Ranking Parser for a Natural Language Processing System
First Claim
1. One or more computer-readable storage media having computer-executable instructions that, when executed by a computer, determine language usage probabilities of a natural language based upon a training corpus, the method comprising:
- examining a training corpus, wherein such corpus includes phrases parsed in accordance with a set of grammar rules;
computing probabilities of usage of combinations of linguistic features based upon empirical tracking of appearances of instances of such combinations in phrases within the training corpus.
1 Assignment
0 Petitions
Accused Products
Abstract
A natural language parse ranker of a natural language processing (NLP) system employs a goodness function to rank the possible grammatically valid parses of an utterance. The goodness function generates a statistical goodness measure (SGM) for each valid parse The parse ranker orders the parses based upon their SGM values. It presents the parse with the greatest SGM value as the one that most likely represents the intended meaning of the speaker. The goodness function of this parse ranker is highly accurate in representing the intended meaning of a speaker. It also has reasonable training data requirements. With this parse ranker, the SGM of a particular parse is the combination of all of the probabilities of each node within the parse tree of such parse. The probability at a given node is the probability of taking a transition (“grammar rule”) at that point. The probability at a node is conditioned on highly predicative linguistic phenomena, such as “phrase levels,” “null transitions,” and “syntactic history”
-
Citations
20 Claims
-
1. One or more computer-readable storage media having computer-executable instructions that, when executed by a computer, determine language usage probabilities of a natural language based upon a training corpus, the method comprising:
-
examining a training corpus, wherein such corpus includes phrases parsed in accordance with a set of grammar rules;
computing probabilities of usage of combinations of linguistic features based upon empirical tracking of appearances of instances of such combinations in phrases within the training corpus. - View Dependent Claims (2, 3)
-
-
4. One or more computer-readable storage media having computer-executable instructions that, when executed by a computer, determine language usage probabilities of a natural language based upon a training corpus, the method comprising:
-
examining a training corpus, wherein such corpus includes phrases parsed in accordance with a set of grammar rules, the phrases having been parsed, at least partially, automatically and without human intervention;
computing probabilities of usage of combinations of linguistic features based upon empirical tracking of appearances of instances of such combinations in phrases within the training corpus. - View Dependent Claims (5, 6, 7)
-
-
8. One or more computer-readable storage media having computer-executable instructions that, when executed by a computer, perform a method to parse a phrase, the method comprising:
-
generating at least one parse tree representing a syntactically valid parse of the phrase, wherein the parse tree has hierarchical nodes;
calculating a syntactic history for each node;
computing the probability for a node based upon the syntactic history calculated for that node. - View Dependent Claims (9, 10)
-
-
11. An apparatus comprising:
-
a processor;
a natural-language-usage parser executable on the processor to;
generating at least one parse tree representing a syntactically valid parse of the phrase, wherein the parse tree has hierarchical nodes;
calculating a syntactic history for each node;
computing the probability for a node based upon the syntactic history calculated for that node. - View Dependent Claims (12)
-
-
13. A natural-language-usage probability determiner comprising:
-
data-acquisition device is configured to receive language-usage probabilities based upon appearances of instances of combinations of linguistic features within a training corpus;
probability calculator is configured to calculate a probability at a node of a parse tree based upon linguistic features of the node and the language-usage probabilities. - View Dependent Claims (14, 15)
-
-
16. A natural-language-usage probability determiner comprising:
-
data-acquisition device is configured to receive language-usage probabilities based upon appearances of instances of combinations of linguistic features within a training corpus, wherein the training corpus includes phrases parsed in accordance with a set of grammar rules, the phrases having been parsed, at least partially, automatically and without human intervention;
probability calculator is configured for calculating a probability at a node of a parse tree based upon linguistic features of the node and the language-usage probabilities. - View Dependent Claims (17, 18)
-
-
19. A data structure for use with a computer having a processor and a memory, the data structure comprising:
-
a corpus comprising one or more phrases in a natural language;
parse trees having hierarchical nodes, each tree representing at least one syntactically valid parse of each phrase in a subset of the corpus;
wherein each of one or more nodes have a syntactic history and a probability associated therewith, wherein the probability of a node is based a node'"'"'s associated syntactic history. - View Dependent Claims (20)
-
Specification