多语言NLP

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tok = AutoTokenizer.from_pretrained("joeddav/xlm-roberta-large-xnli")
model = AutoModelForSequenceClassification.from_pretrained("joeddav/xlm-roberta-large-xnli")


def classify(text, candidate_labels, hypothesis_template="This text is about {}."):
    scores = {}
    for label in candidate_labels:
        hypothesis = hypothesis_template.format(label)
        inputs = tok(text, hypothesis, return_tensors="pt", truncation=True)
        with torch.no_grad():
            logits = model(**inputs).logits[0]
        entail_score = torch.softmax(logits, dim=-1)[2].item()
        scores[label] = entail_score
    return dict(sorted(scores.items(), key=lambda x: -x[1]))


print(classify("I love this product!", ["positive", "negative", "neutral"]))
print(classify("मुझे यह उत्पाद पसंद है!", ["positive", "negative", "neutral"]))
print(classify("J'adore ce produit !", ["positive", "negative", "neutral"]))

from sentence_transformers import SentenceTransformer
import numpy as np

model = SentenceTransformer("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")

pairs = [
    ("The cat is sleeping.", "Le chat dort."),
    ("The cat is sleeping.", "El gato está durmiendo."),
    ("The cat is sleeping.", "Die Katze schläft."),
    ("The cat is sleeping.", "The dog is barking."),
]

for eng, other in pairs:
    emb_eng = model.encode([eng], normalize_embeddings=True)[0]
    emb_other = model.encode([other], normalize_embeddings=True)[0]
    sim = float(np.dot(emb_eng, emb_other))
    print(f"  {eng!r} <-> {other!r}: cos={sim:.3f}")

from transformers import TrainingArguments, Trainer
from datasets import Dataset


def few_shot_finetune(base_model, base_tokenizer, examples):
    ds = Dataset.from_list(examples)

    def tokenize_fn(ex):
        out = base_tokenizer(ex["text"], truncation=True, max_length=128)
        out["labels"] = ex["label"]
        return out

    ds = ds.map(tokenize_fn)
    args = TrainingArguments(
        output_dir="out",
        per_device_train_batch_size=8,
        num_train_epochs=5,
        learning_rate=2e-5,
        save_strategy="no",
    )
    trainer = Trainer(model=base_model, args=args, train_dataset=ds)
    trainer.train()
    return base_model

---
name: multilingual-picker
description: Pick source language, target model, and evaluation plan for a multilingual NLP task.
version: 1.0.0
phase: 5
lesson: 18
tags: [nlp, multilingual, cross-lingual]
---

Given requirements (target languages, task type, available labeled data per language), output:

1. Source language for fine-tuning. Default English; check LANGRANK or qWALS if target language has a typologically close high-resource language.
2. Base model. XLM-R (classification), mT5 (generation), NLLB (translation), Aya-23 (generative LLM).
3. Few-shot budget. Start with 100-500 target-language examples if available. Zero-shot only if labeling is infeasible.
4. Evaluation plan. Per-language accuracy (not aggregate), cross-lingual consistency, entity-level F1 on non-Latin scripts.

Refuse to ship a multilingual model without per-language evaluation — aggregate metrics hide long-tail failures. Flag scripts with low tokenization coverage (Amharic, Tigrinya, many African languages) as needing a model with byte-fallback (SentencePiece with byte_fallback=True, or byte-level tokenizer like GPT-2).