Uporedite metode
Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.
| Segmentacija teksta× | N-gram jezički model× | |
|---|---|---|
| Oblast | Rudarenje teksta | Rudarenje teksta |
| Porodica | Process / pipeline | Process / pipeline |
| Godina nastanka≠ | 1997 | — |
| Tvorac≠ | Marti A. Hearst (TextTiling) | — |
| Tip≠ | NLP document-structure / topic-boundary detection | Statistical language model |
| Temeljni izvor≠ | Hearst, M.A. (1997). TextTiling: Segmenting Text into Multi-Paragraph Subtopic Passages. Computational Linguistics, 23(1), 33-64. link ↗ | Jurafsky, D. & Martin, J.H. (2023). Speech and Language Processing, 3rd ed. link ↗ |
| Drugi nazivi≠ | topic segmentation, discourse segmentation, linear text segmentation, Metin Bölümleme (Text Segmentation) | n-gram model, statistical language model, N-gram Dil Modeli |
| Srodne | 4 | 4 |
| Sažetak≠ | Text segmentation divides a long document into meaningful sections (segments) along topic or discourse boundaries. Introduced for subtopic passages by Marti A. Hearst's TextTiling (1997), it supports document-structure analysis and the detection of topic transitions in continuous text. | An n-gram language model is a statistical model that predicts the probability of the next word by looking only at the previous n−1 words. Described in detail by Jurafsky and Martin (Speech and Language Processing), it provides foundational infrastructure for text generation, spelling correction, and speech recognition. |
| ScholarGateSkup podataka ↗ |
|
|