Open-Domain Question Answering (ODQA): differenze tra le versioni
(Creata pagina con "Tratto da "https://lilianweng.github.io/posts/2020-10-29-odqa/"<blockquote>'''Open-domain Question Answering (ODQA)''' is a type of language tasks, asking a model to produce answers to factoid questions in natural language. The true answer is objective, so it is simple to evaluate model performance. For example, <code>Question: What did Albert Einstein win the Nobel Prize for? Answer: The law of the photoelectric effect.</code> The “open-domain” part refers to the...") |
Nessun oggetto della modifica |
||
| Riga 3: | Riga 3: | ||
Answer: The law of the photoelectric effect.</code> | Answer: The law of the photoelectric effect.</code> | ||
The “open-domain” part refers to the lack of the relevant context for any arbitrarily asked factual question. In the above case, the model only takes as the input the question but no article about “why Einstein didn’t win a Nobel Prize for the theory of relativity” is provided, where the term “the law of the photoelectric effect” is likely mentioned. In the case when both the question and the context are provided, the task is known as '''[[Reading comprehension (RC]])'''.</blockquote> | The “open-domain” part refers to the lack of the relevant context for any arbitrarily asked factual question. In the above case, the model only takes as the input the question but no article about “why Einstein didn’t win a Nobel Prize for the theory of relativity” is provided, where the term “the law of the photoelectric effect” is likely mentioned. In the case when both the question and the context are provided, the task is known as '''[[Reading comprehension (RC]])'''.</blockquote> | ||
[[Categoria:Task]] | |||
Versione attuale delle 14:55, 25 nov 2024
Tratto da "https://lilianweng.github.io/posts/2020-10-29-odqa/"
Open-domain Question Answering (ODQA) is a type of language tasks, asking a model to produce answers to factoid questions in natural language. The true answer is objective, so it is simple to evaluate model performance. For example,
Question: What did Albert Einstein win the Nobel Prize for? Answer: The law of the photoelectric effect.The “open-domain” part refers to the lack of the relevant context for any arbitrarily asked factual question. In the above case, the model only takes as the input the question but no article about “why Einstein didn’t win a Nobel Prize for the theory of relativity” is provided, where the term “the law of the photoelectric effect” is likely mentioned. In the case when both the question and the context are provided, the task is known as Reading comprehension (RC).