Search Results for author: Luke Gessler

Found 16 papers, 7 papers with code

Closing the NLP Gap Documentary Linguistics and NLP Need a Shared Software Infrastructure

no code implementations ComputEL (ACL) 2022 Luke Gessler

For decades, researchers in natural language processing and computational linguistics have been developing models and algorithms that aim to serve the needs of language documentation projects.

Xposition: An Online Multilingual Database of Adpositional Semantics

no code implementations LREC 2022 Luke Gessler, Nathan Schneider, Joseph C. Ledford, Austin Blodgett

We present Xposition, an online platform for documenting adpositional semantics across languages in terms of supersenses (Schneider et al., 2018).

Midas Loop: A Prioritized Human-in-the-Loop Annotation for Large Scale Multilayer Data

no code implementations LREC (LAW) 2022 Luke Gessler, Lauren Levine, Amir Zeldes

Large scale annotation of rich multilayer corpus data is expensive and time consuming, motivating approaches that integrate high quality automatic tools with active learning in order to prioritize human labeling of hard cases.

Active Learning Management +1

GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation

no code implementations3 Jun 2023 Tatsuya Aoyama, Shabnam Behzad, Luke Gessler, Lauren Levine, Jessica Lin, Yang Janet Liu, Siyao Peng, YIlun Zhu, Amir Zeldes

We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE's utility as an evaluation dataset for NLP systems.

coreference-resolution Dependency Parsing +2

PrOnto: Language Model Evaluations for 859 Languages

1 code implementation22 May 2023 Luke Gessler

Evaluation datasets are critical resources for measuring the quality of pretrained language models.

Language Modelling

MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning

1 code implementation23 Dec 2022 Luke Gessler, Amir Zeldes

Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require.

Dependency Parsing Language Modelling +3

BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology

1 code implementation EMNLP (BlackboxNLP) 2021 Luke Gessler, Nathan Schneider

An important question concerning contextualized word embedding (CWE) models like BERT is how well they can represent different word senses, especially those in the long tail of uncommon senses.


AMALGUM -- A Free, Balanced, Multilayer English Web Corpus

1 code implementation LREC 2020 Luke Gessler, Siyao Peng, Yang Liu, YIlun Zhu, Shabnam Behzad, Amir Zeldes

We present a freely available, genre-balanced English web corpus totaling 4M tokens and featuring a large number of high-quality automatic annotation layers, including dependency trees, non-named entity annotations, coreference resolution, and discourse trees in Rhetorical Structure Theory.


Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi

1 code implementation ACL 2020 Aryaman Arora, Luke Gessler, Nathan Schneider

Hindi grapheme-to-phoneme (G2P) conversion is mostly trivial, with one exception: whether a schwa represented in the orthography is pronounced or unpronounced (deleted).

A Discourse Signal Annotation System for RST Trees

1 code implementation WS 2019 Luke Gessler, Yang Liu, Amir Zeldes

This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation.

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