This article is about Semantic Role Labeling for English partitive nouns (5%/REL of the price/ARG1; The price/ARG1 rose 5 percent/REL) in the NomBank annotated corpus. Several systems are described using traditional and transformer-based machine learning, as well as ensembling. Our highest scoring system achieves an F1 of 91.74% using “gold” parses from the Penn Treebank and 91.12% when using the Berkeley Neural parser. This research includes both classroom and experimental settings for system development.

While systems using the Neural Network-based Machine Translation (NMT) paradigm achieve the highest scores on recent shared tasks, phrase-based (PBMT) systems, rule-based (RBMT) systems and other systems may get better results for individual examples. Therefore, combined systems should achieve the best results for MT, particularly if the system combination method can take advantage of the strengths of each paradigm. In this paper, we describe a system that predicts whether a NMT, PBMT or RBMT will get the best Spanish translation result for a particular English sentence in DGT-TM 20161. Then we use fuzzy-match repair (FMR) as a mechanism to show that the combined system outperforms individual systems in a black-box machine translation setting.

In recent years, deep learning has shown promising results when used in the field of natural language processing (NLP).Neural networks (NNs) such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been used for various NLP tasks including sentiment analysis, information retrieval, and document classification.In this paper, we the present the Supreme Court Classifier (SCC), a system that applies these methods to the problem of document classification of legal court opinions.We compare methods using traditional machine learning with recent NN-based methods.We also present a CNN used with pre-trained word vectors which shows improvements over the state-of-the-art applied to our dataset.We train and evaluate our system using the Washington University School of Law Supreme Court Database (SCDB).Our best system (word2vec + CNN) achieves 72.4% accuracy when classifying the court decisions into 15 broad SCDB categories and 31.9%accuracy when classifying among 279 finer-grained SCDB categories.

While algorithms have existed in math, music and other fields for over one thousand years, the use of algorithms to solve problems has become easier than ever before due to the advent of the modern computer. This fact, in combination with advances in signal processing, makes an understanding of computer science an absolute necessity for future composers of music. This paper describes a highly successful intensive three week class called Musicomputation, in which computer science and computer music were taught to eleven 11-17 year old students with previous expertise in music and mathematics. We discuss details of the class and the possible implications for education.

We describe and analyze inference strategies for combining outputs from multiple question answering systems each of which was developed independently. Specifically, we address the DARPA-funded GALE information distillation Year 3 task of finding answers to the 5-Wh questions (who, what, when, where, and why) for each given sentence. The approach we take revolves around determining the best system using discriminative learning. In particular, we train support vector machines with a set of novel features that encode systems’ capabilities of returning as many correct answers as possible. We analyze two combination strategies: one combines multiple systems at the granularity of sentences, and the other at the granularity of individual fields. Our experimental results indicate that the proposed features and combination strategies were able to improve the overall performance by 22% to 36% relative to a random selection, 16% to 35% relative to a majority voting scheme, and 15% to 23% relative to the best individual system. Index Terms: Question answering, Systems for spoken language understanding

Computer Science and Computational Approaches to Music for Middle School and High School Students, also known as Musicomputation (http://musicomputation.com/) was a highly successful course sponsored by the National Science Foundation (IIS-0834034) and first held in June 2008 at New York University. Two NYU professors and two doctoral candidates developed curriculum, gave lectures, and supervised labs introducing computer science and computer music to students aged 12-17. Our hypothesis was that it is easier to learn computer science when the data you are modeling and the problems you are solving belong to a domain that you know well and love. During the project, students progressed far beyond the instructors' expectations, quickly absorbing computer science concepts that even college students often find difficult.

We present an implemented unification-based parser for relational grammars developed within the stratified feature grammar (SFG) framework, which generalizes Kasper-Rounds logic to handle relational grammar analyses. We first introduce the key aspects of SFG and a lexicalized, graph-based variant of the framework suitable for implementing relational grammars. We then describe a head-driven chart parser for lexicalized SFG. The basic parsing operation is essentially ordinary feature-structure unification augmented with an operation of label unification to build the stratified features characteristic of SFG.