Microsoft Technology Licensing, LLC

Sayed Hassan

Achraf Chalabi

Mohamed Ahmed El-Sharqwi

Ahmed Said Morsy

Meyyammai Subramanian

Michelle Follosco Valeriano

Anneliese Creighton Wirth

Hany Awadalla

Technologies are described herein for identifying query intent from a raw query. A method for identifying intent may include repeatedly separating and merging terms of a natural language expression based on a set of rule-based transpositions of natural language terms into one or more defined terms based on predetermined naming conventions for at least one software function. Thereafter, a cluster of previous search terms related to the defined terms may be identified, and the natural language expression may be associated with the identified cluster to create intent-based cluster information.

Identifying query intent

Some implementations provide techniques and arrangements to perform automated translation from a source language to a target language. For example, an out-of-vocabulary word may be identified and a morphological analysis may be performed to determine whether the out-of-vocabulary word reduces to at least one stem. If the out-of-vocabulary word reduces to a stem, the stem may be translated. The translated stem may be inflected if the out-of-vocabulary word is inflected. If the out-of-vocabulary word has any affixes, the affixes may be translated. In some cases, the translated affixes may be reordered before being combined with the inflected and translated stem. If the out-of-vocabulary word is misspelled, the spelling of the out-of-vocabulary word may be corrected before performing the morphological analysis. If the out-of-vocabulary word is a colloquial form of a formal word, the out-of-vocabulary word may be replaced with the formal word before performing the morphological analysis.

Resolving out-of-vocabulary words during machine translation

Growing community of inventors

Giza, Egypt

Sayed Hassan