% of high-quality data to
Open-Source Portuguese-Spanish Machine Translation
TLDR
The MT engine, the formats it uses for linguistic data, and the compilers that convert these data into an efficient format used by the engine are described, and it is described in more detail the pilot Portuguese and Spanish linguistic data.
Making sense of neural machine translation
TLDR
This paper introduces NMT, and explains in detail, without the mathematical complexity, how neural machine translation systems work, how they are trained, and their main differences with SMT systems.
Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units
TLDR
This article describes a simple strategy to devise stable encodings of finite-state machines in computationally capable discrete-time recurrent neural architectures with sigmoid units and gives a detailed presentation on how this strategy may be applied to encode a general class of infinite- state machines in a variety of commonly used first- and second-order recurrent neural networks.
Open-source machine translation : an opportunity for minor languages
I have explored the positive effects that the availability of machine translation may have on the status and development of minor languages, focusing in particular on those effects which are specific
An Implementation of Deterministic Tree Automata Minimization
TLDR
This work fully describes a simple implementation of the standard minimization algorithm that needs a time in O(|A|2), with |A| being the size of the DTA.
...
...