Abstract: Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement an improved search query generation system, the method comprising inputting a natural language question; parsing the natural language question into a parse tree; identifying argument positions comprising one or more argument position terms, wherein each argument position term is a single word; for each argument position: comparing a head term's discriminator score against a threshold discriminator score; and if the head term surpasses the threshold discriminator score, adding the head term as a required term to an improved search query; and outputting the improved search query.

Abstract: Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement an improved search query generation system, the method comprising inputting a natural language question; parsing the natural language question into a parse tree; identifying argument positions comprising one or more argument position terms; for each argument position: comparing a head term's discriminator score against a threshold discriminator score; and if the head term surpasses the threshold discriminator score, adding the head term as a required term to an improved search query; and outputting the improved search query.

Abstract: A grammatically diverse test set of natural language sentences for a deep question answering system is provided by analyzing a given sentence to characterize its syntactical classification, and adding the sentence to the test set if its classification is sufficiently different from other sentences already in the test set. A particular sentence may be selected for inclusion according to a desired syntactic distribution. Multiple sentences having the exact same classification may be allowed subject to a maximum number of such sentences. The test set is adapted to an element of interest by characterizing each syntactical classification relative to the element of interest. The analysis derives a parse tree, identifies a particular node of the tree corresponding to the element of interest, and extracts syntactic information by traversing the tree starting at the particular node and ending at the root node of the tree according to different traversal schemes.

Abstract: Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement an improved search query generation system, the method comprising inputting a natural language question; parsing the natural language question into a parse tree; identifying argument positions comprising one or more argument position terms; for each argument position: comparing a head term's discriminator score against a threshold discriminator score; and if the head term surpasses the threshold discriminator score, adding the head term as a required term to an improved search query; and outputting the improved search query.

Abstract: Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement an improved search query generation system, the method comprising inputting a natural language question; parsing the natural language question into a parse tree; identifying argument positions comprising one or more argument position terms; for each argument position: comparing a head term's discriminator score against a threshold discriminator score; and if the head term surpasses the threshold discriminator score, adding the head term as a required term to an improved search query; and outputting the improved search query.

Abstract: A grammatically diverse test set of natural language sentences for a deep question answering system is provided by analyzing a given sentence to characterize its syntactical classification, and adding the sentence to the test set if its classification is sufficiently different from other sentences already in the test set. A particular sentence may be selected for inclusion according to a desired syntactic distribution. Multiple sentences having the exact same classification may be allowed subject to a maximum number of such sentences. The test set is adapted to an element of interest by characterizing each syntactical classification relative to the element of interest. The analysis derives a parse tree, identifies a particular node of the tree corresponding to the element of interest, and extracts syntactic information by traversing the tree starting at the particular node and ending at the root node of the tree according to different traversal schemes.

Abstract: Embodiments can provide a computer implemented method in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement a type-specific answer filtration system, the method comprising parsing, by the processor, one or more input questions; for each input question: attempting, by a number-subtype finder module, to identify one or more number-subtype head-nouns; attempting, by a number-subtype finder module, to identify one or more number-subtype verbs; attempting, by a number-subtype finder module, to identify one or more number-subtype adjectives; based on the presence of at least one number-subtype head-noun, number-subtype verb, or number-subtype adjective, determining, by a question classifier module, the number-subtype of the input questions; labelling the input question with the determined number-subtype; iterating through one or more answer candidates associated with the input question; for each answer candidat

Abstract: Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement an improved search query generation system, the method comprising inputting a natural language question; parsing the natural language question into a parse tree; identifying argument positions comprising one or more argument position terms; for each argument position: comparing a head term's discriminator score against a threshold discriminator score; and if the head term surpasses the threshold discriminator score, adding the head term as a required term to an improved search query; and outputting the improved search query.

Abstract: A grammatically diverse test set of natural language sentences for a deep question answering system is provided by analyzing a given sentence to characterize its syntactical classification, and adding the sentence to the test set if its classification is sufficiently different from other sentences already in the test set. A particular sentence may be selected for inclusion according to a desired syntactic distribution. Multiple sentences having the exact same classification may be allowed subject to a maximum number of such sentences. The test set is adapted to an element of interest by characterizing each syntactical classification relative to the element of interest. The analysis derives a parse tree, identifies a particular node of the tree corresponding to the element of interest, and extracts syntactic information by traversing the tree starting at the particular node and ending at the root node of the tree according to different traversal schemes.

Abstract: A grammatically diverse test set of natural language sentences for a deep question answering system is provided by analyzing a given sentence to characterize its syntactical classification, and adding the sentence to the test set if its classification is sufficiently different from other sentences already in the test set. A particular sentence may be selected for inclusion according to a desired syntactic distribution. Multiple sentences having the exact same classification may be allowed subject to a maximum number of such sentences. The test set is adapted to an element of interest by characterizing each syntactical classification relative to the element of interest. The analysis derives a parse tree, identifies a particular node of the tree corresponding to the element of interest, and extracts syntactic information by traversing the tree starting at the particular node and ending at the root node of the tree according to different traversal schemes.