SYSTEM AND METHOD FOR DETECTING ORPHAN UTTERANCES Russian patent published in 2019 - IPC G10L15/22 G06F16/35 G06F16/951 

Abstract RU 2699399 C2

FIELD: physics.

SUBSTANCE: invention relates to means of detecting orphaned utterances. Non-domain statement rejected by domain classifier of target language understanding system is received. Out-of-domain statement is evaluated by one or more semantics, syntax, part of speech or lexicon tag, determining whether the out-of-domain statement is a web search request or an orphan dialog system of purposeful language comprehension. It is determined that the out-of-domain statement is an orphan by: checking the evaluated out-of-domain statement on the existence of the semantic feature, wherein the semantic feature is a predicate and/or an argument; and classifying an out-of-domain statement as an orphan, when the predicate and the argument exist. Response is generated indicating that the out-of-domain statement is understood as a request for execution of a certain action addressed to a dialogue system of purposeful understanding of the language.

EFFECT: technical result consists in improvement of efficiency of detection of orphan statements.

14 cl, 9 dwg, 4 tbl

Similar patents RU2699399C2

Title Year Author Number
SIMULATING SESSION CONTEXT FOR COLLOQUIAL SPEECH UNDERSTANDING SYSTEMS 2015
  • Akbacak, Murat
  • Hakkani-Tur, Dilek Z.
  • Tur, Gokhan
  • Heck, Larry P.
RU2693184C2
EMOTION TYPE CLASSIFICATION FOR INTERACTIVE DIALOGUE SYSTEM 2015
  • Leung Maks
  • Un Edvard
RU2705465C2
COREFERENCE RESOLUTION IN AMBIGUITY-SENSITIVE NATURAL LANGUAGE PROCESSING SYSTEM 2008
  • Van Den Berg Martin
  • Krauch Richard
  • Salvetti Franko
  • Tione Dzhovanni Lorentso
  • An Dehvid
RU2480822C2
MACHINE TRAINING 2005
  • Uill'Jams Dehvid R.
  • Khill Dzheffri
RU2391791C2
METHOD AND SYSTEM FOR PROVIDING VOICE INTERFACE 2009
  • Adler Mark
  • Kishsh Imre
  • Polifroni Dzhozef
  • Vu Tao
RU2494476C2
METHOD FOR SEMANTIC PROCESSING OF NATURAL LANGUAGE USING GRAPHIC INTERMEDIARY LANGUAGE 2009
  • Mende Mikhaehl'
RU2509350C2
RESOLUTION OF SEMANTIC AMBIGUITY USING LANGUAGE-INDEPENDENT SEMANTIC STRUCTURE 2013
  • Zuev Konstantin Alekseevich
  • Bogdanova Daria Nikolaevna
RU2579699C2
SENTIMENT ANALYSIS AT THE LEVEL OF ASPECTS USING METHODS OF MACHINE LEARNING 2016
  • Matskevich Stepan Evgenevich
  • Kuznetsova Ekaterina Sergeevna
  • Gusev Ilya Olegovich
RU2657173C2
SENTIMENT ANALYSIS AT LEVEL OF ASPECTS AND CREATION OF REPORTS USING MACHINE LEARNING METHODS 2016
  • Mikhajlov Maksim Borisovich
  • Pasechnikov Konstantin Alekseevich
RU2635257C1
MULTI STAGE RECOGNITION OF THE REPRESENT ESSENTIALS IN TEXTS ON THE NATURAL LANGUAGE ON THE BASIS OF MORPHOLOGICAL AND SEMANTIC SIGNS 2016
  • Anisimovich Konstantin Vladimirovich
  • Indenbom Evgeny Mihaylovich
  • Novitskiy Valery Igorevich
RU2619193C1

RU 2 699 399 C2

Authors

Tur Gokhan

Deoras Anoop

Hakkani-Tur Dilek

Dates

2019-09-05Published

2015-08-20Filed