Future Directions in Natural Language Processing: The Bolt Beranek and Newman Natural Language Symposium

AI Magazine

The Workshop on Future Directions in NLP was held at Bolt Beranek and Newman, Inc. (BBN), in Cambridge, Massachusetts, from 29 November to 1 December 1989. The workshop was organized and hosted by Madeleine Bates and Ralph Weischedel of the BBN Speech and Natural Language Department and sponsored by BBN's Science Development Program.


IDL-Expressions: A Formalism for Representing and Parsing Finite Languages in Natural Language Processing

Journal of Artificial Intelligence Research

We propose a formalism for representation of finite languages, referred to as the class of IDL-expressions, which combines concepts that were only considered in isolation in existing formalisms. The suggested applications are in natural language processing, more specifically in surface natural language generation and in machine translation, where a sentence is obtained by first generating a large set of candidate sentences, represented in a compact way, and then by filtering such a set through a parser. We study several formal properties of IDL-expressions and compare this new formalism with more standard ones. We also present a novel parsing algorithm for IDL-expressions and prove a non-trivial upper bound on its time complexity.


Natural Language Processing and Natural Language Generation: What's the Difference?

#artificialintelligence

Given the nature of our business, we often encounter confusion between Natural Language Processing (NLP), Natural Language Generation (NLG), and Natural Language Understanding (NLU). To most folks, NLP is "Computers reading language." I mentioned NLU earlier; NLU stands for Natural Language Understanding, and is a specific type of NLP. The "reading" aspect of NLP is broad and encompasses a variety of applications, including things like: A more advanced application of NLP is NLU, ie.


Natural Language Access to Enterprise Data

AI Magazine

This paper describes USI Answers -- a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation.


Swift 4 Natural Language Processing Part 1.2

#artificialintelligence

Machine learning is absolutely fascinating and if you watched the WWDC 2017 sessions, you know how awesome it is! So in this set of videos, I'll be sharing with you what I learned about Natural Language Processing in this last video of the NLP series and discovered with NSLinguisticTagger and how powerful it is. If you want to explore and analyze natural language, I break it down for you!;) If you want to explore and learn more about it, definitely read the documentation and watch the videos: https://developer.apple.com/machine-l... Also, do some experiments! I didn't show the raw output for tag and tokens, I dare you to see what outputs without forcible unwrapping everything (which isn't the best thing to do - guard statements should be used if you aren't absolutely positive that there is valid text coming in) and why I coded it the way I did. Song: Paul Flint - Sock It To Them [NCS Release] Music provided by NoCopyrightSounds.