Systems and methods for lexical correspondence linguistic knowledge base creation comprising dependency trees with procedural nodes denoting execute code
First Claim
1. A system comprising:
- a lexical correspondence graphical user interface configured toco-display to a user a first dependency tree of a first multi-word expression in a first natural language and a second dependency tree of a corresponding second multi-word expression in a second natural language, andin response to co-displaying the first and second dependency trees to the user, receive a user input indicating a presence and a type of a lexical correspondence between a first node of the first dependency tree and a second node of the second dependency tree, the user input comprising an indicator of a user selection from a plurality of lexical correspondence type choices presented to the user of the type of the lexical correspondence between the first node of the first dependency tree and the second node of the second dependency tree; and
a lexical correspondence code generator connected to the lexical correspondence graphical user interface and configured to generate grammar abstract language (GAL) computer-readable correspondence code representing the lexical correspondence in response to receiving an indicator of the user input, the grammar abstract language correspondence code designating a set of correspondences between nodes of a grammar abstract language dependency tree representing the first multi-word expression and corresponding nodes of a grammar abstract language dependency tree representing the second multi-word expression, wherein a node of the grammar abstract language representation of the first multi-word expression includes an attribute-value tree characterizing morphologically the node;
wherein at least one node of the first dependency tree is a procedural node representing a procedure, wherein performing the procedure comprises executing code to perform an action selected from turning numerals into numeric values, manipulating a picture embedded in text, and manipulating a sound embedded in text associated with the node.
1 Assignment
0 Petitions
Accused Products
Abstract
In some embodiments, a linguistic knowledge base containing correspondences between pairs of words or multi-word expressions belonging to different natural languages is generated and maintained using a graphical user interface. A linguistic model generates dependency tree representations of each multi-word expression. The dependency trees are simultaneously displayed within a graphical user interface, allowing a user to indicate lexical correspondences between pairs of nodes. Computer-readable (e.g. XML) encodings of the lexical correspondences are generated and stored in the linguistic knowledge base. At least some of the nodes are procedural nodes representing procedures which turn numerals into numeric values or manipulate pictures or sounds embedded in text associated with the node.
64 Citations
22 Claims
-
1. A system comprising:
-
a lexical correspondence graphical user interface configured to co-display to a user a first dependency tree of a first multi-word expression in a first natural language and a second dependency tree of a corresponding second multi-word expression in a second natural language, and in response to co-displaying the first and second dependency trees to the user, receive a user input indicating a presence and a type of a lexical correspondence between a first node of the first dependency tree and a second node of the second dependency tree, the user input comprising an indicator of a user selection from a plurality of lexical correspondence type choices presented to the user of the type of the lexical correspondence between the first node of the first dependency tree and the second node of the second dependency tree; and a lexical correspondence code generator connected to the lexical correspondence graphical user interface and configured to generate grammar abstract language (GAL) computer-readable correspondence code representing the lexical correspondence in response to receiving an indicator of the user input, the grammar abstract language correspondence code designating a set of correspondences between nodes of a grammar abstract language dependency tree representing the first multi-word expression and corresponding nodes of a grammar abstract language dependency tree representing the second multi-word expression, wherein a node of the grammar abstract language representation of the first multi-word expression includes an attribute-value tree characterizing morphologically the node; wherein at least one node of the first dependency tree is a procedural node representing a procedure, wherein performing the procedure comprises executing code to perform an action selected from turning numerals into numeric values, manipulating a picture embedded in text, and manipulating a sound embedded in text associated with the node. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A computer-implemented method comprising:
-
co-displaying to a user a first dependency tree of a first multi-word expression in a first natural language and a second dependency tree of a second multi-word expression in a second natural language; in response to co-displaying the first dependency tree and the second dependency tree to the user, receiving a user input indicating a presence and a type of a lexical correspondence between a first linguistic node of the first dependency tree and a second linguistic node of the second dependency tree, the user input comprising an indicator of a user selection from a plurality of lexical correspondence type choices presented to the user of the type of the lexical correspondence between the first node of the first dependency tree and the second node of the second dependency tree; and in response to receiving the user input, generating grammar abstract language (GAL) computer-readable correspondence code representing the lexical correspondence, the grammar abstract language correspondence code designating a set of correspondences between nodes of a grammar abstract language dependency tree representing the first multi-word expression and corresponding nodes of a grammar abstract language dependency tree representing the second multi-word expression, wherein a node of the grammar abstract language representation of the first multi-word expression includes an attribute-value tree characterizing morphologically the node; wherein at least one node of the first dependency tree is a procedural node representing a procedure, wherein performing the procedure comprises executing code to perform an action selected from turning numerals into numeric values, manipulating a picture embedded in text, and manipulating a sound embedded in text associated with the node. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20)
-
-
21. A system comprising:
-
means for co-displaying to a user a first dependency tree of a first multi-word expression and a second dependency tree of a second multi-word expression; means for receiving a user input indicating a presence and a type of a lexical correspondence between a first linguistic node of the first dependency tree and a second linguistic node of the second dependency tree in response to co-displaying the first dependency tree and the second dependency tree to the user, the user input comprising an indicator of a user selection from a plurality of lexical correspondence type choices presented to the user of the type of the lexical correspondence between the first node of the first dependency tree and the second node of the second dependency tree; and means for generating grammar abstract language computer-readable correspondence code representing the lexical correspondence in response to receiving the user input, the grammar abstract language correspondence code designating a set of correspondences between nodes of a grammar abstract language dependency tree representing the first multi-word expression and corresponding nodes of a grammar abstract language dependency tree representing the second multi-word expression, wherein a node of the grammar abstract language representation of the first multi-word expression includes an attribute-value tree characterizing morphologically the node; wherein at least one node of the first dependency tree is a procedural node representing a procedure, wherein performing the procedure comprises executing code to perform an action selected from turning numerals into numeric values, manipulating a picture embedded in text, and manipulating a sound embedded in text associated with the mode.
-
-
22. A system comprising:
-
a lexicon linguistic knowledge base configured to store a plurality of lexicon entries for each of a plurality of natural languages; a lexical element manager connected to the lexicon linguistic knowledge base, and configured to receive natural language multi-word expressions and generate a structured lexicon entry for each natural language multi-word expression for storage in the lexicon linguistic knowledge base; a lexical correspondence knowledge base storing a plurality of multi-word expression correspondence entries between at least a pair of natural languages of the plurality of natural languages; a graphical user interface configured to co-display to a user a first dependency tree of a first multi-word expression in a first natural language and a second dependency tree of a corresponding second multi-word expression in a second natural language, and in response to co-displaying the first and second dependency trees to the user, receive user input indicating a presence and a type of a lexical correspondence between a first node of the first dependency tree and a second node of the second dependency tree, the user input comprising an indicator of a user selection from a plurality of lexical correspondence type choices presented to the user of the type of the lexical correspondence between the first node of the first dependency tree and the second node of the second dependency tree; and a lexical correspondence manager connected to the lexicon linguistic knowledge base, graphical user interface and the lexical correspondence knowledge base, and configured to generate grammar abstract language (GAL) multi-word expression correspondence code according to lexicon entries stored in the lexicon linguistic knowledge base and multi-word expression correspondence user input, for updating the lexical correspondence knowledge database, the grammar abstract language correspondence code designating a set of correspondences between nodes of a grammar abstract language dependency tree representing the first multi-word expression and corresponding nodes of a grammar abstract language dependency tree representing the second multi-word expression, wherein a node of the grammar abstract language representation of the first multi-word expression includes an attribute-value tree characterizing morphologically the node; wherein at least one node of the first dependency tree is a procedural node representing a procedure, wherein performing the procedure comprises executing code to perform an action selected from turning numerals into numeric values, manipulating a picture embedded in text, and manipulating a sound embedded in text associated with the node.
-
Specification