35.6% Better Than Google NMT For English-to-Italian Securities

This English-to-Italian securities translator uses a Slate Desktop personalized SMT that’s 35.6% more productive than Google NMT.

A Slate Rocks customer (a translator) created a translation engine with his or her translation memories (TMs) using a personal computer. This page describes the engine and compares the translator’s Slate Desktop experience to an experience using Google’s new-and-improved neural machine translation (NMT) technology. You can read the entire report with thirth (30) more customer experiences by downloading the full report Study of Machine Translated Segment Pairs.

Slate Desktop Engine Details

The customer started with translation memories in the language pair and industry of his or her work, totaling the estimated corpus size number of segments. Slate Desktop cleaned the TMs, prepared a training corpus and built the engine. Note that these processes typically runs overnight. During that processing, Slate Desktop also extracted a representative set consisting of randomly selected segments from the training corpus.

sourceen
targetit
subject domainsecurities
estimated corpus size1,500,000
segments per representative set3,381
words per source segment27
words per target segment30

Benchmark Score Comparison

The segment pairs in the representative set are representative of the translator’s daily work. By focusing on one translator’s experience, these scores indicate a level of work reduction this customer will likely experience in his or her daily work using the respective MT system (Google or Slate Desktop) with 95% confidence.

 Google
NMT
Slate Desktop
SMT
words per MT segment2828
BLEU score35.976.64
exact MT match (count)1321289
exact MT match (percent)3.9%38.1%
words per exact MT match (count)1221
filtered BLEU score (no exact MT matches)34.967.9
segments requiring edit (count)3,2492,092
character edits per segment6345
total character edits204,68794,140

These scores indicate this customer using Slate Desktop will likely spend significantly less time editing MT suggestions than if he or she were using Google for this work. This is because Slate Desktop creates engines with the customers translation memories and optimizes them to predict how the customer translates. While on the other hand, Google optimizes its NMT service for millions of customers with countless demands.

Google’s three (3) longest exact MT matches

The exact MT match (count) in the Benchmark Scores table (above) is the number of segments that Google NMT successfully matched to the translator’s actual work, i.e. Google successfully predicted the translator’s actions. The three segments in this table are the exact MT match segments with the longest length. This translator can expect to experience these kinds Google NMT results while translating these kinds of project.

enit (Google and translator)
9. Changes in the composition of the investment portfolio9. Variazioni nella composizione del portafoglio di investimenti
E) Information on the risks and relevant hedging policiesE) Informazioni sui rischi e sulle relative politiche di copertura
The analysis carried out highlighted the following key elementsL’analisi effettuata ha evidenziato i seguenti elementi chiave

Slate’s three (3) longest exact MT matches

The exact MT match (count) in the Benchmark Scores table (above) is the number of segments that this translator’s Slate Desktop engine successfully matched to the translator’s actual work, i.e. Slate Desktop successfully predicted the translator’s actions. The three segments in this table are the exact MT match segments with the longest length. This translator can expect to experience these kinds Slate Desktop results while translating these kinds of project.

enit (Slate and translator)
(b) Confidential Information may be used exclusively to negotiate and, potentially, sign and perform the Documents, as it is absolutely forbidden to use the Confidential Information for other purposes, and it may for not reason be disclosed to third parties unless the other Party has given prior written consent. To this end, the Parties undertake to take all reasonable precautions when dealing with and managing such Confidential Information.(b) Le Informazioni Confidenziali potranno essere utilizzate esclusivamente ai fini della negoziazione ed eventualmente della stipulazione ed esecuzione dei Documenti, essendo assolutamente vietato utilizzare le Informazioni Confidenziali per raggiungere finalità diverse, e non potranno per alcun motivo ed in nessun modo essere divulgate a terzi, se non con il preventivo consenso scritto dell’altra Parte. A tal fine, le Parti si obbligano ad adottare ogni ragionevole precauzione nel trattare e nel gestire tali Informazioni Confidenziali.
The investment objective of such Sub-Funds is to return a proportion or all of the performance of a pre-defined Third Party Trading Strategy or Index to the Sub-Fund via derivative contracts, as defined in the individual Sub-Fund Supplements. The market risk management for such Sub-Funds is non-discretionary and therefore the risk measurements considered in the management of the assets reflect the extent of the Sub-Funds’ exposure to the underlying Index or Strategy.L’obiettivo di investimento di questi Comparti consiste nel conseguire una percentuale o l’intera performance di una predefinita Strategia di negoziazione o Indice di terzi tramite contratti derivati, come stabilito nelle Note Integrative dei singoli Comparti La gestione del rischio di mercato per tali Comparti non è discrezionale e, pertanto, le valutazioni del rischio considerate nella gestione delle attività riflettono la misura dell’esposizione dei Comparti all’Indice o alla Strategia sottostante.
By mentioning rules of transparency and non-discrimination, the budget law for 2004 has codified a principle that was already underlying the original version of Article 1, section 2, and intended to allay the risk that the sale take place at a price that is below market price, favoring the purchaser from a competitive point of view, in violation of the law on the matter of State aid.Con il richiamo a regole di trasparenza e non discriminazione, la legge finanziaria 2004 ha codificato un principio già sotteso alla versione originaria dell’art. 1, comma 2, ed inteso a scongiurare il rischio che la cessione abbia luogo ad un prezzo inferiore a quello di mercato, favorendo l’acquirente dal punto di vista concorrenziale in violazione della normativa in materia di aiuti di Stato.