For the human eye reading a CV (resume) or a job ad is an easy task. These semi-structured documents are usually separated in sections and have layouts that makes it easy to quickly identify important information. In contrast, a computer system that parses CVs needs to be continuously trained and adapted to deal with the endless expressivity of human language. As a leader in the field of language technology, Textkernel is working hard to provide the best CV parser to our customers. In this blog article I will explain how we achieve this and discuss the focus of our current research efforts.

Facebook is getting even closer to a human-level understanding of what people are saying. Facebook has developed DeepText, a new way to parse text using artificial intelligence processes that's quicker at picking up new languages and slang than traditional approaches. In a company blog post published on Wednesday, three members of the company's applied machine learning team -- Ahmad Abdulkader, Aparna Lakshmiratan and Joy Zhang -- announced the technology that's already being used across Facebook and Facebook Messenger. DeepText is able to churn through "several thousands of posts per second" across more than 20 languages and understand what's being communicated with "near-human accuracy," according to the announcement post. Facebook's ability to comprehend what people are saying on its platform isn't new.

We present a framework that couples the syntax and semantics of natural language sentences in a generative model, in order to develop a semantic parser that jointly infers the syntactic, morphological, and semantic representations of a given sentence under the guidance of background knowledge. To generate a sentence in our framework, a semantic statement is first sampled from a prior, such as from a set of beliefs in a knowledge base. Given this semantic statement, a grammar probabilistically generates the output sentence. A joint semantic-syntactic parser is derived that returns the $k$-best semantic and syntactic parses for a given sentence. The semantic prior is flexible, and can be used to incorporate background knowledge during parsing, in ways unlike previous semantic parsing approaches. For example, semantic statements corresponding to beliefs in a knowledge base can be given higher prior probability, type-correct statements can be given somewhat lower probability, and beliefs outside the knowledge base can be given lower probability. The construction of our grammar invokes a novel application of hierarchical Dirichlet processes (HDPs), which in turn, requires a novel and efficient inference approach. We present experimental results showing, for a simple grammar, that our parser outperforms a state-of-the-art CCG semantic parser and scales to knowledge bases with millions of beliefs.

A TensorFlow implementation of the models described in Andor et al. (2016). At Google, we spend a lot of time thinking about how computer systems can read and understand human language in order to process it in intelligent ways. We are excited to share the fruits of our research with the broader community by releasing SyntaxNet, an open-source neural network framework for TensorFlow that provides a foundation for Natural Language Understanding (NLU) systems. Our release includes all the code needed to train new SyntaxNet models on your own data, as well as Parsey McParseface, an English parser that we have trained for you, and that you can use to analyze English text. So, how accurate is Parsey McParseface?

Data imported from other spreadsheets or databases is already separated into fields, using something called a field delimiter--a comma, tab, space, or custom character--to separate one field from another. These databases import easily into Excel and place all the fields in separate columns. If your company pays bills and/or banks online, these sites usually offer copies of the company's records in electronic form. CSV (comma separated values) is the most common data exchange format and, if offered, the best one to use. But what happens when all the data imports into one cell?

Understanding large corpora is an increasingly popular problem. Modern startups and established companies are working diligently to produce models that can extract meaningful data from a body of text. In this post, I will explain some Natural Language Processing (NLP) techniques that can be used to extract the main subject of a particular document. In addition to identifying the main subject, I will explain a technique for getting Subject Verb and Object sets, everywhere the subject is mentioned. To further explain what I'm talking about take a look at this TechCrunch article.

For almost 50 years, CSV has been the format of choice for tabular data. Given the ubiquity of CSV and the pervasive need to deal with CSV in real workflows -- where speed, accuracy, and fault tolerance is a must -- we decided to build a CSV reader that runs in parallel. We conducted extensive benchmarks of ParaText against 7 CSV readers and 5 binary readers. Please refer to our benchmarking whitepaper for more details. In our tests, ParaText can load a CSV file from a cold disk at a rate of 2.5 GB/second and 4.2 GB/second out-of-core from a warm disk.

The classpath must include all of the CoreNLP dependencies. The memory requirements of the server are the same as that of CoreNLP, though it will grow as you load more models (e.g., memory increases if you load both the PCFG and Shift-Reduce constituency parser models). A safe minimum is 4gb; 8gb is recommended if you can spare it. The server can be stopped programmatically by making a call to the /shutdown endpoint with an appropriate shutdown key. This key is saved to the file /tmp/corenlp.shutdown

Artificial intelligence is one of the world's fastest-developing fields of study, and Google AI tools have already surpassed our expectations of the human brain-like capabilities of AI technology. Having created a groundbreaking "parsing" program, new Google AI tool Parsey McParseface could detect lies and eliminate problems of human language with an artificial intelligence language program. Google AI recently stunned the world upon releasing its AI poetry program, which uses a technique called recurrent neural network language model (RNNLM) to write classical, authentic, poetry touted as capable of "making a Vogon proud." The latest AI development as premiered by Google is a language parsing tool -- an artificial intelligence program capable of sorting through passages of human language and detecting inconsistencies in rhetoric and prose -- dubbed Parsey McParseface. Google's AI language tool was given the McParseface name when, 18 months into the program's development and still unable to think of a suitable title, Google developers named the sophisticated AI tool as a tongue-in-cheek reference to the viral poll that almost saw a polar research vessel called Boaty McBoatface.

Before you even ask, the name has no meaning. When Google was trying to figure out what to call its language parsing technology, someone suggested Parsey McParseface; it's a bit like Apple's Liam, which has no clever backstory either. The overall AI model is called SyntaxNet (please make your SkyNet jokes now); 'ol Parsey is just for English. Combining machine learning and search techniques, Parsey McParseface is 94 percent accurate, according to Google. It also leans on SyntaxNet's neural-network framework for analyzing the linguistic structure of a sentence or statement, which parses the functional role of each word in a sentence.