Misplaced Pages

#87912

22-416: The application uses a natural language user interface to answer questions, make recommendations , and perform actions by delegating requests to various applications. Vlingo Find and other iterations were known as first-to-market innovators in speech-to-text recognition. With adaptive hierarchical language models, Vlingo improves its speech-to-text recognition as it learns a user's speech and search habits. It

44-570: A search engine would. It was announced in March 2009 by Stephen Wolfram , and was released to the public on May 15, 2009. Siri is an intelligent personal assistant application integrated with operating system iOS . The application uses natural language processing to answer questions and make recommendations. Siri's marketing claims include that it adapts to a user's individual preferences over time and personalizes results, and performs tasks such as making dinner reservations while trying to catch

66-401: A cab. Semantic ambiguity In linguistics , an expression is semantically ambiguous when it can have multiple meanings. The higher the number of synonyms a word has, the higher the degree of ambiguity. Like other kinds of ambiguity , semantic ambiguities are often clarified by context or by prosody . One's comprehension of a sentence in which a semantically ambiguous word is used

88-473: A lexical ambiguity results from a single word having two senses, it is called polysemy . For instance, the English "foot" is polysemous since in general it refers to the base of an object, but can refer more specifically to the foot of a person or the foot of a pot . When an ambiguity instead results from two separate words which happen to be pronounced the same way, it is called homonymy . For instance,

110-514: A number of companies, including Yahoo , Samsung , RIM , and Nokia . Vlingo ships by default on Samsung Galaxy S2 devices, and Vlingo worked with Samsung to create S Voice personal assistant (available on the Samsung Galaxy S3 and newer Samsung Galaxy devices.) Vlingo also powered early versions of Siri (before Siri was acquired by Apple). Nuance Communications , a large software company, had been trying to acquire Vlingo since

132-408: A traditional keyword search engine could be described as a "shallow" natural-language user interface. A natural-language search engine would in theory find targeted answers to user questions (as opposed to keyword search). For example, when confronted with a question of the form 'which U.S. state has the highest income tax ?', conventional search engines ignore the question and instead search on

154-399: Is a collection of quick and easy natural-language-derived commands that act as mashups of web services, thus allowing users to get information and relate it to current and other webpages. Wolfram Alpha is an online service that answers factual queries directly by computing the answer from structured data, rather than providing a list of documents or web pages that might contain the answer as

176-448: Is here and another interpretation where nobody is. This ambiguity is an example of scope ambiguity , a phenomenon widely studied in formal semantics . De re/de dicto ambiguity is another notable example of sentence-level ambiguity which has received much attention in linguistics and philosophy. In some analyses, such ambiguities are the semantic reflexes of syntactic ambiguities , though in other approaches they are not. The meaning of

198-400: Is strongly influenced by the general structure of the sentence. The language itself is sometimes a contributing factor in the overall effect of semantic ambiguity, in the sense that the level of ambiguity in the context can change depending on whether or not a language boundary is crossed. Lexical ambiguity is a subtype of semantic ambiguity where a word or morpheme is ambiguous. When

220-445: The keywords 'state', 'income' and 'tax'. Natural-language search, on the other hand, attempts to use natural-language processing to understand the nature of the question and then to search and return a subset of the web that contains the answer to the question. If it works, results would have a higher relevance than results from a keyword search engine, due to the question being included. Prototype Nl interfaces had already appeared in

242-477: The English word "row" can denote the action of rowing or to an arrangement of objects. In practice, polysemy and homonymy can be difficult to distinguish. Phrases and sentences can also be semantically ambiguous, particularly when there are multiple ways of semantically combining its subparts. For instance, the English sentence "Everybody isn't here" is ambiguous between an interpretation where not everybody

SECTION 10

#1732791947088

264-714: The Year from Ovi Daily App. Winner of 2009 “Blackberry Rookie of the Year” from Handango . Winner of 2009 Mobie Award: “Best Speech Recognition”. Winner of 2011 Mashable Award: Most Innovative App. Natural language user interface Natural-language user interface ( LUI or NLUI ) is a type of computer human interface where linguistic phenomena such as verbs, phrases and clauses act as UI controls for creating, selecting and modifying data in software applications. In interface design , natural-language interfaces are sought after for their speed and ease of use, but most suffer

286-546: The area's “Best Places to Work” by BBJ in 2008. Recognized as one of the “Fierce 15” Wireless Companies of 2008 from FierceWireless. Recognized as one of ten “FiReStarters” from Future in Review in 2008. Winner of 2008 “Northeast 100 Top Private Company” from AlwaysOn. Recognized as “One of the Top Emerging Mobile Players to Watch in 2008” in 2008 from IDC. Winner of 2009 Must Have Utilities App of

308-519: The challenges to understanding wide varieties of ambiguous input . Natural-language interfaces are an active area of study in the field of natural-language processing and computational linguistics . An intuitive general natural-language interface is one of the active goals of the Semantic Web . Text interfaces are "natural" to varying degrees. Many formal (un-natural) programming languages incorporate idioms of natural human language. Likewise,

330-461: The company was founded, which Vlingo rejected. As Vlingo became successful, Nuance launched a series of patent lawsuits to attempt to weaken the company. Vlingo countered with patent lawsuits of its own. After three years of patent battles, the first lawsuit went to court and Vlingo won. At this point, Nuance increased its offer price for the company and the Vlingo board of directors agreed to sell

352-493: The company. Vlingo was acquired by Nuance in December 2011 for undisclosed terms. In January 2012 AndroidPit discovered that Vlingo sends packets of information containing the users GPS co-ordinates, IMEI (unique device identifier), contact list and the title of every song stored on the device back to Nuance without proper warning in the privacy policy . Users of Vlingo have also found the program sending data to servers at

374-696: The dhs.gov domain name. Concerning the privacy violations , Vlingo stated that the improper warnings in the privacy policies were due to some privacy policies being out of date, or correct for some versions of the app but incorrect for others. Vlingo stated that they would update the privacy policy accordingly. Furthermore, they noted that a software bug was responsible in some situations for sending more data from users’ phones to Vlingo than intended, and stated their intentions to fix such bugs immediately. Winner of 2008 Local Mobile Applications Developers Winner from AT&T . Winner of 2008 Best Mobile Application from Speech Technology Magazine. Recognized as one of

396-422: The extracted features - even from speakers who says the same word or phrase - must be successfully overcome. The natural-language interface gives rise to technology used for many different applications. Some of the main uses are: Below are named and defined some of the applications that use natural-language recognition, and so have integrated utilities listed above. Ubiquity, an add-on for Mozilla Firefox ,

418-479: The late sixties and early seventies. Natural-language interfaces have in the past led users to anthropomorphize the computer, or at least to attribute more intelligence to machines than is warranted. On the part of the user, this has led to unrealistic expectations of the capabilities of the system. Such expectations will make it difficult to learn the restrictions of the system if users attribute too much capability to it, and will ultimately lead to disappointment when

440-444: The market. In addition, localisation across multiple language sites requires extra consideration - this is based on differing sentence structure and language syntax variations between most languages. Finally, regarding the methods used, the main problem to be solved is creating a general algorithm that can recognize the entire spectrum of different voices, while disregarding nationality, gender or age. The significant differences between

462-496: The system fails to perform as expected as was the case in the AI winter of the 1970s and 80s. A 1995 paper titled 'Natural Language Interfaces to Databases – An Introduction', describes some challenges: Other goals to consider more generally are the speed and efficiency of the interface, in all algorithms these two points are the main point that will determine if some methods are better than others and therefore have greater success in

SECTION 20

#1732791947088

484-418: Was the first technology of its kind to use adaptive hierarchical language models to learn from the corrections a user would make. Vlingo servers analyze speech queries and send any recommendations or possible corrections back to the user. This technology allows users to text, search, and navigate smartphones without typing. Vlingo had its own application with over 5 million users in addition to partnerships with

#87912