Dietrich Klakow

Some steps towards the generation of diachronic WordNets

2019 · DSpace repository (University of Tartu)

We apply hyperbolic embeddings to trace the dynamics of change of conceptualsemantic relationships in a large diachronic scientific corpus (200 years).Our focus is on emerging scientific fields and the increasingly specialized terminology establishing around them.Reproducing …

Learning Functions to Study the Benefit of Multitask Learning

2020 · arXiv (Cornell University)

We study and quantify the generalization patterns of multitask learning (MTL) models for sequence labeling tasks. MTL models are trained to optimize a set of related tasks jointly. Although multitask learning has achieved improved performance …

On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers

2020

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little …

Call-Sign Recognition and Understanding for Noisy Air-Traffic Transcripts Using Surveillance Information

2022 · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Air traffic control (ATC) relies on communication via speech between pilot and air-traffic controller (ATCO). The call-sign, as unique identifier for each flight, is used to address a specific pilot by the ATCO. Extracting the …

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

David Adelani, Jesujoba Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Emezue, Colin Leong, Michael Beukman, Shamsuddeen …

Meta Self-Refinement for Robust Learning with Weak Supervision

2022 · arXiv (Cornell University)

Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs …

Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models

2022 · arXiv (Cornell University)

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an LSTM-based autoregressive …

EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation

2024 · arXiv (Cornell University)

Large language models (LLMs) have gained popularity recently due to their outstanding performance in various downstream Natural Language Processing (NLP) tasks. However, low-resource languages are still lagging behind current state-of-the-art (SOTA) developments in the field …

Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?

2024

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text.However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically difficult environment, …