This English-to-Italian patents translator uses a Slate Desktop personalized SMT that’s 37.2% 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.
|estimated corpus size||1,000,000|
|segments per representative set||2,396|
|words per source segment||16|
|words per target segment||18|
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.
|words per MT segment||17||18|
|exact MT match (count)||138||978|
|exact MT match (percent)||5.8%||40.8%|
|words per exact MT match (count)||7||14|
|filtered BLEU score (no exact MT matches)||39.07||65.28|
|segments requiring edit (count)||2,258||1,418|
|character edits per segment||35||30|
|total character edits||79,030||42,540|
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.
|en||it (Google and translator)|
|Button that saves the configured data and sends the corrective actions to the users involved in the flow.||Pulsante che salva i dati configurati e invia le azioni correttive agli utenti coinvolti nel flusso.|
|Use this procedure to schedule system data backups to a backup tape or USB flash drive.||Utilizzare questa procedura per pianificare i backup dei dati di sistema su un nastro di backup o un’unità flash USB.|
|Audit Trail provides information about the activity that has occurred for this version of this document.||Audit Trail fornisce informazioni sull’attività che si è verificata per questa versione di questo documento.|
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.
|en||it (Slate and translator)|
|If the XXXXXX Drain Pump inside your system is oriented with the Drain Hoses at the top of the pump, then use the procedure described on pages 6-40 through 6-44 in the IFU to perform the yearly XXXXXX Drain Pump Tube Replacement.||Se la pompa XXXXXXa di drenaggio all’interno del sistema è orientata con i tubi di drenaggio nella parte superiore della pompa, utilizzare la procedura descritta nella pagine da 6-40 a 6-44 nell’IFU per eseguire la sostituzione annuale del tubo della pompa XXXXXXa di drenaggio.|
|16 to 38°C (60 to 100°F)To reach temperatures above ambient, the centrifuge is dependent on the frictional heat generated inside the chamber during operation.||da 16 a 38 °C (da 60 a 100 °F)Per raggiungere temperature superiori alla temperatura ambiente, la centrifuga dipende dal calore dell’attrito generato all’interno della camera durante l’operazione.|
|A possible interference was tested by adding the substance to whole blood with low galactose concentration, and testing the blood spots for galactose according to CLSI Document EP7-A (8).||Una possibile interferenza è stata valutata aggiungendo la sostanza a sangue intero a bassa concentrazione di galattosio e analizzando le macchie di sangue per il galattosio in conformità al documento CLSI EP7-A (8).|