مقایسهٔ روشها
روشهای انتخابی خود را کنار هم مرور کنید؛ ردیفهای متفاوت برجسته شدهاند.
| برچسبگذاری نقش معنایی (SRL)× | پاسخگویی به پرسش (QA)× | |
|---|---|---|
| حوزه | متنکاوی | متنکاوی |
| خانواده | Process / pipeline | Process / pipeline |
| سال پیدایش≠ | 2002 | — |
| پدیدآور≠ | Daniel Gildea & Daniel Jurafsky | — |
| نوع≠ | NLP shallow semantic parsing task | NLP text-comprehension task |
| منبع بنیادین≠ | Gildea, D. & Jurafsky, D. (2002). Automatic Labeling of Semantic Roles. Computational Linguistics, 28(3), 245-288. DOI ↗ | Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP. DOI ↗ |
| نامهای دیگر | SRL, shallow semantic parsing, Anlamsal Rol Etiketleme (SRL) | QA, machine reading comprehension, Soru Cevaplama (Question Answering) |
| مرتبط≠ | 3 | 4 |
| خلاصه≠ | Semantic role labeling, introduced by Gildea and Jurafsky in 2002, is a natural-language-processing task that assigns semantic roles — who did what to whom, where, when, and how — to the components around a verb (predicate) in a sentence. It turns plain text into structured predicate-argument representations and is a foundational tool for event extraction. | 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. |
| ScholarGateمجموعهداده ↗ |
|
|