Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Otkrivanje događaja× | Odgovaranjem na pitanja (QA)× | |
|---|---|---|
| Područje | Rudarenje teksta | Rudarenje teksta |
| Obitelj | Process / pipeline | Process / pipeline |
| Godina nastanka | — | — |
| Tvorac | — | — |
| Vrsta≠ | NLP information-extraction task | NLP text-comprehension task |
| Temeljni izvor≠ | Doddington, G. et al. (2004). The Automatic Content Extraction (ACE) Program — Tasks, Data, and Evaluation. LREC. link ↗ | Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP. DOI ↗ |
| Drugi nazivi≠ | event extraction, Olay Tespiti (Event Detection) | QA, machine reading comprehension, Soru Cevaplama (Question Answering) |
| Srodne | 4 | 4 |
| Sažetak≠ | Event detection is a natural-language-processing information-extraction task that finds events, historical developments, and action expressions in text and classifies them by type. It grew out of the Automatic Content Extraction (ACE) program described by Doddington et al. (2004) and is widely used in news analysis and historical research. | Question answering is a natural-language-processing task that automatically answers natural-language questions grounded in a given context passage, using either extractive or generative approaches. The task was crystallised by the SQuAD benchmark of Rajpurkar et al. (2016), and later models such as XLNet (Yang et al., 2019) pushed reading-comprehension accuracy higher. |
| ScholarGateSkup podataka ↗ |
|
|