A lead management system can employ a scheduling language and model for extracting appointments from consumer interactions. By using a scheduling language and model, the lead management system can accurately determine from textual content a particular time at which a consumer agreed to be called or to otherwise participate in an appointment with a representative of a business. As a result, AI-based consumer interaction agents can be utilized much more effectively to revive dead leads.

A set of partial words is received. At least one partial word in the set of partial words is completed. The set of partial words with the at least one completed partial word is run through a trained deep neural network, the trained deep neural network inferring a word embedding associated with an unfinished word in the set of partial words. An inferred word is determined based on the inferred word embedding associated with the unfinished word. A sentence may be output, which includes at least the completed partial word and the inferred word.

Systems and processes for multi-modal input interpretation are provided. For example, an input associated with a touch is received from a user. A first reconstruction based on the input is determined. A first simulated input is obtained based on a modification of the input. A second reconstruction is determined based on the first reconstruction and the first simulated input. Based on at least the first reconstruction and the second reconstruction, a probability representation is obtained. An output is determined, by a language model, based on the probability representation. The output is then provided to the user.

Systems and processes for multi-modal input interpretation are provided. For example, an input associated with a touch is received from a user. A first reconstruction based on the input is determined. A first simulated input is obtained based on a modification of the input. A second reconstruction is determined based on the first reconstruction and the first simulated input. Based on at least the first reconstruction and the second reconstruction, a probability representation is obtained. An output is determined, by a language model, based on the probability representation. The output is then provided to the user.

Generating text suggestions based on context can leverage sources associated with the context to generate more accurate and informed text suggestions. For example, the context can be a user situation, such as the user is attending a meeting. Obtaining text from sources associated with the user situation can generate a corpus of text that can be leveraged for generating the context-based text suggestions.

Generating text suggestions based on context can leverage sources associated with the context to generate more accurate and informed text suggestions. For example, the context can be a user situation, such as the user is attending a meeting. Obtaining text from sources associated with the user situation can generate a corpus of text that can be leveraged for generating the context-based text suggestions.

Translation capability for language processing determines an existence of an abbreviation, followed by non-exact matching to map the abbreviation to the original full term. A received string in a source language is provided as input to a translation service. Translation proposals in a different target language are received back. A ruleset (considering factors, e.g., camel case format, the presence of a concluding period, and/or consecutive consonants) is applied to generate abbreviation candidates from the translation proposals. Non-exact matching (referencing e.g., a comparison metric) may then be used to map the abbreviation candidates to text strings of their original full terms. A mapping of the abbreviation to the text string of the original full term is stored in a translation database comprising linguistic data. Embodiments leverage existing resources (e.g., translation service, non-exact matching) to reduce effort and expense of accurately identifying abbreviations and then mapping them to their full original terms.

Translation capability for language processing determines an existence of an abbreviation, followed by non-exact matching to map the abbreviation to the original full term. A received string in a source language is provided as input to a translation service. Translation proposals in a different target language are received back. A ruleset (considering factors, e.g., camel case format, the presence of a concluding period, and/or consecutive consonants) is applied to generate abbreviation candidates from the translation proposals. Non-exact matching (referencing e.g., a comparison metric) may then be used to map the abbreviation candidates to text strings of their original full terms. A mapping of the abbreviation to the text string of the original full term is stored in a translation database comprising linguistic data. Embodiments leverage existing resources (e.g., translation service, non-exact matching) to reduce effort and expense of accurately identifying abbreviations and then mapping them to their full original terms.

A computer-implemented example generator is described which has a memory storing a text item, examples of use of the text item having been requested. A processor searches at least one n-gram language model to identify n-grams containing the text item. The processor is configured to rank the identified n-grams on the basis of a position of the text item in the identified n-grams; and a user interface presents at least some of the identified n-grams to a user taking into account the ranking.

A computer-implemented example generator is described which has a memory storing a text item, examples of use of the text item having been requested. A processor searches at least one n-gram language model to identify n-grams containing the text item. The processor is configured to rank the identified n-grams on the basis of a position of the text item in the identified n-grams; and a user interface presents at least some of the identified n-grams to a user taking into account the ranking.