Old is Gold: Linguistic Driven Approach for Entity and Relation Linking of Short Text

1 code implementation • NAACL 2019 • Ahmad Sakor, on, Isaiah o Mulang{'}, Kuldeep Singh, Saeedeh Shekarpour, Maria Esther Vidal, Jens Lehmann, S{\"o}ren Auer

Short texts challenge NLP tasks such as named entity recognition, disambiguation, linking and relation inference because they do not provide sufficient context or are partially malformed (e. g. wrt.

Entity Linking Implicit Relations +5

Learning Exceptionality and Variation with Lexically Scaled MaxEnt

no code implementations • WS 2019 • Coral Hughto, Andrew Lamont, Br Prickett, on, Gaja Jarosz

Adding the Third Dimension to Spatial Relation Detection in 2D Images

no code implementations • WS 2018 • Br Birmingham, on, Adrian Muscat, Anja Belz

Detection of spatial relations between objects in images is currently a popular subject in image description research.

Object Relation +1

Seq2Seq Models with Dropout can Learn Generalizable Reduplication

no code implementations • WS 2018 • Br Prickett, on, Aaron Traylor, Joe Pater

Natural language reduplication can pose a challenge to neural models of language, and has been argued to require variables (Marcus et al., 1999).

Interactive Visualization for Linguistic Structure

no code implementations • EMNLP 2017 • Aaron Sarnat, Vidur Joshi, Cristian Petrescu-Prahova, Alvaro Herrasti, Br Stilson, on, Mark Hopkins

We provide a visualization library and web interface for interactively exploring a parse tree or a forest of parses.

The Use of Object Labels and Spatial Prepositions as Keywords in a Web-Retrieval-Based Image Caption Generation System

no code implementations • WS 2017 • Br Birmingham, on, Adrian Muscat

On the other hand, images with two image objects were better described with template-generated sentences composed of object labels and prepositions.

Caption Generation Image Retrieval +4

Effect of Data Annotation, Feature Selection and Model Choice on Spatial Description Generation in French

no code implementations • WS 2016 • Anja Belz, Adrian Muscat, Br Birmingham, on, Jessie Levacher, Julie Pain, Adam Quinquenel

feature selection Image Captioning +1

Exploring Different Preposition Sets, Models and Feature Sets in Automatic Generation of Spatial Image Descriptions

no code implementations • WS 2016 • Anja Belz, Adrian Muscat, Br Birmingham, on

Classifying Out-of-vocabulary Terms in a Domain-Specific Social Media Corpus

no code implementations • LREC 2016 • SoHyun Park, Afsaneh Fazly, Annie Lee, Br Seibel, on, Wenjie Zi, Paul Cook

We then propose a supervised approach to classify out-of-vocabulary terms according to these categories, drawing on features based on word embeddings, and linguistic knowledge of common properties of out-of-vocabulary terms.

General Classification Word Embeddings