International Business Machines Corporation

Victoria Mazel

Yigal Shai Dayan

Josemina Marcella Magdalen

Oren Paikowsky

Irit Maharian

Andrei Shtilman

Daniel Cohen

Josemina Marcolla Magdalon

Techniques for processing a speech to text query are described herein. The techniques may include receiving a plurality of speech to text translation alternatives for a phrase of a natural language query, and tagging and parsing each of the translation alternatives based on a static analysis of the known domain that is at least partially structured, known tags of the known domain, and custom rules. The techniques may also include ranking the translation alternatives based on the tagging and parsing and translating the phrase based on the ranking.

Processing speech to text queries by optimizing conversion of speech queries to text

Techniques for analyzing a repository are described herein. A method for analyzing a repository may include obtaining a list of known persons in a repository based on objects, users, and groups retrieved from the repository. The method may further select one of the objects having a field and a value, and then determine whether the field of the selected object is a facet based on a probability that the field of the selected object has a limited number of possible values. In analyzing the repository, a repository information archive may be generated. The repository information archive may include the relationship between the selected object and at least one other object, statistics and counts related to properties in the selected objects, and whether or not the field of the selected object is a facet.

Automatic analysis of repository structure to facilitate natural language queries

Techniques for generating query language statements for a document repository are described herein. An example method includes detecting a search query corresponding to a document repository and generating a modified search query by adding atomic tags to the search query, the atomic tags being based on prior knowledge obtained by static analysis of the document repository and semantic rules. The method also includes generating enriched tags based on combinations of the atomic tags and any previously identified enriched tags and generating a first set of conditions based on combinations of the atomic tags and the generated enriched tags and generating a second set of conditions based on free-text conditions. The method also includes generating the query language statements based on the first set of conditions and the second set of conditions and displaying a plurality of documents from the document repository that satisfy the query language statements.

Generating and executing query language statements from natural language

Constructing an automaton for automated analysis of agglutinative languages comprises: constructing an affix automaton for each of a plurality of affix types of an agglutinative language, where each of the affix types is associated with one or more affixes associated with a morphological concept; combining any of the affix automatons to form a plurality of template automatons, where each of the template automatons is patterned after any of a plurality of agglutination templates of any of the affix types for the language; and combining the template automatons into a master automaton.

Efficient implementation of morphology for agglutinative languages

A system for stemming words of Semitic languages, the system including an affix scanner configured to scan a word of a Semitic language for at least one affix according to a predefined scanning sequence and determine if at least one predefined scanning criterion is met, and a stemmer configured to remove the affix from the word if the predefined scanning criterion is met.

Efficient stemming of semitic languages

Illustrative embodiments provide a computer implemented method, apparatus, and computer program product for learning word segmentation from non-white space language corpora. In one illustrative embodiment, the computer implemented method receives text input characters and calculates a ratio-measure for each pair of characters in the input characters. The computer implemented method further determines whether the ratio-measure of each pair of characters is equal to a predetermined threshold value. Responsive to determining the ratio-measure is less than the predetermined threshold value, and a local-minimum value, the computer method further identifies the pair as a weak pair and breaks the weak pair of characters.

Learning word segmentation from non-white space languages corpora

A hybrid n-gram/lexical analysis tokenization system including a lexicon and a hybrid tokenizer operative to perform both N-gram tokenization of a text and lexical analysis tokenization of a text using the lexicon, and to construct either of an index and a classifier from the results of both of the N-gram tokenization and the lexical analysis tokenization, where the hybrid tokenizer is implemented in at least one of computer hardware and computer software and is embodied within a computer-readable medium.

Hybrid text segmentation using N-grams and lexical information

Illustrated embodiments provide a computer implemented method, an apparatus, and a computer program product for unsupervised stemming schema learning and lexicon acquisition from corpora. In one illustrative embodiment, the computer implemented method obtains a corpus from corpora, analyzes the corpus to deduce a set of possible stemming schema and reviews and revises the set of possible stemming schema, to create a pruned set of stemming schema. The computer implemented method further deduces a lexicon from the corpus using the pruned set of stemming schema.

Growing community of inventors

Jerusalem, Israel

Victoria Mazel