activity
20162023
most citedAttending to Characters in Neural Sequence Labeling Models

67 citations · 82 across the 15 of their papers we have counts for

collaborators
Showing 2017 · cs.CLShow all

6 papers · 2 filters

cs.CL2017

Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

Marek Rei, Luana Bulat, Douwe Kiela +1

The ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date re…

cs.CL2017

An Error-Oriented Approach to Word Embedding Pre-Training

Youmna Farag, Marek Rei, Ted Briscoe

We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based o…

cs.CL2017

Artificial Error Generation with Machine Translation and Syntactic Patterns

Marek Rei, Mariano Felice, Zheng Yuan +1

Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating w…

cs.CL2017

Detecting Off-topic Responses to Visual Prompts

Marek Rei

Automated methods for essay scoring have made great progress in recent years, achieving accuracies very close to human annotators. However, a known weakness of such automated score…

cs.CL2017

Auxiliary Objectives for Neural Error Detection Models

Marek Rei, Helen Yannakoudakis

We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary cos…

cs.CL2017

Semi-supervised Multitask Learning for Sequence Labeling

Marek Rei

We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective…