ANNIE Named Entity Recognizer The ANNIE named entity recognition service. Identifies names of persons, locations, organizations, as well as money amounts, time and date expressions.
Standard quota: 1,200 calls / 24h
TwitIE Named Entity Recognizer for Tweets Named entity recognition service for Twitter data. Identifies person,location, organization etc. and also performsnormalization of abbreviations and common shorthands ("brb", "gr8", "2day",etc.).
Standard quota: 1,200 calls / 24h
YODIE Named Entity Disambiguation (English) Identifies named entities of various types in English documents, and disambiguates them against DBpedia.
Standard quota: 800 calls / 24h
YODIE Named Entity Disambiguation (German) Identifies named entities of various types in German documents, and disambiguates them against DBpedia.
Standard quota: 800 calls / 24h
YODIE Named Entity Disambiguation (French) Identifies named entities of various types in French documents, and disambiguates them against DBpedia.
Standard quota: 800 calls / 24h
YODIE Named Entity Disambiguation (Spanish) Identifies named entities of various types in Spanish documents, and disambiguates them against DBpedia.
Standard quota: 800 calls / 24h
BioYODIE Named Entity Disambiguation (MeSH only) Identifies biomedical named entities of various types, and disambiguates them against UMLS (Medical Subject Headings subset only).
Standard quota: 800 calls / 24h
BioYODIE Named Entity Disambiguation (Snomed only) Identifies biomedical named entities of various types, and disambiguates them against UMLS (Snomed subset only).
Standard quota: 800 calls / 24h
BioYODIE Named Entity Disambiguation Identifies biomedical named entities of various types, and disambiguates them against UMLS.
Standard quota: 800 calls / 24h
German Named Entity Recognizer A named entity recognition service for documents in German. Based on ANNIE, it identifies names of persons, locations, and organizations.
Standard quota: 1,200 calls / 24h
spaCy English Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for English.
Standard quota: 1,200 calls / 24h
spaCy German Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for German.
Standard quota: 1,200 calls / 24h
spaCy Greek Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for Greek.
Standard quota: 1,200 calls / 24h
spaCy Spanish Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for Spanish.
Standard quota: 1,200 calls / 24h
spaCy French Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for French.
Standard quota: 1,200 calls / 24h
spaCy Italian Named Entity Recognition Annotates documents using the spaCy Named Entity Recognition component for Italian.
Standard quota: 1,200 calls / 24h
Language Identification for Tweets Service to identify the languages of tweets.
Standard quota: 1,200 calls / 24h
English Tweet Tokenizer Identifies words and punctuation in tweets
Standard quota: 1,200 calls / 24h
French Named Entity Recognizer A named entity recognition service for documents in French. Based on ANNIE, it identifies names of persons, locations, and organizations.
Standard quota: 1,200 calls / 24h
Part-of-Speech Tagger for Tweets A service that tags tweets with part-of-speech information, e.g. nouns, verbs.
Standard quota: 1,200 calls / 24h
Romanian Named Entity Recognizer A named entity recognition service for documents in the Romanian language. Based on ANNIE, it identifies names of persons, locations, organizations, as well as money amounts, time and date expressions.
Standard quota: 1,200 calls / 24h
Russian Named Entity Recognizer (basic) A named entity recognition service for documents in the Russian language. Based on ANNIE, it identifies names of persons, locations, organizations, as well as money amounts, time and date expressions.
Standard quota: 1,200 calls / 24h
Russian NER (with inflexional gazetteer and orthomatcher) A named entity recognition service for documents in the Russian language. Based on ANNIE, it identifies names of persons, locations, organizations, as well as money amounts, time and date expressions.
Standard quota: 1,200 calls / 24h
CYMRIE Welsh Named Entity Recognizer The CYMRIE named entity recognition service for Welsh text. Identifies namesof persons, locations, organizations, as well asmoney amounts, time and date expressions.
Standard quota: 1,200 calls / 24h
French Named Entity Recognizer for Tweets Analyse French tweets for names of persons, locations and organizations. Also performs normalization of abbreviations and common Twitter slang.
Standard quota: 1,200 calls / 24h
German Named Entity Recognizer for Tweets Analyse German tweets for names of persons, locations and organizations. Also performs normalization of abbreviations and common Twitter slang.
Standard quota: 1,200 calls / 24h
Social Media Tokenizer: French A tokenizer for French social media text that handles hashtags and user mentions etc.
Standard quota: 1,200 calls / 24h
Social Media Tokenizer: German A tokenizer for German social media text that handles hashtags and user mentions etc.
Standard quota: 1,200 calls / 24h
English Part-of-Speech and Morphology Analyzer Annotates tokens and sentences in English text, adding part-of-speech and morphological root and affix to each token.
Standard quota: 1,200 calls / 24h
Noun Phrase Chunker Base Noun Phrase Chunker, producing NounChunk annotations.
Standard quota: 1,200 calls / 24h
Measurement Expression Annotator Annotates numbers and measurement expressions, with their normalised values in SI units.
Standard quota: 1,200 calls / 24h
ANNIE+Measurements Annotates named entities (person, location, organization, date) as well as numbers and measurement expressions.
Standard quota: 1,200 calls / 24h
Generic Opinion Mining (English) Recognises opinionated sentences in English text and classifies them as positive or negative. It also indicates emotion type, author and target of the opinion, average sentiment, nd some sentence types.
Standard quota: 1,200 calls / 24h
DecarboNet Environmental Annotator The DecarboNet environmental annotation service. Identifies named entities, environmental terms, linguistic features and sentiment in social media texts.
Standard quota: 1,200 calls / 24h
DecarboNet German Environmental Annotator The DecarboNet environmental annotation service. Identifies named entities, environmental terms, and sentiment in German language social media texts.
Standard quota: 1,200 calls / 24h
Twitter Opinion Mining (English) Recognises opinionated sentences in English tweets and classifies them as positive or negative. It also indicates emotion type, author and target of the opinion, and some sentence types.
Standard quota: 1,200 calls / 24h
Rumour veracity classifier [DEPRECATED] Classifies tweets based on whether the claims they make are true, false or unverifiable.
Standard quota: 1,200 calls / 24h
Hyperpartisan scorer Estimates the probability that a document could be classed as "hyper-partisan".
Standard quota: 600 calls / 24h
Journalist Safety Analyser Annotates descriptions of violations against journalists such as killings, threats etc. Identifies key information about the event and people involved.
Standard quota: 1,200 calls / 24h
Stance Classification: English Classifies a reply to a tweet based on its stance (support, deny, query, or comment) to the original
Standard quota: 1,200 calls / 24h
GATE Hate for Politics [DEPRECATED] A service that tags abusive utterances. It will also tag UK members of parliament from 2015 to 2020, a range of politically relevant topics, and entities such as persons, locations, organizations and Twitter entities such as hashtags and user mentions.
Standard quota: 1,200 calls / 24h
COVID-19 Claim Categoriser Assigns claims about COVID-19 to one of several categories, including government actions, impact on community, medical advice, conspiracy theories, vaccine, etc.
Standard quota: 1,200 calls / 24h
Stance Classification: Multilingual Classifies a reply to a tweet based on it's stance (support, deny, query, or comment) to the original
Standard quota: 1,200 calls / 24h
Toxic Language Classifier A classifier that labels text as being toxic or not.
Standard quota: 1,200 calls / 24h
Offensive Language Classifier A classifier that labels text as being offensive or not.
Standard quota: 1,200 calls / 24h
URL Domain Analysis Annotates URLs to highlight potential credibility information on the domain at which they ultimately point.
Standard quota: 1,200 calls / 24h
COVID-19 Vaccine Text Categoriser Assigns COVID-19 vaccine information to one of several categories, including Safety Efficacy and Necessity, Development Provision and Access, Politics and Economics, Liberty/Freedom, Conspiracy, Morality Religiosity and Ethics
Standard quota: 1,200 calls / 24h
GATE Hate Analyses text to find abusive phrases and attempts to determine who the abuse is aimed at. As well as finding abusive phrases it tags standard named entities, UK political topics/entities and, when processing Tweets, hashtags and user mentions.
Standard quota: 1,200 calls / 24h
Multi-Lingual OCR Service A multi-lingual OCR service that detects areas of text, extracts the text from each area, and then determines the language of each block of text.
Standard quota: 150 calls / 24h
Chemical Named Entity Recognizer A chemical named entity tagger based around OSCAR4.
Standard quota: 1,200 calls / 24h
ChemDataExtractor Extracts chemical named entities from text using ChemDataExtractor.
Standard quota: 1,200 calls / 24h
Political Abuse Monitor A service which finds abusive utterances and idenitifies the politicians being abused. It currently knows abouut UK MPs from 2015 to 2022 and members of the Irish Dáil Éireann from 20th February 2020.
Standard quota: 1,200 calls / 24h
Anglo-Irish Politics Monitor A service which annnotates entities relating to politics in both the UK and Ireland. This includes politicians, government organizations, and related topics.
Standard quota: 1,200 calls / 24h
Multilingual News Article Framing Classifier A news article can address a story from a number of different perspectives or "frames". This service identifies the main frames used in a particular article.
Standard quota: 1,200 calls / 24h
Multilingual Persuasion Technique Classifier Identifies persuasion techniques used in documents.
Standard quota: 1,200 calls / 24h
Target Oblivious Stance Classification Classifies a reply to a tweet based on its stance (support, deny, query, or comment) to the original, without needing access to the orignal tweet.
Standard quota: 1,200 calls / 24h
Multilingual News Genre Classifier Identifies the main news genre that a text belongs to.
Standard quota: 1,200 calls / 24h
Multilingual Persuasion Technique Classifier (spans) Identifies persuasion techniques in sentences.
Standard quota: 1,200 calls / 24h
Crop Pest Text Classifier Detect crop pests and diseases mentioned in the text, and the impact of the pest or disease on the crop.
Standard quota: 150 calls / 24h
Vaccine Hesitancy Classifier [DEPRECATED] Classifies documents based on hesitancy towards COVID-19 vaccination.
Standard quota: 1,200 calls / 24h
EDMO Ireland Stance Classifier Classifies a reply to a tweet based on its stance (support, deny, query, or comment) to the original -- this version is tuned to the rumours and topics that are of interest to Irish citizens and stakeholders.
Standard quota: 1,200 calls / 24h
Multilingual Rumour veracity classifier Classifies tweets based on whether the claims they make are true, false or unverifiable.
Standard quota: 1,200 calls / 24h
Multilingual Vaccine Hesitancy Classifier Classifies documents based on hesitancy towards COVID-19 vaccination.
Standard quota: 1,200 calls / 24h
GeoNames Geolocation Recognizer Identifies geographical named entities and disambiguates them against GeoNames.
Standard quota: 150 calls / 24h
Pleiades Geolocation Recognizer Identifies geographical named entities and disambiguates them against Pleiades.
Standard quota: 150 calls / 24h
Geonames Geolocation Recognizer (Gazetteer) Identifies geographical named entities and disambiguates them against Geonames using a gazetteer based approach.
Standard quota: 150 calls / 24h
 The "Brexit Analyzer" Pipeline A service for analysing tweets about the UK's referendum on EU membership. It identifies topics, hashtags, user mentions, and voting intention (where possible).
Standard quota: 1,200 calls / 24h
The Political Futures Pipeline A service for analysing tweets about UK politics. It identifies topics, politicians, sentiment, abuse terms and more.
Standard quota: 1,200 calls / 24h
English Archaeology Named Entity Recognizer Identifies archaeological named entities of various types in English based on the National Cultural Heritage Thesauri and Vocabularies (UK).
Standard quota: 1,200 calls / 24h
Dutch Archaeology Named Entity Recognizer Identifies archaeological named entities of various types and relevant phrases in Dutch based on the Rijksdienst vor het Cultureel Erfgoed (RCE) Thesauri (NL).
Standard quota: 1,200 calls / 24h
Swedish Archaeology Named Entity Recognizer Identifies archaeological named entities of various types, terms and relevant phrases in Swedish based on domain specific, cultural heritage glossary.
Standard quota: 1,200 calls / 24h
English Dendrochronology Entity Recognizer A named entity recognition service for archaeology documents in English. Based on the National Cultural Heritage Thesauri and Vocabularies (UK) it identifies named entities of various types, terms and sentences relevant to dendrochology.
Standard quota: 1,200 calls / 24h
Dutch Dendrochronology Entity Recognizer A named entity recognition service for archaeology documents in Dutch. Based on the Rijksdienst vor het Cultureel Erfgoed (RCE) Thesauri (NL) it identifies named entities of various types, terms and sentences relevant to dendrochology.
Standard quota: 1,200 calls / 24h
Swedish Dendrochronology Entity Recognizer A named entity recognition service for archaeology documents in Swedish. Based on domain specific, cultural heritage glossary it identifies named entities of various types, terms and sentences relevant to dendrochology.
Standard quota: 1,200 calls / 24h
Multilingual News Similarity Service Determines the similarity between two news articles based on an embedding model, optionally supplemented with named entity information.
Standard quota: 800 calls / 24h
SUMMA Text Summarization (EN) The SUMMA Text Summarization (EN) uses the SUMMA toolkit developed by Horacio Saggion to provide a generic English document summarizer.
Standard quota: 1,200 calls / 24h
SUMMA Text Summarization (ES) The SUMMA Text Summarization (ES) uses the SUMMA toolkit developed by Horacio Saggion to provide a generic Spanish document summarizer.
Standard quota: 1,200 calls / 24h
OpenNLP English Pipeline The English tokeniser, sentence splitter, POS tagger, phrase chunker and named-entity recogniser from Apache OpenNLP.
Standard quota: 1,200 calls / 24h
OpenNLP German Pipeline The German tokeniser, sentence splitter and POS tagger from Apache OpenNLP.
Standard quota: 1,200 calls / 24h
OpenNLP Dutch Pipeline The Dutch tokeniser, sentence splitter, POS tagger, phrase chunker and named-entity recogniser from Apache OpenNLP.
Standard quota: 1,200 calls / 24h
Twitter user classification A service to classify the author of a tweet as either a person, organization or location, of various sub-types. Note: can only operate on Twitter JSON documents.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for en / English Universal Dependencies POS tagger for en / English based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for bg / Bulgarian Universal Dependencies POS tagger for bg / Bulgarian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for cs / Czech Universal Dependencies POS tagger for cs / Czech based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for pl / Polish Universal Dependencies POS tagger for pl / Polish based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for ca / Catalan Universal Dependencies POS tagger for ca / Catalan based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for da / Danish Universal Dependencies POS tagger for da / Danish based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for el / Greek Universal Dependencies POS tagger for el / Greek based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for es / Spanish Universal Dependencies POS tagger for es / Spanish based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for et / Estonian Universal Dependencies POS tagger for et / Estonian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for eu / Basque Universal Dependencies POS tagger for eu / Basque based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for fi / Finnish Universal Dependencies POS tagger for fi / Finnish based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for fr / French Universal Dependencies POS tagger for fr / French based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for hr / Croatian Universal Dependencies POS tagger for hr / Croatian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for id / Indonesian Universal Dependencies POS tagger for id / Indonesian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for lv / Latvian Universal Dependencies POS tagger for lv / Latvian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for nl / Dutch Universal Dependencies POS tagger for nl / Dutch based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for pt / Portugese Universal Dependencies POS tagger for pt / Portugese based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for ro / Romanian Universal Dependencies POS tagger for ro / Romanian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for ru / Russian Universal Dependencies POS tagger for ru / Russian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for sk / Slovak Universal Dependencies POS tagger for sk / Slovak based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for sl / Slovenian Universal Dependencies POS tagger for sl / Slovenian based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h
Universal Dependencies POS Tagger for sv / Swedish Universal Dependencies POS tagger for sv / Swedish based on a simple window-based maximum entropy model.
Standard quota: 1,200 calls / 24h