Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
courses:rg:natural-logic-for-textual-inference [2011/05/03 01:49] gutierrez |
courses:rg:natural-logic-for-textual-inference [2011/05/03 09:41] popel typos |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ====== Natural Logic for Textual Inference ====== | ||
+ | **Bill MacCartney, Christopher D. Manning (2007)** | ||
+ | |||
===== Introduction ===== | ===== Introduction ===== | ||
- | This paper deals with “**natural logic**” which is logical inference that operates over natural language. Usually the approaches for natural language inference are whether | + | This paper deals with “**natural logic**” which is logical inference that operates over natural language. Usually the approaches for natural language inference are either |
- | quantifiers, | + | |
- | One key concept in the theory of natural logic is “monoticity” in which, instead of using quantifiers, | + | One key concept in the theory of natural logic is “monotonicity” in which, instead of using quantifiers, |
- | The developed system is called **NatLog** and has an architecture with three main stages: Linguistic preprocessing (parse input sentences, monotonicity marking) Alignment (alignment between the premise and the hypothesis | + | The developed system is called **NatLog** and has an architecture with three main stages: Linguistic preprocessing (parse input sentences, monotonicity marking) Alignment (alignment between the premise and the hypothesis |
Line 22: | Line 25: | ||
*It is good that the examples in test data contain 3 different answers. | *It is good that the examples in test data contain 3 different answers. | ||
*Disadvantage: | *Disadvantage: | ||
- | *We liked the evaluation presented in the paper and the result' | + | *We liked the evaluation presented in the paper and the results |
- | Comments | + | Written |