Search Results for author:
Found 25 papers, 2 papers with code
Fairness-Aware Low-Rank Adaptation Under Demographic Privacy Constraints
To address this issue, we introduce a set of LoRA-based fine-tuning methods that can be trained in a distributed fashion, where model developers and fairness auditors collaborate without sharing sensitive attributes or predictors.
A New Perspective on Determining Disease Invasion and Population Persistence in Heterogeneous Environments
We introduce a new quantity known as the network heterogeneity index, denoted by $\mathcal{H}$, which facilitates the investigation of disease propagation and population persistence in heterogeneous environments.
Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis
The text sanitization process starts with a privacy-oriented entity recognizer that seeks to determine the text spans expressing identifiable personal information.
Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation
We show that although performance is overall improved, the filterbanks exhibit strong sensitivity to their initialisation strategy.
Parsing linearizations appreciate PoS tags - but some are fussy about errors
PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning.
Learnable Acoustic Frontends in Bird Activity Detection
Combining this data with species agnostic bird activity detection systems enables the monitoring of activity levels of bird populations.
The Impact of Edge Displacement Vaserstein Distance on UD Parsing Performance
We contribute to the discussion on parsing performance in NLP by introducing a measurement that evaluates the differences between the distributions of edge displacement (the directed distance of edges) seen in training and test data.
Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences
The increase in performance in NLP due to the prevalence of distributional models and deep learning has brought with it a reciprocal decrease in interpretability.
Low Resource Species Agnostic Bird Activity Detection
This paper explores low resource classifiers and features for the detection of bird activity, suitable for embedded Automatic Recording Units which are typically deployed for long term remote monitoring of bird populations.
Bioacoustic Event Detection with prototypical networks and data augmentation
This report presents deep learning and data augmentation techniques used by a system entered into the Few-Shot Bioacoustic Event Detection for the DCASE2021 Challenge.
Learning from learning machines: a new generation of AI technology to meet the needs of science
We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery.
Replicating and Extending ``Because Their Treebanks Leak'': Graph Isomorphism, Covariants, and Parser Performance
S{\o}gaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance.
Splitting EUD graphs into trees: A quick and clatty approach
We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2021.
A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance.
A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021
We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front.
John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs
We hypothesize that the temporary challenge humans face in integrating the two contradicting signals, one from the lexical semantics of the verb, one from the sentence-level semantics, would be reflected in higher error rates for models on tasks dependent on causal links.
Replicating and Extending "Because Their Treebanks Leak": Graph Isomorphism, Covariants, and Parser Performance
S{\o}gaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance.
What Taggers Fail to Learn, Parsers Need the Most
We present an error analysis of neural UPOS taggers to evaluate why using gold standard tags has such a large positive contribution to parsing performance while using predicted UPOS tags either harms performance or offers a negligible improvement.
Near-unity broadband omnidirectional emissivity via femtosecond laser surface processing
It is very challenging to achieve near perfect absorption/emission that is both broadband and omnidirectional while utilizing a scalable fabrication process.
Optics
On the Frailty of Universal POS Tags for Neural UD Parsers
We present an analysis on the effect UPOS accuracy has on parsing performance.
Efficient EUD Parsing
We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2020.
Distilling Neural Networks for Greener and Faster Dependency Parsing
The carbon footprint of natural language processing research has been increasing in recent years due to its reliance on large and inefficient neural network implementations.
Inherent Dependency Displacement Bias of Transition-Based Algorithms
Empirical studies have shown that performance varies across different treebanks in such a way that one algorithm outperforms another on one treebank and the reverse is true for a different treebank.
Artificially Evolved Chunks for Morphosyntactic Analysis
We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks.
