30 items found

Tags: Text mining

Filter Results

  • Access required...

    ×

    Method

    Private Cybersecurity NER BERT-base-cased model

    This method includes a Python script and files of a BERT-base-cased model fine-tuned on our Cybersecurity NER dataset. The method requires as input a list of sentences that...
  • Method

    Cybersecurity NER RoBERTa-base model

    This method includes a Python script and files of a RoBERTa-base model fine-tuned on our Cybersecurity NER dataset. The method requires as input a list of sentences that will...
    • JSON
      The resource: 'config' is not accessible as guest user. You must login to access it!
    • TXT
      The resource: 'merges' is not accessible as guest user. You must login to access it!
    • BIN
      The resource: 'model' is not accessible as guest user. You must login to access it!
    • JSON
      The resource: 'model_args' is not accessible as guest user. You must login to access it!
    • ZIP
      The resource: 'scheduler' is not accessible as guest user. You must login to access it!
    • JSON
      The resource: 'special_tokens_map' is not accessible as guest user. You must login to access it!
    • JSON
      The resource: 'tokenizer_config' is not accessible as guest user. You must login to access it!
    • ZIP
      The resource: 'training_args' is not accessible as guest user. You must login to access it!
    • JSON
      The resource: 'tokenizer' is not accessible as guest user. You must login to access it!
    • JSON
      The resource: 'vocab' is not accessible as guest user. You must login to access it!
    • ZIP
      The resource: 'optimizer' is not accessible as guest user. You must login to access it!
    • py
      The resource: 'inference' is not accessible as guest user. You must login to access it!
  • Dataset

    Santorini Tweets July-August 2021

    This dataset contains 225.501 tweets written by 141.277 users. These tweets are geolocated in Santorini, or they contain the word or the hashtag "santorini" in the text. They...
    • ZIP
      The resource: 'tweet_santorini.csv' is not accessible as guest user. You must login to access it!
  • Dataset

    FANCY Dataset

    (NLI) FANCY (FActivity, Negation, Common-sense, hYpernimy) is a new dataset with 4000 sentence pairs concerning complex linguistic phenomena such as factivity, negation,...
    • The resource: 'FANCY Dataset' is not accessible as guest user. You must login to access it!
  • Dataset

    SWH Filenames

    A 69 GB dataset with ~2.3 billion strings representing deduplicated names of source code files collected by Software Heritage, the great library of source code...
    • ZIP
      The resource: 'SWH Filenames' is not accessible as guest user. You must login to access it!
  • Method

    Quantum Distance-Based Classifier

    The Quantum Distance-Based Classifier is a technique inspired by the classical k-Nearest Neighbors that leverages quantum properties to perform prediction.
  • Method

    CLiQS

    CLiQS is a Python language software package for social media texts summarization with a diversified approach.
    • The resource: 'CLiQS-CM' is not accessible as guest user. You must login to access it!

  • Access required...

    ×

    Method

    Private Distributed W2V

    Accelerated training of Word Embeddings for large text corpora. Creates a word2vec-model from an input corpus of tokenized texts through the use of parallel distributed...
  • Dataset

    Conversational search dataset with labels

    CAsT 2019 data is split into two files one for training and the other one for testing. - Training set: CAsT 2019 conversations from training set and from test set without...
    • The resource: 'Conversational dataset ...' is not accessible as guest user. You must login to access it!
  • Dataset

    Dataset for Evaluating Abstractive Summaries of Crisis-Related Social Media

    The dataset created for evaluation of summaries generated from social media posted during five natural disasters. The dataset contains: ground truth reports created by human...
    • The resource: 'Dataset for Evaluating ...' is not accessible as guest user. You must login to access it!
  • Dataset

    WIRE dataset

    This dataset consists of 503 pairs of Wikipedia entities drawn from the New York Times dataset with a human assigned relatedness score. The domain experts based their...
    • HTML
      The resource: 'WikipediaRelatedness' is not accessible as guest user. You must login to access it!
    • CSV
      The resource: 'WIRE dataset' is not accessible as guest user. You must login to access it!
  • Method

    Ariadne English Dendrochronology Entity Recognizer

    Identifies terms and phrases in English for analysing archaeological text. The method delivers named entities of archaeological elements, wood material, sample, and date, with...
    • method-engine
      The resource: 'Method Engine' is not accessible as guest user. You must login to access it!
  • Method

    Ariadne Dutch Dendrochronology Entity Recognizer

    Identifies terms and phrases in Dutch for analysing archaeological text. The method delivers named entities of archaeological elements, wood material, sample, and date, with...
    • method-engine
      The resource: 'Method Engine' is not accessible as guest user. You must login to access it!
  • Dataset

    Amazon reviews

    This (link to the) dataset contains product reviews and metadata from Amazon, including 142.8 million reviews spanning May 1996 - July 2014. This dataset includes reviews...
    • HTML
      The resource: 'Julian McAuley's repository.' is not accessible as guest user. You must login to access it!
  • Dataset

    Cross-Lingual Dataset of Crisis-Related Social Media

    If you use this dataset, please cite the following paper: Fedor Vitiugin, Carlos Castillo: Cross-Lingual Query-Based Summarization of Crisis-Related Social Media: An Abstractive...
    • The resource: 'Cross-Lingual Dataset of ...' is not accessible as guest user. You must login to access it!
  • Method

    Dictionary creator

    This tool creates a dictionary with inverse document frequency (idf) values from the Google NGrams dataset.
    • The resource: 'Source code' is not accessible as guest user. You must login to access it!
  • Method

    GATE Cloud Chemical Entity Recogniser

    This service annotates chemical named entities using the open source OSCAR4 tagger. As well as the names of the detected entities the tagger also returns their structure in...
    • method-engine
      The resource: 'Method Engine' is not accessible as guest user. You must login to access it!
  • Method

    Ariadne Swedish Archaeology Named Entity Recognizer

    Identifies terms and phrases in Swedish for analysing archaeological text. The method delivers named entities of archaeological context, physical object, material, time...
    • method-engine
      The resource: 'Method Engine' is not accessible as guest user. You must login to access it!
  • Dataset

    The Italian Music Dataset

    The dataset is built by exploiting the Spotify and SoundCloud APIs. It is composed of over 14,500 different songs of both famous and less famous Italian musicians. Each song...
    • JSON
      The resource: 'Dataset' is not accessible as guest user. You must login to access it!
  • Method

    Ariadne Swedish Dendrochronology Entity Recognizer

    Identifies terms and phrases in Swedish for analysing archaeological text. The method delivers named entities of archaeological elements, wood material, sample, and date, with...
    • method-engine
      The resource: 'Method Engine' is not accessible as guest user. You must login to access it!