Idanwo ti o sopọ mọ itọsọna · Rọrun Ipele

Idanwo Isọsọ ọrọ

Test text label assignment, multi-label tasks, imbalance, recall, task-specific zero-shot use, embeddings, precision arithmetic, and output scores.

Jẹmọ itọsọna awọn ọnaỌrọ Isọri
Ibeere 1 ti 8

Bawo ni olupilẹṣẹ ọrọ ṣe ilana iṣelọpọ fun iwe titẹ sii?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Bawo ni olupilẹṣẹ ọrọ ṣe ilana iṣelọpọ fun iwe titẹ sii?
    • By necessarily translating it into another language
    • By assigning one or more predefined category labels
    • By generating only a new unrelated paragraph
    • By changing its compressed file format
  2. Oju iṣẹlẹ wo ni apẹẹrẹ ti iyasọtọ aami-ọpọlọpọ?
    • Siṣamisi imeeli bi àwúrúju tabi kii ṣe àwúrúju
    • Gbigbe tikẹti kan si ẹka kan pato
    • Yiyan kan nikan star Rating
    • Ifi aami si nkan kan pẹlu mejeeji 'oselu' ati 'aje' ni ẹẹkan
  3. Lori iwe data ọrọ ti o jẹ gaba lori nipasẹ kilasi kan, kini deede apapọ giga le fi pamọ?
    • An inability to calculate any metric
    • Proof that recall equals one for every category
    • Failure to identify cases of a rare class
    • A guarantee that every minority example is correct
  4. Kí ni ìwọn ÌRÁNTÍ ni a classification iṣẹ-ṣiṣe?
    • Bawo ni ọpọlọpọ awọn ọran gidi ti eto naa mu ni aṣeyọri
    • Melo ni awọn ohun kan ti a fi ami si jẹ deede
    • Bawo ni iyara awoṣe nṣiṣẹ
    • Bawo ni awoṣe ṣe tobi to
  5. Ninu isọdi-ọrọ ọrọ-shot odo-iṣẹ-ṣiṣe kan pato, kini ko si fun iṣẹ-ṣiṣe isọdi tuntun?
    • All model pretraining of any kind
    • Every description of the candidate categories
    • The ability to use any learned representation
    • Labeled training examples for that task
  6. How can learned text embeddings contribute to a classification pipeline?
    • They guarantee perfect predictions on every new domain
    • They provide numerical features used to compute label scores
    • They delete every grammatical distinction by definition
    • They replace all label definitions with filenames
  7. A stated text-classification evaluation has six true positives and two false positives. What is precision for the designated positive class?
    • 75 percent
    • 25 percent
    • 100 percent
    • Six percent
  8. Which output-score design permits several text labels to score highly at once rather than requiring scores to sum to one?
    • A single softmax over mutually exclusive classes
    • A rule requiring exactly one positive label
    • A separate sigmoid output for each label
    • A filename-only representation without label scores