Natural language processing (NLP) with awareness of textual polarity. An NLP system, such as a search engine or a Question-Answering (QA) system receives input text for processing. The input text may be a text fragment, a search phrase, a question having a general type, or a polar question having a yes or no answer. The NLP system identifies textual polarity and provides responses to the input text (for example, in answer form) based on identifying evidence whose selection, scoring, and processing, is informed by the textual polarity of the input text, and the textual polarity of candidate evidence passages.

Systems and methods are disclosed for providing automated assistance for a user by receiving a user request for assistance from an appliance with a microphone and speaker and plugged into an electrical grid; translating the request to a language and determining semantics of the user request and identifying at least one domain, at least one task, and at least one parameter for the user request; searching a semantic database on the Internet for the at least one matching domain, task, and parameter; and accessing semantic data and services having one or more triples including subject, predicate, and object available over the Internet; and responding to the user request.

A system and method for processing digital multimedia files to provide searchable results includes the steps of converting a digital multimedia file to a plain text data format, annotating each word in the file with an indicator such as a time stamp to indicate where the word appears in the file, converting each indicator to an encoded indicator using characters that are not indexed by search software, indexing the converted, annotated file, storing the converted, annotated file and a file location of the converted, annotated file, receiving a query from a user's computer, and returning search results to the user's computer that include search snippets comprising unindexed portions of one or more files considered responsive to the query and the file location of those files.

Natural language processing (NLP) with awareness of textual polarity. An NLP system, such as a search engine or a Question-Answering (QA) system receives input text for processing. The input text may be a text fragment, a search phrase, a question having a general type, or a polar question having a yes or no answer. The NLP system identifies textual polarity and provides responses to the input text (for example, in answer form) based on identifying evidence whose selection, scoring, and processing, is informed by the textual polarity of the input text, and the textual polarity of candidate evidence passages.

According to one embodiment, a foreign language service assisting apparatus is provided with first and second acquisition units, a translation unit, a presentation unit and an accepting unit. The first acquisition unit acquires first information on a first article. The second acquisition unit acquires second information on second articles associated with the first article, and subsequent speech candidates expected to be spoken, based on the first information. The translation unit translates the first information, the second information, and the candidates. The presentation unit presents translation result. The accepting unit accepts selection associated with the first or second articles or the candidate.

A system and method for processing audio text files includes a content repository storing audio text files. A text transformer linguistically analyzes the audio text files within a content of multiple lexicons to form edited text results and creates a reflection repository having reflection files therein corresponding to the audio text files from the edited text results. A search engine searches the reflection files and a user device displays a first reflection file from the reflection files or a first audio text file from the audio files in response to searching.

An input method editor (IME) is associated with a local user. Memory stores local data and a processor, coupled to the memory, is configured to receive input from a local, first user, obtain shared data associated with at least a remote, second user from a remote server and generate prediction candidates and conversion candidates based on the input provided by the local, first user and correlation of the input and the obtained shared data.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for content evaluation. In one aspect, a method includes identifying a first document object model for a resource, the first document object model being associated with a performance profile, the performance profile specifying performance factors for content item presentation positions of the resource. A first similarity measure can be computed for first document object model based on the first document object model and a second document object model for the resource, the second document object model for the resource being a previous document object model for the resource. A new performance profile can be computed for the resource if the first similarity measure does not meet a similarity threshold.

A method of creating an electronic file corresponding to a printed artifact may include receiving an image file of a document page. The method may include analyzing the image file to detect a potential form identifier on the document page and automatically (without human intervention) performing a search to identify an actual form that corresponds to the potential form identifier. The method may further include validating that the image file is of a document page that corresponds to the actual form, locating a probable fill-in field on the document page and mapping the probable fill-in field to an actual fill-in field of the actual form.

Systems and processes are disclosed for predicting words in a text entry environment. Candidate words and probabilities associated therewith can be determined by combining a word n-gram language model and a unigram language model. Using the word n-gram language model, based on previously entered words, candidate words can be identified and a probability can be calculated for each candidate word. Using the unigram language model, based on a character entered for a new word, candidate words beginning with the character can be identified along with a probability for each candidate word. In some examples, a geometry score can be included in the unigram probability related to typing geometry on a virtual keyboard. The probabilities of the n-gram language model and unigram model can be combined, and the candidate word or words having the highest probability can be displayed for a user.