NLP Startup

Natural Language Processing and Text Analysis at NLP Startup Fast Data Science

We focus mainly on natural language processing (NLP), although we are also active in other areas of data science. The manager, Thomas Wood, studied a Masters in Computer Speech, Text and Internet Technology in 2008 at Cambridge University and since then he has been working exclusively in machine learning and mostly in natural language processing. In 2018 he founded the startup Fast Data Science Ltd, with an aim of delivering NLP consultancy to large organisations.

We have built NLP processing pipelines from scratch, and worked on natural language dialogue systems, document classifiers and text-based recommendation engines. For these tasks, we use both traditional machine learning techniques as well as cutting-edge technology such as neural networks. We normally use Python as a programming language of choice but we are flexible according to your organisation’s technology.

What an NLP startup does

As an NLP startup, we take on consulting work in all areas of NLP including the following:

Document classification – assign a document to one of many categories
Natural language understanding – understand the meaning of an utterance by a human
Text analysis – for example, identify common topics in factory error reports
Document anonymisation – make sensitive documents GDPR or HIPAA compliant
Topic analysis – clustering
Document-based recommender systems
Natural language dialogue systems
Unstructured data analysis

Unstructured data and NLP

Today many companies, in particular in certain industries such as healthcare, pharmaceuticals, legal, and insurance, must process amounts of unstructured data. This data is often in text format, maybe even unscanned documents, PDFs, HTML, or any other file type.

Unstructured data is very difficult to deal with but can contain a goldmine of information when handled with the appropriate NLP approaches. NLP startups like Fast Data Science specialise in extracting value from companies’ unstructured datasets.

Natural Language Processing applications in healthcare

The healthcare sector is increasingly turning to NLP startups such as Fast Data Science for consulting and assistance in adopting AI and natural language processing. NLP technologies in healthcare would fall under the umbrella of healthtech or MedTech. NLP startups are using the technology to compare and detect changes in clinical reports, extract clinical concepts such as MeSH terms from electronic medical records, and develop human-to-machine natural language dialogue systems to improve the healthcare experience.

We have worked on a number of projects in healthcare, including:

a model to predict the complexity of clinical trials from the trial protocol for Boehringer Ingelheim.
a desktop application to analyse researchers’ outputs, fields, collaborations and affiliations using PubMed search result exports.
a model to identify researchers who have used open sourced molecules in their published research without attribution, also for Boehringer Ingelheim.

Natural Language Processing technologies at Fast Data Science

We do a lot of natural language processing with Python. We have worked on a variety of NLP models, including:

Bag of words, tf*idf, cosine similarity
NLP pipelines, lemmatisation, parsers, chunkers
Deep neural networks
- convolutional neural networks (text as well as images)
- RNN, LSTM
- Seq2seq, word2vec, doc2vec
- see a live demo of a CNN for author identification
Clustering: Latent Dirichlet Allocation
- This is useful for extracting topics from a set of unstructured documents, for example legal documents, survey responses, factory error reports, etc.
Search engines and search term recommenders
Google Natural Language, AWS, Microsoft Azure

Topic detection is an NLP technique that allows you to discover common themes in a set of unstructured documents.

Python and R for NLP

We work with the following programming languages and frameworks:

TensorFlow
Keras
Python NLTK
R

Past projects at NLP startup Fast Data Science

Some of our past NLP projects include:

a spoken dialogue system to control a smart home
an unsupervised text analysis program to analyse text descriptions of manufacturing defects (for the German pharma company Boehringer Ingelheim)
a model to classify jobseekers’ CVs into industries and salary bands (CV-Library).
analysis of survey responses for the American nonprofit White Ribbon Alliance

NLP Startup Fast Data Science

How can I find an NLP startup? If you are interested in locating NLP startups in a particular region, CrunchBase is a good place to start: List of UK-based NLP startups.

Fast Data Science Ltd is a leading NLP startup company in the UK. We offer consulting in Natural Language Processing and Data Science. We have primarily Oxbridge educated, Microsoft certified professionals on our staff.

Our specialist area is Natural language processing or NLP. NLP can be defined as teaching computers to communicate with humans by means of human languages, such as English. Fast Data Science offers consulting in all areas of NLP.

We help our clients to extract value from unstructured data, such as long PDF documents. We target a variety of industries including legal, insurance, healthcare, and pharma. In fact, any industry where text data is commonplace. For example, a client may have a dataset of 1 million text documents in plain English, such as clinical trial protocols, vehicle inspection reports, medical records, or similar. It can be a daunting endeavour to read through such large datasets manually and that is where an NLP startup such as Fast Data Science Ltd gets involved.

NLP startup Fast Data Science offers bespoke Natural Language Processing consulting

NLP startup Fast Data Science offers Natural Language Processing consulting