The authors show several relation extraction methods. Which of these are preferable over others and why? It seems like what makes the difference is the amount of data we have and we are able to process, rather than any substantial differences between the methods. Are there any reasons for which to prefer, for example, unsupervised relation extraction over distant supervision?
The authors show several relation extraction methods. Which of these are preferable over others and why? It seems like what makes the difference is the amount of data we have and we are able to process, rather than any substantial differences between the methods. Are there any reasons for which to prefer, for example, unsupervised relation extraction over distant supervision?