International Business Machines Corporation

Nuance Communications, Inc.

Jeffrey Scott McCarley

Martin Franz

Mihaela Ancuta Bornea

Jim Alain Laredo

Radu Florian

Salim Estephan Roukos

Kenneth W Church

Jason William Pelecanos

Robert T Ward

Yunhui Zheng

Alessandro Morari

Sara Rosenthal

Nicholas Stephen Kersting

Saurabh Pujar

Weizhong Zhu

Leiming R Qian

Wei-Jing Zhu

Luca Buratti

A method of using a computing device using natural language software to respond to a Boolean question is presented. The method includes receiving, by a computing device, a question and at least one passage. The computing device classifies the question as a Boolean type question. The computing device generates evidence from the at least one passage to the Boolean question. The computing device generates a response to the Boolean question using the generated evidence. The computing device provides the generated evidence that supports the response to the Boolean question.

Computer assisted answering Boolean questions with evidence

In a computer-implemented method for improving a static analyzer output, a processor receives a labeled data set with labeled true vulnerabilities and labeled false vulnerabilities. A processor receives pretrained contextual embeddings from a contextual embeddings model. A processor maps the true vulnerabilities and the false vulnerabilities to the pretrained contextual embeddings model. A processor generates a fine-tuned model with classifications for true vulnerabilities.

Contextual embeddings for improving static analyzer output

Embodiments of the present invention provide a computer-implemented method for communicating a reference code for a transaction. The method monitors a communication session conducted between a user and an agent via a communication channel, extracts user and channel properties from the monitored communication session, selects a reference code from a set of references codes stored on a database, in which the selection is based at least in part on the extracted communication channel properties and the extracted user properties, and then communicates the selected reference code to the user.

Adaptive selection of message data properties for improving communication throughput and reliability

An automated speech processing method, system and computer program product are disclosed. In one embodiment, a speech-to-text (STT) engine is used for converting an audio input to text data in a source language, and a machine translation (MT) engine is used for translating this text data to text data in a target language. In this embodiment, the text data in the target language is rendered on a display device, and different visualization schemes are applied to different parts of the rendered text data based on defined characteristics of the STT engine and the MT engine. In one embodiment, the defined characteristics include a defined confidence value representing the accuracy of the rendered text. For example, this confidence value may be based on both the accuracy of the conversion of the audio input and the accuracy of the translation of the text data to the target language.

Visualizing automatic speech recognition and machine translation output

An improved method, apparatus, and computer instructions displaying search results. A query is received in a first language. A snippet in the document containing the word is selected in response to identifying a document in a second language in which the document contains a word matching a query word in the query. This snippet is translated into the first language.

Display of results of cross language search

There is provided a method for compressing an index file in an information retrieval system that retrieves information from a plurality of documents. Each of the plurality of documents has features occurring therein. Each of the features has parameters corresponding thereto. Parameter values corresponding to the parameters of the features are mapped into a plurality of bins. Bin identifiers are stored in the index file. Each of the bin identifiers identifies a bin to which is assigned at least one individual parameter value corresponding to at least one individual parameter.

Compressing index files in information retrieval

Disclosed is a method of validating a byte sequence having a plurality of states, the method comprising designating one or more noise states from among the plurality of states; generating a most probable state sequence for the byte sequence; utilizing said state sequence to identify all noise in the byte sequence; and localizing said noise in said noise states. Once localized, the noise may be deleted from the byte sequence.

Noise removal in multibyte text encodings using statistical models

An audio indexing system including, in addition to a speech recognition subsystem for converting the audio information into a textual form and an indexing subsystem for extracting the features to be used for searching and browsing, a statistical machine translation model, trained on a parallel or comparable corpus of automatically and by-hand transcribed data, for processing the output of the speech recognition system.

Indexing with translation model for feature regularization

A method of indexing a database of documents, by providing a vocabulary of n terms, indexing the database in the form of a non-negative n&#xd7;m index matrix V, wherein each of its m columns represents an jdocument having n entries containing a function of the number of occurrences of a iterm of said vocabulary appearing in said jdocument, factoring out non-negative matrix factors T and D such that V&#x2248;TD, and wherein T is an n&#xd7;r term matrix, D is an r&#xd7;m document matrix, and r&#x3c;nm/(n+m). The index so generated is useful in two-pass information retrieval systems.

Information retrieval with non-negative matrix factorization

A method for retrieving information, in accordance with the present invention, includes the steps of providing an initial query in a first language, retrieving data in a second language in accordance with the initial query, formulating the query in the second language, retrieving data in a third language in accordance with the query formulated in the second language and outputting data retrieved in the third language in accordance with the initial query. A system is also provided in accordance with the invention.

Multilingual information retrieval with a transfer corpus

A system and method for translating a series of source words in a first language to a series of target words in a second language is provided. The system includes an input device for inputting the series of source words. A fertility hypothesis generator operatively coupled to the input device generates at least one fertility hypotheses for a fertility of a source word, based on the source word and a context of the source word. A sense hypothesis generator operatively coupled to the input device generates sense hypotheses for a translation of the source word, based on the source word and the context of the source word. A fertility model operatively coupled to the fertility hypothesis generator determines a probability of the fertility of the source word, based on the source word and the context of the source word. A sense model operatively coupled to the sense hypothesis generator determines a probability of a target word being a correct translation of the source word, based on the source word and the context of the source word. A decoder operatively coupled to the fertility and sense models for generating a list of target words for the translation of the source word, based on the probability calculated by the fertility model and the probability calculated by the sense model.

Growing community of inventors

Bedford Hills, NY, United States of America

Jeffrey Scott McCarley