Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| Koreferensupplösning× | Frågesvarande (QA)× | |
|---|---|---|
| Ämnesområde | Textutvinning | Textutvinning |
| Familj | Process / pipeline | Process / pipeline |
| Ursprungsår≠ | 1978 | — |
| Upphovsperson≠ | Hobbs (1978); Lee et al. (2017, neural end-to-end) | — |
| Typ≠ | NLP information-extraction task | NLP text-comprehension task |
| Ursprungskälla≠ | Lee, K. et al. (2017). End-to-end Neural Coreference Resolution. EMNLP. link ↗ | Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP. DOI ↗ |
| Alias | coreference, anaphora resolution, Eşgönderim Çözümleme (Coreference Resolution) | QA, machine reading comprehension, Soru Cevaplama (Question Answering) |
| Närliggande | 4 | 4 |
| Sammanfattning≠ | Coreference resolution is a natural-language-processing task that detects when different expressions in a text refer to the same entity — for example a name, a later pronoun, and a descriptive phrase all pointing at one person. Rooted in early linguistic work by Hobbs (1978) and advanced by the end-to-end neural model of Lee et al. (2017), it improves the quality of information extraction and text understanding. | 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. |
| ScholarGateDatamängd ↗ |
|
|