Abstract: Certain embodiments involve creating multimedia content with text and media assets that illustrate the text. Multiple sentences are ranked on various features. A sentence ranking is determined based on, for example, the presence of important phrases in the sentence, the degree to which informational content of the sentence can be represented through a media asset, the presence of one or more sentiments associated with the sentence, and the readability of the sentence. In some examples, the ranked sentences are analyzed to determine similar information content, and the sentences are re-ranked based on this analysis. A subset of the ranked sentences with higher ranks are analyzed to determine similarities between content in the sentence and text descriptions of media assets. This analysis can be used to select appropriate images or other media assets. Multimedia content is generated in which the selected media assets are positioned near the set of sentences.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.

Abstract: Certain embodiments involve creating multimedia content with text and media assets that illustrate the text. Multiple sentences are ranked on various features. A sentence ranking is determined based on, for example, the presence of important phrases in the sentence, the degree to which informational content of the sentence can be represented through a media asset, the presence of one or more sentiments associated with the sentence, and the readability of the sentence. In some examples, the ranked sentences are analyzed to determine similar information content, and the sentences are re-ranked based on this analysis. A subset of the ranked sentences with higher ranks are analyzed to determine similarities between content in the sentence and text descriptions of media assets. This analysis can be used to select appropriate images or other media assets. Multimedia content is generated in which the selected media assets are positioned near the set of sentences.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.