Textual entailment

A method comprising:

• obtaining, by a processor, a query from a user, the query indicating a data entailment requirement comprising entailment data and associated with entailment operations;
• implementing, by the processor, an artificial intelligence component to:
• identify a word index from a knowledge database, the word index including a plurality of words being associated with the data entailment requirement;
• identify a premise from the entailment data, the premise comprising a first word data set associated with the data entailment requirement;
• and
• determine a premise index by mapping the first word data set with the word index;
• implementing, by the processor, a first cognitive learning operation to determine a plurality of hypothesis corresponding to the premise, each of the plurality of hypothesis comprising a second word data set and indicating an inference associated with the premise, the second word data set being associated with the word index;
• determining, by the processor, a hypothesis index by mapping the second word data set with the word index;
• generating, b the processor, a premise graph and a hypothesis graph, the premise graph mapping the first word data set against the second word data set, and the hypothesis graph mapping the second word data set against the first word data set;
• generating, by the processor, a confidence index for each of the plurality of hypothesis based on a comparison of the hypothesis index with the premise index;
• determining, by the processor, an entailment value based on the confidence index for each of the plurality of hypothesis, the entailment value indicating a probability of a hypothesis from the plurality of hypothesis being positively associated with the premise;
• determining, by the processor, a contradiction value from the confidence index for each of the plurality of hypothesis, the contradiction value indicating a probability of a hypothesis from the plurality of hypothesis being negatively associated with the premise;
• determining, by the processor, neutral entailment value from the confidence index for each of the plurality of hypothesis, the neutral entailment value indicating a probability of a hypothesis from the plurality of hypothesis being neutrally associated with the premise;
• determining, by the processor, an entailed output index by collating the entailment value, the contradiction value, and the neutral entailment value for each of the plurality of hypothesis;
• and
• generating, by the processor, an entailment result relevant for resolving the query, the entailment result comprising the plurality of hypothesis along with the corresponding entailed output index.

A non-transitory computer readable medium including machine readable instructions that are executable by a processor to:

• obtain a query from a user, the query indicating a data entailment requirement comprising entailment data and associated with entailment operations;
• implement an artificial intelligence component to:
• identify a word index from a knowledge database, the word index including a plurality of words being associated with the data entailment requirement;
• identify a premise from the entailment data, the premise comprising a first word data set associated with the data entailment requirement;
• and
• determine a premise index by mapping the first word data set with the word index;
• implement a first cognitive learning operation to determine a plurality of hypothesis corresponding to the premise, each of the plurality of hypothesis comprising a second word data set and indicating an inference associated with the premise, the second word data set being associated with the word index:
• determine a hypothesis index by mapping the second word data set with the word index;
• generate a premise graph and a hypothesis graph, the premise graph mapping the first word data set against the second word data set, and the hypothesis graph mapping the second word data set against the first word data set:
• generate a confidence index for each of the plurality of hypothesis based on a comparison of the hypothesis index with the premise index;
• determine an entailment value based on the confidence index for each of the plurality of hypothesis, the entailment value indicating a probability of a hypothesis from the plurality of hypothesis being positively associated with the premise;
• determine a contradiction value from the confidence index for each of the plurality of hypothesis, the contradiction value indicating a probability of a hypothesis from the plurality of hypothesis being negatively associated with the premise;
• determine neutral entailment value from the confidence index for each of the plurality of hypothesis, the neutral entailment value indicating a probability of a hypothesis from the plurality of hypothesis being neutrally associated with the premise;
• determine an entailed output index by collating the entailment value, the contradiction value, and the neutral entailment value for each of the plurality of hypothesis;
• and
• generate an entailment result relevant for resolving the query, the entailment result comprising the plurality of hypothesis along with the corresponding entailed output index.