International Business Machines Corporation

Ofer Lavi

Inbal Ronen

David Boaz

Boaz Carmeli

David Amid

Ella Rabinovich

Segev Shlomov

Guy Lev

Einat Kermany

Guy Hadash

Ateret Anaby-Tavor

George Kour

Yaara Goldschmidt

Matan Yitshak Ninio

Eran Raichstein

Ophir Azulai

Oren Sar-Shalom

Ateret Anaby Tavor

Elad Mezuman

Alon Jacovi

Ori Bar El

Yftah Ziser

Ateret Anaby - Tavor

An example system includes a processor to receive a bot design and escalation logs associated with a chat bot configured based on the bot design. The processor can compute a similarity score between each of a number of bot response nodes in the bot design and the escalation logs. The processor can generate a sorted list of the bot response nodes in the bot design based on the similarity scores.

Adjusting chat bot design based on matched escalation logs

A method, computer system, and a computer program product for automated agent intent detection enhancement are provided. A first message from a first user is received. The first message is generated during a first conversation between the first user and a first automated agent. A computer produces a second message that includes a same request as the first message but a different language modality than the first message. The second message and the first message are combined to form a combined message. The combined message is input into the first automated agent such that the first automated agent produces an intent classification for the first message.

Message mapping and combination for intent classification

Automatic measurement of semantic textual similarity of conversations, by: receiving two conversation texts, each comprising a sequence of utterances; encoding each of the sequences of utterances into a corresponding sequence of semantic representations; computing a minimal edit distance between the sequences of semantic representations; and, based on the computation of the minimal edit distance, performing at least one of: quantifying a semantic similarity between the two conversation texts, and outputting an alignment of the two sequences of utterances with each other.

Automatic measurement of semantic similarity of conversations

A specification of a property required to be upheld by a computerized machine learning system is obtained. A training data set corresponding to the property and inputs and outputs of the system is built. The system is trained on the training data set. Activity of the system is monitored before, during, and after the training. Based on the monitoring, performance of the system is evaluated to determine whether the system, once trained on the training data set, upholds the property.

Deep learning testing

During end-to-end training of a Deep Neural Network (DNN), a differentiable estimator subnetwork is operated to estimate a functionality of an external software application. Then, during inference by the trained DNN, the differentiable estimator subnetwork is replaced with the functionality of the external software application, by enabling API communication between the DNN and the external software application.

Integration of external applications into deep neural networks

The computer receives a group of conversation data associated with the escalation node, identifies agent responses in the conversation data, and clusters them into agent response types. The computer identifies dialog state feature value sets for the conversations. The computer identifies feature value set associations with response types, and generates, Boolean expressions representing the feature value sets associated with each of the response types. The computer makes a recommendation to add to at least one child node for the escalation node, with the child node corresponding to one of the response types. The child node has, as an entry condition, the Boolean expression for the response type to which the child node corresponds. The child node has as an action, which according to some aspects, provides a response representative of the cluster of agent responses for the response type to which the child node corresponds.

Computerized dialog system improvements based on conversation data

A method, apparatus and product for automatic detection of anomalies in graphs. The method comprising obtaining training data, the training data comprising a plurality of graphs, each defined by nodes and edges connecting between the nodes, at least some of the nodes are labeled; determining a statistical model of a graph in accordance with the training data, the statistical model takes into account at least one structured and labeled feature of the graph, wherein the structured and labeled feature of the graph is defined based on a connection between a plurality of nodes and based on at least a portion of the labels of the plurality of nodes; obtaining an examined graph; and determining a score of the examined graph indicative of a similarity between the examined graph and the training data, wherein the score is based on a value of the structured and labeled feature in the examined graph.

Automatic detection of anomalies in graphs

Automatic cloning of a PYTHON CONDA environment into a DOCKER image, such that at least one CONDA container that functions the same as the PYTHON CONDA environment can be started from the DOCKER image. The automatic cloning may include: First, creating a Dockerfile that comprises commands to: install a PYTHON ANACONDA environment or obtain a PYTHON ANACONDA environment image, copy the PYTHON CONDA environment into the DOCKER image, and run a CONDA command, in the ANACONDA environment, to create a cloned PYTHON CONDA environment from the copied PYTHON CONDA environment. Second, building the DOCKER image from the Dockerfile.

Automatic cloning of Conda environment into Docker image

In some examples, a system for executing natural language processing techniques can include a processor to detect text comprising a word and a number. The processor can also embed, via a word embedding model, the word into a first vector of a vector space and embed the number by converting the number into a second vector of the vector space. Additionally, the processor can train a deep neural network to execute instructions based on the first embedded vector of the word and the second embedded vector of the number. Furthermore, the processor can process an instruction based on the trained deep neural network.

Numerical representation in natural language processing techniques

An example system includes a processor to receive a plurality of object aspects of an object to be evaluated using a process, a structure of the process, a plurality of extracted facts from documents, a tree related to the plurality of object aspects and the structure, and a thesis for each leaf in the tree. The processor is also to relate the extracted facts to the theses in the tree. The processor is to generate a score for each leaf corresponding to a fact in the tree. The processor is to generate a thesis score and a thesis summary for each thesis based on the scores and the summaries of related facts for each thesis. The processor is to further generate a final score for the object based on the thesis scores.

Growing community of inventors

Tel Aviv, Israel

Ofer Lavi