मुख्य सामग्री पर जाएँ

पाठ वर्गीकरण और भावना विश्लेषण

पाठ को पूर्वनिर्धारित लेबल देना

भाषा और ज्ञानप्रारंभिक #05
इनपुटटेक्स्टटेक्स्ट

यह पृष्ठ अंग्रेज़ी में प्रस्तुत है; शीर्षक और सारांश का स्थानीयकरण किया गया है।

यह क्षमता क्या है

Takes a piece of text and outputs its category — sentiment polarity, topic, intent or policy violation. The label set is fixed at training time, so it answers which class rather than what is said. A single text can carry several labels, and the model can also emit a probability distribution over the label set.

तकनीकी रूप से कैसे

Early systems paired bag-of-words with linear classifiers; fine-tuning a pre-trained encoder such as the BERT family later became the standard when labelled data is scarce. A classification head sits on top of the encoder and is trained with cross-entropy. With many labels and few examples, it can be recast as sentence-pair entailment or done zero-shot by prompting a large model.

प्रतिनिधि उत्पाद

5

संबंधित संस्थान

सामान्य उपयोग

  • Sentiment polarity of reviews and public opinion
  • Spam and policy-violation filtering
  • Routing tickets by topic and priority
  • Intent detection to drive dialogue

इसका मूल्यांकन कैसे होता है

F1
Harmonic mean of precision and recall; more trustworthy than accuracy under imbalance
ROC-AUC
Ranking quality, threshold-independent
Confusion matrix
Per-class error direction, to locate systematic bias

सीमाएँ और कठिनाइयाँ

  • Under heavy class imbalance, minority classes are ignored while accuracy still looks high
  • Wording drift outside the training domain degrades predictions
  • Sarcasm, negation and double negation are often flipped, since the literal words point the other way

इसके पीछे की अवधारणाएँ