Logical Rule Extraction Using a Learning Machine with Sparse Function Representation.

Source Extraction Using Sparse Representation

Rule-based Logical Forms Extraction

In this paper, we present concise but robust rules for dependency-based logical form identification with high accuracy. We describe our approach from an intuitive and formalized perspective, which we believe overcomes much of the complexity. In comparison to previous work, we believe ours is more compact and involves less rules and exceptions. We also provide the reader with a comparison of the...

Term extraction using machine learning

In this term paper I motivate and describe a monolingual term extraction method using the Ripper machine learning algorithm and linguistic and statistical features of n-grams extracted from a patent text corpus. The n-grams are labeled as terms or non-terms using a manually validated term list based on the same patent text corpus. The results for experiments conducted show promise for further r...

Visual Tracking Based on Extreme Learning Machine and Sparse Representation

The existing sparse representation-based visual trackers mostly suffer from both being time consuming and having poor robustness problems. To address these issues, a novel tracking method is presented via combining sparse representation and an emerging learning technique, namely extreme learning machine (ELM). Specifically, visual tracking can be divided into two consecutive processes. Firstly,...

Parallel Dictionary Learning Using a Joint Density Restricted Boltzmann Machine for Sparse-representation-based Voice Conversion

In voice conversion, sparse-representation-based methods have recently been garnering attention because they are, relatively speaking, not affected by over-fitting or over-smoothing problems. In these approaches, voice conversion is achieved by estimating a sparse vector that determines which dictionaries of the target speaker should be used, calculated from the matching of the input vector and...