Natural Language APIs is a collection of APIs that convert unstructured data to structured data in Natural Language Processing. The Language APIs can analyze text and help you to understand its entities, attributes, relations and more.
The Entity Discovery API seeks to locate and classify named entities in text into pre-defined categories such as persons, locations, organizations, etc. The entity discovery API takes raw text as input, and return all the entities' name with its location and entity label. More particularly, we provide the discovery of disease and chemical entities in biomedical domain.
Input: raw text
Input Format: Json
Output: entity name with it's offset in the text and entity label.
Output Format: Json
URL: https://api.ksstudio.org/entitydiscovery
Example
The Entity Linking API accepts the text of a document as input. It first calls entity discovery to find the entity mentions in the document and then link those mentions to the corresponding entities in knowledge bases. We link the entity mentions to three knowledge bases: Wikipedia, MeSH and ChEBI. This API is particularly useful when the name string of a mention can refer to several different entities, e.g. "Clinton" may refer to Hillary Clinton or Bill Clinton. In this case we will try to offer a result that fits the context.
Input: raw text
Input Format: Json
Output: A list of entity mention information. For each entity mention, the output contains its position in the input text, its type and the ID of its refferred entity in knowledge base (KB). Since we link mentions to three KB's (Wikipedia, MeSH, ChEBI), the ID of a particular KB is presented only if the mention can be linked to that knowledge base.
Output Format: Json
URL: http://api.ksstudio.org/entitylinking
Example
The Slot Filling API accept the text of a document as input. We find the candidates among the document and then label these sentences. Our system is able to return the Chemical Induced Diseases.
Input: raw text
Input Format: Json
Output: the Chemical Induced Diseases.
Output Format: Json
URL: http://api.ksstudio.org/slotfilling
Example
The Open domain information extraction API extracts the relation tuples, typically binary relations, from plain text. The central difference is that the schema for these relations does not need to be specified in advance; typically the relation name is just the text linking two arguments. For example, Barack Obama was born in Hawaii would create a triple (Barack Obama; was born in; Hawaii), corresponding to the open domain relation was-born-in (Barack-Obama, Hawaii).
Input: raw text
Input Format: Json
Output: open domain relation triplets.
Output Format: Json
URL: https://api.ksstudio.org/openie
Example
Enter the entity name, return the entity list, click on the entity, and return the corresponding Infobox and summary.
输入一段文章和一个问题，返回相应的候选答案和分数。
