The present invention discloses a method for amending translated draft text, an electronic device for amending translated draft text, and an APP implementing said method. The present invention provides an editing function for machine translation text which issues a final feedback or approval.

The present invention discloses a method for amending translated draft text, an electronic device for amending translated draft text, and an APP implementing said method. The present invention provides an editing function for machine translation text which issues a final feedback or approval.

Systems and methods for improving question-answering recall for complex, multi-sentence, convergent questions. More specifically, an autonomous agent accesses an initial answer that partly answers a question received from a user device. The agent represents the question and the initial answer as discourse trees. From the discourse trees, the agent identifies entities in the question that are not addressed by the answer. The agent forms an additional discourse tree from an additional resource such as a corpus of text. The additional discourse tree rhetorically connects a non-addressed entity with the answer. The agent designates this discourse tree as an imaginary discourse tree. When combined with the initial answer discourse tree, the imaginary discourse tree is used to generate an improved answer relative to existing solutions.

Systems and methods for improving question-answering recall for complex, multi-sentence, convergent questions. More specifically, an autonomous agent accesses an initial answer that partly answers a question received from a user device. The agent represents the question and the initial answer as discourse trees. From the discourse trees, the agent identifies entities in the question that are not addressed by the answer. The agent forms an additional discourse tree from an additional resource such as a corpus of text. The additional discourse tree rhetorically connects a non-addressed entity with the answer. The agent designates this discourse tree as an imaginary discourse tree. When combined with the initial answer discourse tree, the imaginary discourse tree is used to generate an improved answer relative to existing solutions.

Methods and systems for multi-modality soft-agents for an enterprise virtual assistant tool are disclosed. An exemplary method comprises capturing, with a computing device, one or more user requests based on at least one multi-modality interaction, populating, with a computing device, soft-queries to access associated data sources and applications, and mining information retrieved by executing at least one populated soft-query. A soft-query is created from user requests. A multi-modality user interface engine annotates the focus of user requests received via text, speech, touch, image, video, or object scanning. A query engine populates queries by identifying the sequence of multi-modal interactions, executes queries and provides results by mining the query results. The multi-modality interactions identify specific inputs for query building and specific parameters associated with the query. A query is populated and used to generate micro-queries associated with the applications involved. Micro-query instances are executed to obtain results.

Methods and systems for multi-modality soft-agents for an enterprise virtual assistant tool are disclosed. An exemplary method comprises capturing, with a computing device, one or more user requests based on at least one multi-modality interaction, populating, with a computing device, soft-queries to access associated data sources and applications, and mining information retrieved by executing at least one populated soft-query. A soft-query is created from user requests. A multi-modality user interface engine annotates the focus of user requests received via text, speech, touch, image, video, or object scanning. A query engine populates queries by identifying the sequence of multi-modal interactions, executes queries and provides results by mining the query results. The multi-modality interactions identify specific inputs for query building and specific parameters associated with the query. A query is populated and used to generate micro-queries associated with the applications involved. Micro-query instances are executed to obtain results.

A method is provided for validating a hypothesis sentence. The method extracts, from a document database D using a hypothesis sentence that includes a causal part and a consequence part, a set D1 of documents related to the causal part. The method extracts, from set D1, a set S of sentences that include expressions of opinion. The method obtains a word list W of words that have a high co-occurrence in the set D1. The method selects, from the set S, a set S1 of sentences that are positionally close to any of the words in the word list W. The method selects, from the set S, a set S2 of sentences that are related to the words in the consequence part of the hypothesis. The method extracts and displays sentences included in both the set S1 and the set S2 as opinion sentences in relation to the hypothesis sentence.

A method is provided for validating a hypothesis sentence. The method extracts, from a document database D using a hypothesis sentence that includes a causal part and a consequence part, a set D1 of documents related to the causal part. The method extracts, from set D1, a set S of sentences that include expressions of opinion. The method obtains a word list W of words that have a high co-occurrence in the set D1. The method selects, from the set S, a set S1 of sentences that are positionally close to any of the words in the word list W. The method selects, from the set S, a set S2 of sentences that are related to the words in the consequence part of the hypothesis. The method extracts and displays sentences included in both the set S1 and the set S2 as opinion sentences in relation to the hypothesis sentence.

Vocabulary consistency for a language model may be improved by splitting a target token in an initial vocabulary into a plurality of split tokens, calculating an entropy of the target token and an entropy of the plurality of split tokens in a bootstrap language model, and determining whether to delete the target token from the initial vocabulary based on at least the entropy of the target token and the entropy of the plurality of split tokens.

Vocabulary consistency for a language model may be improved by splitting a target token in an initial vocabulary into a plurality of split tokens, calculating an entropy of the target token and an entropy of the plurality of split tokens in a bootstrap language model, and determining whether to delete the target token from the initial vocabulary based on at least the entropy of the target token and the entropy of the plurality of split tokens.