Taste and smell classification from multilanguage descriptions can be performed by extracting, by one or more processors using natural language processing, a text including one or more words associated with taste and smell perceptions from an input received from a plurality of users. The input includes multilanguage information regarding at least one of changes in smell and changes in taste perceived by each of the plurality of users. Feature vectors are generated for the text extracted from the input using global vectors, and a distance between the feature vectors and a plurality of reference descriptors associated with taste and smell is calculated for determining a similarity between the text and the reference descriptors and creating a training dataset based on which a classification model is generated for categorizing the plurality of users according to the at least one of changes in smell and changes in taste.

In one embodiment, a device determines a comprehension level for a portion of text associated with an online conversation, based in part on a topic of the portion of text. The device makes a comparison between the comprehension level for the portion of text with a comprehension level of a participant of the online conversation. The device generates adjusted text based on the portion of text, wherein the adjusted text has a comprehension level that is equal to or lower than that of the participant. The device provides the adjusted text for display to the participant.

In one embodiment, a device determines a comprehension level for a portion of text associated with an online conversation, based in part on a topic of the portion of text. The device makes a comparison between the comprehension level for the portion of text with a comprehension level of a participant of the online conversation. The device generates adjusted text based on the portion of text, wherein the adjusted text has a comprehension level that is equal to or lower than that of the participant. The device provides the adjusted text for display to the participant.

There are provided a method and system for automatic augmentation of gloss-based sign language translation data. A system for automatic augmentation of sign language translation training data according to an embodiment includes: a database configured to store a sequence of sign language glosses and a sequence of spoken-language words in pairs; and an augmentation module configured to augment the pairs stored in the database. Accordingly, gloss-based training data of high quality may be acquired by performing automatic augmentation for gloss-based training data for sign language translation in an efficient method in terms of time and economic aspects, and eventually, accuracy of translation between sign language glosses and sentences may be enhanced.

In response to running at least one testing phrase on a previously trained text classifier and identifying a separate predicted classification label based on a score calculated for each respective at least one testing phrase, a text classifier decomposes extracted features summed in the score into word-level scores for each word in the at least one testing phrase. The text classifier assigns a separate heatmap value to each of the word-level scores, each respective separate heatmap value reflecting a weight of each word-level score. The text classifier outputs the separate predicted classification label and each separate heatmap value reflecting the weight of each word-level score for defining a heatmap identifying the contribution of each word in the at least one testing phrase to the separate predicted classification label for facilitating client evaluation of text classification anomalies.

In response to running at least one testing phrase on a previously trained text classifier and identifying a separate predicted classification label based on a score calculated for each respective at least one testing phrase, a text classifier decomposes extracted features summed in the score into word-level scores for each word in the at least one testing phrase. The text classifier assigns a separate heatmap value to each of the word-level scores, each respective separate heatmap value reflecting a weight of each word-level score. The text classifier outputs the separate predicted classification label and each separate heatmap value reflecting the weight of each word-level score for defining a heatmap identifying the contribution of each word in the at least one testing phrase to the separate predicted classification label for facilitating client evaluation of text classification anomalies.

In accordance with one embodiment, a method can be implemented that comprises receiving as an input a title of a video from a video sharing web site; parsing the title of the video into one or more n-grams; computing with a computer a title-searchability-score by utilizing the one or more n-grams.

A 3D conversational chatbot is disclosed. The conversational chatbot is embodied in an avatar to provide a human-like experience for end-users. The chatbot is an artificial intelligence-based chatbot. The chatbot is configured with the knowledge of the chatbot owner. The knowledge may depend on the owner, such as the products and/or services provided by the owner. For example, the chatbot is customized with AI for the specific needs of its owner. The avatar communicates with the user, such as a customer, to answer questions with life-like speech and facial movement.

In various example embodiments, a system and method for a Listing Engine that translates a first listing from a first language to a second language. The first listing includes an image(s) of a first item. The Listing Engine provides as input to an encoded neural network model a portion(s) of a translated first listing and a portions(s) of a second listing in the second language. The second listing includes an image(s) of a second item. The Listing Engine receives from the encoded neural network model a first feature vector for the translated first listing and a second feature vector for the second listing. The first and the second feature vectors both include at least one type of image signature feature and at least one type of listing text-based feature. Based on a similarity score of the first and second feature vectors at least meeting a similarity score threshold, the Listing Engine generates a pairing of the first listing in the first language with the second listing in the second language for inclusion in training data of a machine translation system.

Systems and methods are provided to pre-train projection networks for use as transferable natural language representation generators. In particular, example pre-training schemes described herein enable learning of transferable deep neural projection representations over randomized locality sensitive hashing (LSH) projections, thereby surmounting the need to store any embedding matrices because the projections can be dynamically computed at inference time.