Menjawab pertanyaan

Natural Language Processing (NLP) in Python

Fouad Trad

Machine Learning Engineer

QA ekstraktif

Jawaban disalin langsung dari teks

Gambar menampilkan konteks "Perpustakaan tutup pukul 18.00 pada hari kerja"

Gambar menampilkan jawaban ekstraktif: "18.00"

QA abstraktif

Model menghasilkan jawaban alami

Gambar menampilkan pertanyaan: "Kapan perpustakaan tutup pada hari kerja?"

Gambar menampilkan jawaban abstraktif: "Tutup pukul 18.00"

QA ekstraktif

Berguna untuk:
- Mesin pencari
- Sistem temu kembali dokumen
- Aplikasi pemahaman bacaan
Lebih akurat, lebih kecil risiko salah

QA abstraktif

Berguna untuk:
- Agen percakapan
- Asisten virtual
- Bot dukungan pelanggan
Dapat menimbulkan kesalahan

QA ekstraktif

from transformers import pipeline

qa_pipeline = pipeline(task="question-answering", 
                       model="distilbert/distilbert-base-cased-distilled-squad")

context = """The Amazon rainforest is the largest tropical rainforest in the world, 
covering parts of Brazil, Peru, and Colombia."""

question = "Which countries does the Amazon rainforest cover?"

qa_answer = qa_pipeline(question=question, context=context)
print(qa_answer)

{'score': 0.9242347478866577,

 'start': 90, 'end': 116,

 'answer': 'Brazil, Peru, and Colombia'}

QA abstraktif

from transformers import pipeline
qa_pipeline = pipeline(task="text2text-generation",
                       model="fangyuan/hotpotqa_abstractive")

context = """The Amazon rainforest is the largest tropical rainforest in the world, 
covering parts of Brazil, Peru, and Colombia."""
question = "Which countries does the Amazon rainforest cover?"

input_text = f"question: {question}  context: {context}"

result = qa_pipeline(input_text)

print(result)

[{'generated_text': 'The Amazon rainforest covers parts of Brazil, Peru, and Colombia.'}]

Ayo berlatih!

Natural Language Processing (NLP) in Python