Entailment Decision Task
(Redirected from Logical Entailment Test)
Jump to navigation
Jump to search
An Entailment Decision Task is a classification task of whether an expression is in a logically entailed relation with another expression.
- Context:
- Example(s):
- a Linguistic Expression Entailment Assessment Task.
- EDT("My cat is black”, “I have a black cat”) ⇒ True.
- EDT("I have a black cat”, “My cat is black”) ⇒ True.
- EDT("The Dow Jones Industrial Average closed up 255 points to brake its record high”, “Dow ends up”) ⇒ True.
- EDT("Dow ends up”, “The Dow Jones Industrial Average closed up 255 points to brake its record high”) ⇒ False.
- EDT("The Dow Jones Industrial Average closed up 255 points to brake its record high”, “Dow gains 255 points”) ⇒ True.
- EDT("The Dow Jones Industrial Average closed up 255 points to brake its record high”, “Stock market hits record high”) ⇒ True.
- a Logic Statement Entailment Assessment Task.
- …
- a Linguistic Expression Entailment Assessment Task.
- Counter-Example(s):
- See: Logical Entailment, Reasoning Argument, Textual Entailment, NLP.
References
2023
- chat
- Q: Does the statement "Dow ends up” logically entail that “The Dow Jones Industrial Average closed up 255 points to brake its record high”?
- A: No, the statement "Dow ends up" does not logically entail that "The Dow Jones Industrial Average closed up 255 points to brake its record high." The first statement simply states that the Dow ended positively, without providing any information about the specific amount or how it compares to previous records. The second statement provides specific information about the close of the Dow Jones Industrial Average and that it broke a record high.
2016
- (Vita & Kriz, 2016) ⇒ Víta, M., & Kríž, V. (2016, September). Word2vec based system for recognizing partial textual entailment. In Computer Science and Information Systems (FedCSIS), 2016 Federated Conference on (pp. 513-516). IEEE.
- ABSTRACT: Recognizing textual entailment is typically considered as a binary decision task - whether a text T entails a hypothesis H. Thus, in case of a negative answer, it is not possible to express that H is “almost entailed” by T. Partial textual entailment provides one possible approach to this issue. This paper presents an attempt to use word2vec model for recognizing partial (faceted) textual entailment. The proposed approach does not rely on language dependent NLP tools and other linguistic resources, therefore it can be easily implemented in different language environments where word2vec models are available.
2006
- (Dagan et al., 2006) ⇒ Ido Dagan, Oren Glickman, and Bernardo Magnini. (2006). “The PASCAL Recognising Textual Entailment Challenge.” In: : Lecture Notes in Computer Science, 3944. Springer. doi:10.1007/11736790_9
- ABSTRACT: This paper describes the PASCAL Network of Excellence first Recognising Textual Entailment (RTE-1) Challenge benchmark1. The RTE task is defined as recognizing, given two text fragments, whether the meaning of one text can be inferred (entailed) from the other. This application-independent task is suggested as capturing major inferences about the variability of semantic expression which are commonly needed across multiple applications. The Challenge has raised noticeable attention in the research community, attracting 17 submissions from diverse groups, suggesting the generic relevance of the task.