Xerox Corporation

Conduent Business Services, LLC

Naver Corporation

Nikolaos Lagos

Matthias Gallé

Vassilina Nikoulina

Caroline Brun

Stefania Castellani

Frederic Roulland

Jinhee Lee

Jean-Yves Vion-Dury

Stéphane Clinchant

Maria Antonietta Grasso

Ioan Calapodescu

Salah Aït-Mokhtar

Nicolas Hairon

Ágnes Sandor

Ngoc Phuoc An Vo

Alexandr Chernov

There is disclosed a method for using a computer to enable correction of misclassified labels in a database. The computer initially applies a dataset (including labels pointing respectively to categories) to a first classifier, which includes a first loss function. Pursuant to the initial application, the computer determines that one or more labels have been misclassified. Responsive to such determination, the computer changes the first loss function to a second loss function to form a second classifier including the second loss function. The computer then applies the dataset to the second classifier for enabling correction of the one or more misclassified labels.

Computer-implemented method for improving classification of labels and categories of a database

A method for change management includes providing a dependency graph as an instantiation of a linked resource model in which a plurality of resources are linked by at least one dependency. The resources include at least one source resource and at least one target resource, each of the at least one dependency specifying preconditions on at least one of the at least one source resources for the dependency to be activated and an impact on at least one of the at least one target resources when the dependency is activated. A change to one of the plurality of resources is propagated to at least one other of the plurality of resources in the graph and information based on the propagation is output.

Data governance: change management based on contextualized dependencies

A computer-implemented system and method provide for mapping a set of strings onto an ontology which may be represented as a graph. The method includes receiving a set of strings, each string denoting a respective object. For each of the strings, a pairwise similarity is computed between the string and each of a set of objects in the ontology. For each of a set of candidate subsets (subgraphs) of the set of objects, a global score is computed, which is a function of the pairwise similarities between the strings and the objects in the subset and a tightness score. The tightness score is computed on the objects in the subset with a submodular function. An optimal subset is identified from the set of candidate subsets based on the global scores. Strings in the set of strings are mapped to the objects in the optimal subset, based on the pairwise similarities.

System for mapping a set of related strings on an ontology with a global submodular function

A computer-implemented linking system and method provide for linking actionable phrases in a first document to other documents in a document corpus. The method includes identifying at least one actionable phrase in a first document. The actionable phrase may include an action, its direct object, and any modifier of the direct object. For each identified action phrase the document corpus is searched to identify other documents, which are scored using a scoring function which takes into account occurrences of words of the actionable phrase in each identified document. The actionable phrase is linked to at least a part of one of the most highly ranked documents in the set of documents.

Enriching how-to guides by linking actionable phrases

A system and method provide assistance to an agent in responding to a customer query. A dialog including communications between a customer and an agent is displayed to an agent on a display device. During the dialog, keywords are extracted from at least one of the customer's text communications. This includes identifying keywords that are found in a set of terms extracted from a knowledge base. A search query is generated, based on the extracted keywords. Results of the search query are retrieved from at least one of the knowledge base and an external website. The results are displayed on the display device contemporaneously with at least a portion of the text communications, allowing the agent to quickly copy and paste text from one of the results into his response without having to leave the window in which the communications are displayed.

Online dynamic solution retrieval based on automatic keyword selection during customer dialogue

A method for categorizing an issue includes, for each of a plurality of categories of issue, providing at least one discourse pattern for identify text sequences that meet the discourse pattern. At least one of the discourse patterns specifies that an instance of a domain term in a domain term vocabulary be present in the text sequence for the pattern to be met. An issue is received which includes a text sequence. The text sequence is categorized based on which, if any, of the discourse patterns are met by the text sequence of the received issue. Information based on the categorization of the text sequence is output.

Method and system for identifying user issues in forum posts based on discourse analysis

A system and method provide for identifying coreference from serialized data coming from different services. The method includes generating a tree structure from serialized data. The serialized data includes responses to queries from the different services. The responses each identify a hierarchical relationship between a respective set of objects. Nodes of the tree structure each have a name corresponding to a respective one of the objects. The tree structure is traversed in a breadth first manner and, for each node in the tree structure, a respective pairwise similarity is computed with each of the other nodes of the tree structure. The computed pairwise similarity is compared with a threshold to identify co-referring nodes that refer to a same entity. The threshold is a function of a depth of the node in the tree structure.

Matching co-referring entities from serialized data for schema inference

A system and method for guiding a user in building a query are disclosed. The method includes providing an interaction space in which a user formulates a query using a plurality of query building blocks selected from a predefined set of query building blocks. The user's formulation of the query is guided. Guiding selection of at least a next building block is provided by at least one of a content-based mechanism which limits the selection of the next building block to those which will yield at least one result from an indexed collection of documents, a structure-based selection mechanism which limits the selection of the next building block to those which meet a predefined grammar, and a usage-based selection mechanism which proposes a next building block based on patterns of building blocks used in building prior queries. Each of these guidance mechanisms may be provided with the result that the next block proposed is informed by each of the mechanisms.

Method and system to guide formulations of questions for digital investigation activities

A system and method for natural language processing of queries are provided. A lexicon includes text elements that are recognized as being a proper noun when capitalized. A natural language query includes a sequence of text elements including words. The query is processed. The processing includes a preprocessing step, in which part of speech features are assigned to the text elements in the query. This includes identifying, from a lexicon, a text element in the query which starts with a lowercase letter and assigning recapitalization information to the text element in the query, based on the lexicon. This information includes a part of speech feature of the capitalized form of the text element. Then parts of speech for the text elements in the query are disambiguated, which includes applying rules for recapitalizing text elements based on the recapitalization information.

Linguistically-adapted structural query annotation

A system and method suited to translation of queries are disclosed. The method includes receiving an input query in a source language and outputting a target query, based on a translation of the input query into a target language, different from the source language. The translation is performed with a machine translation system which has been trained on representations of features of translated queries that have been generated by translation of an original query, in the source language, into the target language and a measure of information retrieval performance of each the translated queries, for each of a set of original queries.

Translation system adapted for query translation via a reranking framework

A translation system and method suited to use in Cross Language Information Retrieval employ a retrieval-based scoring function for reranking candidate translations. The method includes translating an input source language query to generate a set of the candidate translations in a target language. The candidate translations are scored with the scoring function, which allows them to be reranked, and an optimal one or more selected for use in querying a domain-specific collection of documents in the target language. The scoring function applies weights to features extracted from the candidate translations. The weights have been learned on features extracted from translated queries, each generated by translation of an original query into the target language, and a measure of information retrieval performance of each the translated queries. One or more of the features used is a domain-specific feature which relies on a corpus of documents in the domain of interest.

Growing community of inventors

Grenoble, France

Nikolaos Lagos