Search Results for author: Abdou Youssef

Found 6 papers, 0 papers with code

GOT: Testing for Originality in Natural Language Generation

no code implementations ACL (GEM) 2021 Jennifer Brooks, Abdou Youssef

We propose an approach to automatically test for originality in generation tasks where no standard automatic measures exist.

Text Generation

A general-purpose method for applying Explainable AI for Anomaly Detection

no code implementations23 Jul 2022 John Sipple, Abdou Youssef

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm.

Explainable Artificial Intelligence (XAI) Unsupervised Anomaly Detection

Semantic Preserving Bijective Mappings of Mathematical Formulae between Document Preparation Systems and Computer Algebra Systems

no code implementations17 Sep 2021 Howard S. Cohl, Moritz Schubotz, Abdou Youssef, André Greiner-Petter, Jürgen Gerhard, Bonita V. Saunders, Marjorie A. ~McClain

Using LaTeX, LaTeXML, and tools generated for use in the National Institute of Standards (NIST) Digital Library of Mathematical Functions, semantically enhanced mathematical LaTeX markup (semantic LaTeX) is achieved by using a semantic macro set.

Math

Metaphor Detection using Ensembles of Bidirectional Recurrent Neural Networks

no code implementations WS 2020 Jennifer Brooks, Abdou Youssef

In this paper we present our results from the Second Shared Task on Metaphor Detection, hosted by the Second Workshop on Figurative Language Processing.

Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language

no code implementations22 May 2020 Philipp Scharpf, Moritz Schubotz, Abdou Youssef, Felix Hamborg, Norman Meuschke, Bela Gipp

In this paper, we show how selecting and combining encodings of natural and mathematical language affect classification and clustering of documents with mathematical content.

Classification Clustering +3

Query Expansion for Patent Searching using Word Embedding and Professional Crowdsourcing

no code implementations14 Nov 2019 Arthi Krishna, Ye Jin, Christine Foster, Greg Gabel, Britt Hanley, Abdou Youssef

By designing a user interface that allows examiners to interact with the word embedding suggestions, we are able to use these interactions to power crowdsourced modes of related terms.

Cannot find the paper you are looking for? You can Submit a new open access paper.