Als je deze blog hebt gevolgd, weet je dat ik een beetje geobsedeerd ben door machine vertaling.Ik heb geschreven over, gebruik van EasyNMThet bouwen van vertaaldiensten voor achtergronden;, en zelfsEasyNMT verbeteren**Maar ik realiseerde me dat ik het nooit echt heb uitgelegd.
hoe
neurale machine vertaling werkt onder de motorkap.
OPMERKING: Dit is onderdeel van mijn experimenten met AI / een manier om $1000 Calude Code Web credits te besteden.
Wat kunstmatige neurale netwerken zijn en hoe ze leren
Wat "aandacht" betekent in AI (spoiler: het gaat niet over aandacht besteden)
graph LR
A[Source Sentence] --> B[Convert to Numbers]
B --> C[Neural Network Processing]
C --> D[Convert to Words]
D --> E[Translated Sentence]
Hoe werkt de encoder-decoder architectuur?
Maak je geen zorgen als je geen wiskunde persoon bent - ik zal dit zo praktisch en visueel mogelijk houden.
Het kernidee: Vertaling als Number Crunching
Laten we beginnen met de bouwstenen.
graph LR
I1[Input 1] -->|weight: 0.8| N[Neuron]
I2[Input 2] -->|weight: -0.3| N
I3[Input 3] -->|weight: 0.5| N
N --> O[Output]
style N stroke-width:4px
Artificiële Neurale Netwerken: Stichting
public class Neuron
{
private double[] weights;
private double bias;
public double Activate(double[] inputs)
{
// Step 1: Multiply each input by its weight and sum them
double sum = bias;
for (int i = 0; i < inputs.Length; i++)
{
sum += inputs[i] * weights[i];
}
// Step 2: Apply activation function (tanh keeps values between -1 and 1)
return Math.Tanh(sum);
}
}
Voordat we neurale machine vertaling kunnen begrijpen, moeten we kunstmatige neurale netwerken begrijpen.Math.TanhOndanks de mooie naam, zijn ze eigenlijk vrij eenvoudig in hun kern.
Een kunstmatig neuron is een wiskundige functie die:
graph LR
subgraph Input Layer
I1[Input 1]
I2[Input 2]
I3[Input 3]
end
subgraph Hidden Layer 1
H1[Neuron 1]
H2[Neuron 2]
H3[Neuron 3]
H4[Neuron 4]
end
subgraph Hidden Layer 2
H5[Neuron 5]
H6[Neuron 6]
H7[Neuron 7]
end
subgraph Output Layer
O1[Output 1]
O2[Output 2]
end
I1 --> H1 & H2 & H3 & H4
I2 --> H1 & H2 & H3 & H4
I3 --> H1 & H2 & H3 & H4
H1 --> H5 & H6 & H7
H2 --> H5 & H6 & H7
H3 --> H5 & H6 & H7
H4 --> H5 & H6 & H7
H5 --> O1 & O2
H6 --> O1 & O2
H7 --> O1 & O2
Neemt meerdere ingangen
Laten we dit beton maken met wat C# code:
graph TD
A[Start with Random Weights] --> B[Feed in Training Example]
B --> C[Network Makes Prediction]
C --> D{Is Prediction Correct?}
D -->|No| E[Calculate Error]
E --> F[Adjust Weights Slightly]
F --> B
D -->|Yes| G[Try Next Example]
G --> B
style E stroke-width:2px
style F stroke-width:2px
De activeringsfunctie (in dit geval**) is wat neurale netwerken interessant maakt.**Het introduceert niet-lineairheid, waardoor het netwerk complexe patronen kan leren.
Zonder dat, hoeveel neuronen je ook bij elkaar hebt gestapeld, heb je gewoon een mooie lineaire functie.
public class SimpleNeuralNetwork
{
private double learningRate = 0.01;
private Neuron[] neurons;
public void Train(TrainingExample[] examples, int epochs)
{
for (int epoch = 0; epoch < epochs; epoch++)
{
foreach (var example in examples)
{
// Forward pass: make a prediction
double prediction = Predict(example.Input);
// Calculate error
double error = example.ExpectedOutput - prediction;
// Backward pass: adjust weights
// (simplified - real networks use backpropagation)
AdjustWeights(error * learningRate);
}
}
}
}
Van Neuronen naar Netwerken**De magie gebeurt als je duizenden of miljoenen van deze neuronen met elkaar verbindt in lagen:**Elke laag "verfijnt" de weergave van de input, het extraheren van steeds abstracter patronen.
Vroege lagen kunnen detecteren "dit is een werkwoord" of "dit woord is verleden tijd"
Latere lagen combineren deze tot "vertaal dit als een beleefde vraag over het weer van morgen"
// Don't do this!
var wordToNumber = new Dictionary<string, int>
{
{"cat", 1},
{"dog", 2},
{"king", 3},
{"queen", 4},
{"man", 5},
{"woman", 6}
};
Hoe netwerken leren: Het trainingsproces
Het netwerk leert ze van voorbeelden!Dit proces heethellingsdaling
public class WordEmbedding
{
// Each word is represented by a vector of floats
private Dictionary<string, float[]> embeddings;
public float[] GetEmbedding(string word)
{
return embeddings[word]; // e.g., [0.2, -0.5, 0.8, 0.1, ...]
}
// Calculate similarity between two words
public double Similarity(string word1, string word2)
{
var vec1 = GetEmbedding(word1);
var vec2 = GetEmbedding(word2);
// Cosine similarity: how "aligned" are the vectors?
return CosineSimilarity(vec1, vec2);
}
private double CosineSimilarity(float[] a, float[] b)
{
double dot = 0, magA = 0, magB = 0;
for (int i = 0; i < a.Length; i++)
{
dot += a[i] * b[i];
magA += a[i] * a[i];
magB += b[i] * b[i];
}
return dot / (Math.Sqrt(magA) * Math.Sqrt(magB));
}
}
graph TD
subgraph "2D Projection of 300D Space"
King[King<br/>0.8, 0.6]
Queen[Queen<br/>0.75, 0.55]
Man[Man<br/>0.3, 0.2]
Woman[Woman<br/>0.25, 0.15]
Dog[Dog<br/>-0.6, 0.4]
Cat[Cat<br/>-0.65, 0.38]
end
King -.similar.-> Queen
Man -.similar.-> Woman
Dog -.similar.-> Cat
King -.same vector.-> Man
Queen -.same vector.-> Woman
Voor elk verkeerd antwoord komt het netwerk erachter "welke gewichten het meest verantwoordelijk waren voor deze fout?" en tweaks ze een klein beetje.king - man + woman ≈ queen
public float[] AnalogicalReasoning(string a, string b, string c)
{
// king - man + woman = ?
var vecA = GetEmbedding(a); // king
var vecB = GetEmbedding(b); // man
var vecC = GetEmbedding(c); // woman
var result = new float[vecA.Length];
for (int i = 0; i < vecA.Length; i++)
{
result[i] = vecA[i] - vecB[i] + vecC[i];
}
// Find the word closest to this vector
return FindClosestWord(result); // Should return "queen"
}
Hier is een vereenvoudigde versie in C#:
graph LR
A["The cat sat on the mat"] --> B[Train Neural Network]
B --> C["cat → [0.1, 0.5, -0.3, ...]"]
B --> D["sat → [0.2, -0.1, 0.4, ...]"]
B --> E["mat → [0.15, 0.45, -0.25, ...]"]
Echte neurale netwerken gebruiken een meer geavanceerde algoritme genaamd
dat efficiënt berekent hoe gewichten in het hele netwerk aan te passen, maar het principe is hetzelfde: leren van fouten.
graph TD
subgraph English
E1[The]
E2[cat]
E3[sat]
E4[on]
E5[the]
E6[mat]
end
subgraph French
F1[Le]
F2[chat]
F3[s'est assis]
F4[sur]
F5[le]
F6[tapis]
end
E2 -. focus 90% .-> F2
E3 -. focus 70% .-> F3
E4 -. focus 80% .-> F4
E6 -. focus 85% .-> F6
E1 -. focus 30% .-> F1
Woord inbeddingen: Taal veranderen in wiskundeNu hebben we onze eerste grote uitdaging: hoe voeden we woorden in een neuraal netwerk?
Het probleem met One-Hot codering
public class AttentionMechanism
{
// Calculate attention weights for each source word
public double[] CalculateAttention(
float[] currentTargetState, // Where we are in translation
float[][] sourceWordStates) // All source words
{
int sourceLength = sourceWordStates.Length;
double[] scores = new double[sourceLength];
// Step 1: Calculate relevance scores
for (int i = 0; i < sourceLength; i++)
{
scores[i] = DotProduct(currentTargetState, sourceWordStates[i]);
}
// Step 2: Convert to probabilities (softmax)
return Softmax(scores);
}
public float[] ApplyAttention(
double[] attentionWeights,
float[][] sourceWordStates)
{
// Create weighted average of source words
int dim = sourceWordStates[0].Length;
float[] result = new float[dim];
for (int i = 0; i < sourceWordStates.Length; i++)
{
for (int j = 0; j < dim; j++)
{
result[j] += (float)(attentionWeights[i] * sourceWordStates[i][j]);
}
}
return result;
}
private double[] Softmax(double[] scores)
{
double[] result = new double[scores.Length];
double sum = 0;
for (int i = 0; i < scores.Length; i++)
{
result[i] = Math.Exp(scores[i]);
sum += result[i];
}
for (int i = 0; i < scores.Length; i++)
{
result[i] /= sum;
}
return result;
}
private double DotProduct(float[] a, float[] b)
{
double sum = 0;
for (int i = 0; i < a.Length; i++)
{
sum += a[i] * b[i];
}
return sum;
}
}
De naïeve benadering is "one-hot encoding" - geef elk woord een uniek getal:
vector
graph TD
subgraph "English (Source)"
E1[The]
E2[agreement]
E3[on]
E4[the]
E5[European]
E6[Economic]
E7[Area]
end
subgraph "German (Target)"
G1[Das]
G2[Abkommen]
G3[über]
G4[den]
G5[Europäischen]
end
E1 -->|0.8| G1
E2 -->|0.9| G2
E3 -->|0.6| G3
E4 -->|0.3| G3
E5 -->|0.85| G5
E6 -->|0.7| G5
van getallen, meestal 300-1000 dimensies.
Dit is wat maakt inbedden magisch - ze vastleggen semantische relaties:**Het beroemde voorbeeld:**Hoe worden inbeddingen geleerd?
graph LR
subgraph "Self-Attention for 'bank'"
B[bank]
R[river]
W[water]
F[fish]
end
B -.high attention.-> R
B -.high attention.-> W
B -.medium attention.-> F
Inbeddingen worden geleerd door een neuraal netwerk te trainen op een eenvoudige taak: "voorspel de omliggende woorden."
Na training over miljarden zinnen, worden woorden die in vergelijkbare contexten verschijnen met soortgelijke inbeddingen. "Cat" en "hond" beide verschijnen in de buurt van "pet," "feed" en "schattig," zodat hun inbeddingen dicht bij elkaar eindigen.Attentie: de spelwisselaarHier is een kritisch inzicht: bij het vertalen van "De kat zat op de mat" naar het Frans, verschillende bron woorden belangrijk voor verschillende doel woorden:
graph LR
subgraph Encoder
E1[Word Embeddings] --> E2[Self-Attention Layer 1]
E2 --> E3[Self-Attention Layer 2]
E3 --> E4[Self-Attention Layer N]
E4 --> E5[Contextual Representations]
end
subgraph Decoder
D1[Previous Translations] --> D2[Self-Attention]
D2 --> D3[Cross-Attention to Encoder]
D3 --> D4[Feed Forward]
D4 --> D5[Next Word Prediction]
end
E5 -.provides context.-> D3
is een mechanisme waarmee het netwerk "focus" op verschillende delen van de invoer bij het genereren van elk uitvoerwoord.
public class TransformerEncoder
{
private WordEmbedding wordEmbedding;
private SelfAttentionLayer[] layers;
public float[][] Encode(string[] sourceWords)
{
// Step 1: Convert words to embeddings
float[][] embeddings = sourceWords
.Select(w => wordEmbedding.GetEmbedding(w))
.ToArray();
// Step 2: Add positional encoding (so network knows word order)
float[][] withPositions = AddPositionalEncoding(embeddings);
// Step 3: Apply multiple self-attention layers
float[][] representations = withPositions;
foreach (var layer in layers)
{
representations = layer.Forward(representations);
}
return representations; // Contextual representations for each word
}
private float[][] AddPositionalEncoding(float[][] embeddings)
{
// Add position-specific patterns so network knows word order
// (transformers don't naturally understand sequence order)
int sequenceLength = embeddings.Length;
int embeddingDim = embeddings[0].Length;
for (int pos = 0; pos < sequenceLength; pos++)
{
for (int i = 0; i < embeddingDim; i++)
{
double angle = pos / Math.Pow(10000, (2.0 * i) / embeddingDim);
// Use sine for even dimensions, cosine for odd
embeddings[pos][i] += (float)(i % 2 == 0 ? Math.Sin(angle) : Math.Cos(angle));
}
}
return embeddings;
}
}
Hoe Attentie werkt
Converteert scores naar waarschijnlijkheden (ze sommen op 1)
public class TransformerDecoder
{
private WordEmbedding targetEmbedding;
private SelfAttentionLayer[] selfAttentionLayers;
private CrossAttentionLayer[] crossAttentionLayers;
private FeedForwardLayer[] feedForwardLayers;
public string[] Decode(float[][] encodedSource, int maxLength)
{
List<string> translation = new List<string>();
translation.Add("<START>"); // Special token to begin
while (translation.Count < maxLength)
{
// Get next word
string nextWord = GenerateNextWord(encodedSource, translation.ToArray());
if (nextWord == "<END>") break; // Stop token
translation.Add(nextWord);
}
return translation.Skip(1).ToArray(); // Remove <START> token
}
private string GenerateNextWord(float[][] encodedSource, string[] partialTranslation)
{
// Step 1: Embed the partial translation
float[][] targetEmbeddings = partialTranslation
.Select(w => targetEmbedding.GetEmbedding(w))
.ToArray();
// Step 2: Self-attention on target words
float[][] selfAttended = ApplySelfAttention(targetEmbeddings);
// Step 3: Cross-attention to source (this is where translation happens!)
float[][] crossAttended = ApplyCrossAttention(selfAttended, encodedSource);
// Step 4: Feed forward
float[] finalState = ApplyFeedForward(crossAttended[^1]); // Last position
// Step 5: Predict next word
return PredictWord(finalState);
}
private string PredictWord(float[] state)
{
// Convert state to probability distribution over all possible words
Dictionary<string, double> wordProbabilities = CalculateWordProbabilities(state);
// Return most likely word (or sample from distribution)
return wordProbabilities.OrderByDescending(kv => kv.Value).First().Key;
}
}
Maakt een gewogen gemiddelde van bronwoorden op basis van deze waarschijnlijkheden
sequenceDiagram
participant Input as Source Sentence
participant Encoder
participant Decoder
participant Output as Translation
Input->>Encoder: "The cat sat"
Encoder->>Encoder: Build representations
Encoder->>Decoder: Encoded states
Decoder->>Decoder: Generate [START]
Decoder->>Output: Emit START token
Decoder->>Decoder: Attend to "The" → Generate "Le"
Decoder->>Output: "Le"
Decoder->>Decoder: Attend to "cat" → Generate "chat"
Decoder->>Output: "chat"
Decoder->>Decoder: Attend to "sat" → Generate "s'est assis"
Decoder->>Output: "s'est assis"
Decoder->>Decoder: Generate [END]
Output->>Output: "Le chat s'est assis"
Bij de vertaling van "De overeenkomst over de Europese Economische Ruimte werd in augustus 1992" naar het Duits ondertekend, ziet de aandacht er als volgt uit:
public class TranslationTrainer
{
private TransformerEncoder encoder;
private TransformerDecoder decoder;
private double learningRate = 0.0001;
public void Train(ParallelCorpus corpus, int epochs)
{
foreach (var epoch in Enumerable.Range(0, epochs))
{
double totalLoss = 0;
int batchCount = 0;
foreach (var batch in corpus.GetBatches(batchSize: 32))
{
// Forward pass
var predictions = new List<string[]>();
var losses = new List<double>();
foreach (var pair in batch)
{
// Encode source
var encoded = encoder.Encode(pair.Source);
// Try to decode target
var predicted = decoder.Decode(encoded, pair.Target.Length);
// Calculate loss (how different is prediction from target?)
double loss = CalculateLoss(predicted, pair.Target);
losses.Add(loss);
}
// Backward pass: adjust weights
double avgLoss = losses.Average();
UpdateWeights(avgLoss);
totalLoss += avgLoss;
batchCount++;
}
Console.WriteLine($"Epoch {epoch}: Average Loss = {totalLoss / batchCount}");
}
}
private double CalculateLoss(string[] predicted, string[] target)
{
// Cross-entropy loss: how far off were our word predictions?
double loss = 0;
for (int i = 0; i < Math.Min(predicted.Length, target.Length); i++)
{
if (predicted[i] != target[i])
{
loss += 1.0; // Simplified - real loss is more nuanced
}
}
return loss / target.Length;
}
private void UpdateWeights(double loss)
{
// Backpropagation: adjust all weights in encoder and decoder
// to reduce the loss (simplified here)
// Real implementation uses automatic differentiation
}
}
De Encoder-Decoder Architectuur
graph TD
A[10M Sentence Pairs] --> B[Initial Random Weights]
B --> C[Epoch 1: Loss = 5.2]
C --> D[Epoch 2: Loss = 3.8]
D --> E[Epoch 3: Loss = 2.1]
E --> F[Epoch 10: Loss = 0.8]
F --> G[Epoch 20: Loss = 0.3]
G --> H[Trained Model!]
style A stroke-width:2px
style H stroke-width:4px
Nu kunnen we het allemaal in elkaar zetten!
Zijn positie in de zin (van positionele codering)
graph TD
subgraph "1. Encoding"
A1[The] --> E1[emb: 0.2, -0.1, ...]
A2[cat] --> E2[emb: 0.5, 0.3, ...]
A3[sat] --> E3[emb: -0.1, 0.4, ...]
A4[on] --> E4[emb: 0.1, -0.2, ...]
A5[the] --> E5[emb: 0.2, -0.1, ...]
A6[mat] --> E6[emb: 0.4, 0.2, ...]
end
subgraph "2. Self-Attention in Encoder"
E1 & E2 & E3 & E4 & E5 & E6 --> SA[Self-Attention]
SA --> C1[ctx: 0.3, 0.1, ...]
SA --> C2[ctx: 0.6, 0.4, ...]
SA --> C3[ctx: -0.2, 0.5, ...]
end
subgraph "3. Decoding"
D1[START] --> G1[Le]
C2 -.attend.-> G1
G1 --> G2[chat]
C2 -.attend.-> G2
G2 --> G3[s'est assis]
C3 -.attend.-> G3
end
De decoder: het genereren van de vertaling
var theEmbedding = encoder.GetEmbedding("The");
// [0.2, -0.1, 0.3, 0.05, ..., 0.1] (300 dimensions)
De decoder genereert de vertaling één woord tegelijk:
var catEmbedding = encoder.GetEmbedding("cat");
// [0.5, 0.3, -0.2, 0.4, ..., 0.15] (300 dimensions)
Het volledige vertaalproces:
// "cat" attends to other words
var catAttention = attention.CalculateAttention(catEmbedding, allWordEmbeddings);
// [0.1, 0.3, 0.2, 0.05, 0.1, 0.25]
// High attention to "sat" (0.3) and "mat" (0.25)
var catContextual = attention.ApplyAttention(catAttention, allWordEmbeddings);
// Weighted average incorporating context
Opleiding van een vertaalmodel
var decoderState = decoder.InitialState();
Het trainen van een vertaalmodel vereist drie dingen:
// Attend to source
var sourceAttention = crossAttention.Calculate(decoderState, encodedSource);
// [0.8, 0.05, 0.05, 0.02, 0.05, 0.03]
// Strong focus on "The" (0.8)
var nextWordProbs = decoder.PredictNextWord(decoderState, sourceAttention);
// {"Le": 0.85, "La": 0.08, "Les": 0.04, ...}
var firstWord = "Le";
Parallelle corpus
decoderState = decoder.UpdateState(decoderState, "Le");
var sourceAttention = crossAttention.Calculate(decoderState, encodedSource);
// [0.05, 0.9, 0.02, 0.01, 0.01, 0.01]
// Strong focus on "cat" (0.9)
var nextWordProbs = decoder.PredictNextWord(decoderState, sourceAttention);
// {"chat": 0.92, "chien": 0.03, ...}
var secondWord = "chat";
: Miljoenen zinsparen in beide talen
Final translation: "Le chat s'est assis sur le tapis"
Hoe "fout" was onze voorspelling?
graph LR
subgraph "Old: Recurrent Neural Networks"
R1[Word 1] --> R2[Word 2]
R2 --> R3[Word 3]
R3 --> R4[Word 4]
end
subgraph "New: Transformers"
T1[Word 1] -.attend.-> T2[Word 2]
T1 -.attend.-> T3[Word 3]
T1 -.attend.-> T4[Word 4]
T2 -.attend.-> T3
T2 -.attend.-> T4
T3 -.attend.-> T4
end
Opleidingstijd
Modelgrootte
public class TranslationService
{
private readonly HttpClient _httpClient;
private readonly string _nmtServiceUrl;
public TranslationService(HttpClient httpClient, IConfiguration config)
{
_httpClient = httpClient;
_nmtServiceUrl = config["NMT:ServiceUrl"];
}
public async Task<TranslationResult> TranslateAsync(
string text,
string sourceLang,
string targetLang)
{
var request = new TranslationRequest
{
Text = new[] { text },
SourceLang = sourceLang,
TargetLang = targetLang
};
var response = await _httpClient.PostAsJsonAsync(
$"{_nmtServiceUrl}/translate",
request);
response.EnsureSuccessStatusCode();
var result = await response.Content
.ReadFromJsonAsync<TranslationResponse>();
return new TranslationResult
{
Original = text,
Translated = result.Translated[0],
SourceLanguage = sourceLang,
TargetLanguage = targetLang,
TranslationTime = result.TranslationTime
};
}
}
public class TranslationRequest
{
[JsonPropertyName("text")]
public string[] Text { get; set; }
[JsonPropertyName("source_lang")]
public string SourceLang { get; set; }
[JsonPropertyName("target_lang")]
public string TargetLang { get; set; }
}
public class TranslationResponse
{
[JsonPropertyName("translated")]
public string[] Translated { get; set; }
[JsonPropertyName("translation_time")]
public double TranslationTime { get; set; }
}
: 100M tot 1B+ parameters (gewichten)
// In your controller or service
public class BlogPostController : ControllerBase
{
private readonly TranslationService _translator;
public async Task<IActionResult> TranslatePost(int postId, string targetLang)
{
var post = await _blogService.GetPostAsync(postId);
var translatedTitle = await _translator.TranslateAsync(
post.Title,
"en",
targetLang);
var translatedContent = await _translator.TranslateAsync(
post.Content,
"en",
targetLang);
return Ok(new
{
Title = translatedTitle.Translated,
Content = translatedContent.Translated,
OriginalLanguage = "en",
TargetLanguage = targetLang
});
}
}
Stap-voor-stap proces:
public async Task<string> TranslateLongText(string longText, string targetLang)
{
const int maxChunkSize = 500; // characters
// Split on paragraph boundaries
var paragraphs = longText.Split(new[] { "\n\n", "\r\n\r\n" },
StringSplitOptions.RemoveEmptyEntries);
var translatedParagraphs = new List<string>();
foreach (var paragraph in paragraphs)
{
if (paragraph.Length <= maxChunkSize)
{
var result = await _translator.TranslateAsync(paragraph, "en", targetLang);
translatedParagraphs.Add(result.Translated);
}
else
{
// Split long paragraph into sentences
var sentences = SplitIntoSentences(paragraph);
var translatedSentences = new List<string>();
foreach (var sentence in sentences)
{
var result = await _translator.TranslateAsync(sentence, "en", targetLang);
translatedSentences.Add(result.Translated);
}
translatedParagraphs.Add(string.Join(" ", translatedSentences));
}
}
return string.Join("\n\n", translatedParagraphs);
}
Stap 2: Codeer "kat"
public async Task<string> TranslateMarkdown(string markdown, string targetLang)
{
// Extract text from markdown while preserving structure
var doc = Markdig.Markdown.Parse(markdown);
var textSegments = new List<(string text, int position)>();
// Walk the AST and extract translatable text
foreach (var node in doc.Descendants())
{
if (node is LiteralInline literal)
{
var text = literal.Content.ToString();
if (!string.IsNullOrWhiteSpace(text) && !IsImagePath(text))
{
textSegments.Add((text, literal.Span.Start));
}
}
}
// Translate all segments
var translations = await Task.WhenAll(
textSegments.Select(async seg => new
{
seg.position,
translated = (await _translator.TranslateAsync(seg.text, "en", targetLang)).Translated
}));
// Reconstruct markdown with translations
var result = markdown;
foreach (var translation in translations.OrderByDescending(t => t.position))
{
result = result.Remove(translation.position, textSegments
.First(s => s.position == translation.position).text.Length)
.Insert(translation.position, translation.translated);
}
return result;
}
Stap 4: Decoder begint met
public async Task<Dictionary<string, string>> TranslateBatch(
IEnumerable<string> texts,
string targetLang)
{
const int batchSize = 32;
var results = new Dictionary<string, string>();
foreach (var batch in texts.Chunk(batchSize))
{
var request = new TranslationRequest
{
Text = batch.ToArray(),
SourceLang = "en",
TargetLang = targetLang
};
var response = await _httpClient.PostAsJsonAsync(
$"{_nmtServiceUrl}/translate",
request);
var result = await response.Content
.ReadFromJsonAsync<TranslationResponse>();
for (int i = 0; i < batch.Length; i++)
{
results[batch[i]] = result.Translated[i];
}
}
return results;
}
Stap 6: "chat" genereren
graph TD
A[Translation Request] --> B{Model Size}
B -->|Small 100M params| C[Fast: 50-100ms]
B -->|Medium 500M params| D[Medium: 200-500ms]
B -->|Large 1B+ params| E[Slow: 1-3 seconds]
A --> F{Hardware}
F -->|CPU| G[Slow: 2-5x slower]
F -->|GPU| H[Fast: Baseline]
F -->|TPU/Special AI chips| I[Very Fast: 2-3x faster]
style C stroke-width:2px
style E stroke-width:2px
Stap 7: Doorgaan tot
Schaalbaarheid: Meer gegevens + groter model = betere resultaten (tot een punt)
**Recurrente netwerken verwerken achtereenvolgens (langzaam!), terwijl transformatoren alle woorden tegelijk verwerken (snel!).**Gebruik van NMT in C#: Een praktisch voorbeeld
Gebruik:
Eén zin tegelijk vertalen is traag.
Batch ze!
(1B+ params): 1-3 seconden
Now when you hit "translate" on your blog posts, you'll know exactly what's happening under the hood! 🚀
: GPU is 2-10x sneller voor NMT
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.