A huge amount of information is stored or communicated in the form of natural language. But it is difficult to make use of this information without asking people to read or listen it all. In our European research centre in Grenoble (France), we teach computers to read, understand and act. Our research in natural language processing (NLP) makes this information accessible, but also comprehensible, integrated, and actionable. Our algorithms and models are used in text analytics applications for healthcare, litigation, automation and finance.

Researchers in MIT's Computer Science and Artificial Intelligence Laboratory, working with colleagues at the University of Washington, have developed a new computer system that can automatically solve the type of word problems common in introductory algebra classes. In the near term, the work could lead to educational tools that identify errors in students' reasoning or evaluate the difficulty of word problems. But it may also point toward systems that can solve more complicated problems in geometry, physics, and finance -- problems whose solutions don't appear in the back of the teacher's edition of a textbook. According to Nate Kushman, an MIT graduate student in electrical engineering and computer science and lead author on the new paper, the new work is in the field of "semantic parsing," or translating natural language into a formal language such as arithmetic or formal logic. Most previous work on semantic parsing -- including his own -- has focused on individual sentences, Kushman says. "In these algebra problems, you have to build these things up from many different sentences," he says.

The class will cover models at the level of syntactic, semantic and discourse processing. The emphasis will be on corpus-based methods and algorithms, such as Hidden Markov Models and probabilistic context free grammars. We will discuss the use of these methods and models in a variety of applications including syntactic parsing, information extraction, statistical machine translation, and summarization. File decompression software, such as Winzip or StuffIt, is required to open the .gz Postscript viewer software, such as Ghostscript/Ghostview, can be used to view the .ps

In the lead-up to November's presidential election, Donald Trump released a list of 21 potential Supreme Court nominees in what many saw as an effort to mollify conservatives who tend to worry about these sorts of things. Now, that list has reportedly been narrowed to eight. On this episode, we sit down with William Jay, a former clerk to Justice Antonin Scalia, to discuss Scalia's possible successors.

A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of (Weston et al., 2015) and large-scale question answering from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.

This blog was originally published on the AYLIEN Text Analysis blog. We wanted to gather and analyze news content in order to look for similarities and differences in the way two journalists write headlines for their respective news articles and blog posts. Note: For a more technical, in-depth and interactive representation of this project, check out the Jupyter notebook we created. This includes sample code and more in depth descriptions of our approach. In linguistics, a parse tree is a rooted tree that represents the syntactic structure of a sentence, according to some pre-defined grammar.

The corpus is intended to serve as a reference for training and evaluating methods for anatomical entity mention detection in life science publications.

People not infrequently complain that Stanford CoreNLP is slow or takes a ton of memory. In some configurations this is true. In other configurations, this is not true. This section tries to help you understand what you can or can't do about speed and memory usage. The advice applies regardless of whether you are running CoreNLP from the command-line, from the Java API, from the web service, or from other languages.

We wanted to gather and analyze news content in order to look for similarities and differences in the way two journalists write headlines for their respective news articles and blog posts. Finance: Akin Oyedele of Business Insider, who covers market updates. Celebrity: Carly Ledbetter of the Huffington Post, who mainly writes about celebrities. Finance: Akin Oyedele of Business Insider, who covers market updates. Celebrity: Carly Ledbetter of the Huffington Post, who mainly writes about celebrities.

Two eye-catching Machine-Learning libraries, PHP-ML and Skale-ML, written in PHP and Node.js respectively, are found in this week. Is this a sign of the up-coming wide-spread of ML everywhere? Deep Learning Papers by Nam Vu Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled. If you have subscribed this blog, please make sure to change the feed address.