Document summarizer
The presently disclosed embodiments may include a computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to: receive an identification of at least one source text document; load text of the at least one source text document; segment the text of the at least one source text document into two or more segments, generate, based on the analysis, at least one summary snippet associated with one or more portions of the text of the at least one source text document; and cause the at least one summary snippet to be shown on a display.
1 . A non-transitory computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method including:
receiving an identification of two or more source text documents;
loading text from the two or more source text documents;
receiving from a user a search query;
analyzing the search query received from the user;
generating, based on the analysis of the search query and based on information conveyed by the text from the two or more source text documents, a plurality of summary snippets associated with one or more portions of the text of the two or more source text documents, wherein the plurality of summary snippets summarize information found in the one or more portions of the text of the two or more source text documents that is also relevant to the search query; and
causing the plurality of summary snippets to be shown on a display with the text of the two or more source text documents, wherein navigation relative to the text of the two or more source text documents initiates corresponding navigation of the generated summary snippets.
2 . The non-transitory computer readable medium of claim 1 , wherein the search query includes free text including one or more words.
3 . The non-transitory computer readable medium of claim 1 , wherein the search query includes an entity identification.
4 . The non-transitory computer readable medium of claim 3 , wherein the entity identification is used to generate an entity graph relative to the two or more source text documents, and wherein the entity graph is shown on the display.
5 . The non-transitory computer readable medium of claim 1 , wherein one or more of the plurality of summary snippets includes a link to source text included in at least one of the two or more source text documents.
6 . The non-transitory computer readable medium of claim 1 , wherein the plurality of summary snippets are generated based on analysis of text segments based on segmenting the two or more source text documents.
7 . The non-transitory computer readable medium of claim 6 , wherein the segmenting of the two or more source text documents is based on at least one of a target segment length, formatting of at least one of the two or more source text documents, or semantic context of text of at least one of the two or more source text documents.
8 . The non-transitory computer readable medium of claim 1 , wherein the navigation relative to the text of the two or more source text documents is enabled by at least one scroll bar.
9 . The non-transitory computer readable medium of claim 1 , wherein the method further includes:
generating a knowledge graph of entities referenced in at least one of the two or more source text documents; and
causing a representation of the knowledge graph to be shown on the display.
10 . The non-transitory computer readable medium of claim 1 , wherein the method further includes ranking the plurality of summary snippets according to a degree to which information contained in the plurality of summary snippets is spread throughout at least one of the two or more source text documents.
11 . The non-transitory computer readable medium of claim 1 , wherein the two or more source text documents comprise at least one of a PDF document, online text document, WORD document, HTML document, or plain text document.
12 . The non-transitory computer readable medium of claim 1 , wherein the at least one of the two or more source text documents was acquired via the Internet.
13 . A method for user search queries, comprising:
receiving an identification of two or more source text documents;
loading text from the two or more source text documents;
receiving from a user a search query;
analyzing the search query received from the user;
generating, based on the analysis of the search query and based on information conveyed by the text from the two or more source text documents, a plurality of summary snippets associated with one or more portions of the text of the two or more source text documents, wherein the plurality of summary snippets summarize information found in the one or more portions of the text of the two or more source text documents that is also relevant to the search query; and
causing the plurality of summary snippets to be shown on a display with the text of the two or more source text documents, wherein navigation relative to the text of the two or more source text documents initiates corresponding navigation of the generated summary snippets.
14 . The method of claim 13 , wherein the plurality of summary snippets are generated based on analysis of text segments based on segmenting the two or more source text documents.
15 . The method of claim 13 , wherein the navigation relative to the text of the two or more source text documents is enabled by at least one scroll bar.
16 . The method of claim 13 , wherein the two or more source text documents comprise at least one of a PDF document, online text document, WORD document, HTML document, or plain text document.
17 . A system for user search queries, the system comprising at least one processor comprising circuitry and a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processor to:
receive an identification of two or more source text documents;
load text from the two or more source text documents;
receive from a user a search query;
analyze the search query received from the user;
generate, based on the analysis of the search query and based on information conveyed by the text from the two or more source text documents, a plurality of summary snippets associated with one or more portions of the text of the two or more source text documents, wherein the plurality of summary snippets summarize information found in the one or more portions of the text of the two or more source text documents that is also relevant to the search query; and
cause the plurality of summary snippets to be shown on a display with the text of the two or more source text documents, wherein navigation relative to the text of the two or more source text documents initiates corresponding navigation of the generated summary snippets.
18 . The system of claim 17 , wherein the plurality of summary snippets are generated based on analysis of text segments based on segmenting the two or more source text documents.
19 . The system of claim 17 , wherein the navigation relative to the text of the two or more source text documents is enabled by at least one scroll bar.
20 . The system of claim 17 , wherein the two or more source text documents comprise at least one of a PDF document, online text document, WORD document, HTML document, or plain text document.