Search Results for author:
Found 28 papers, 6 papers with code
Understanding the effects of language-specific class imbalance in multilingual fine-tuning
We study the effect of one type of imbalance often present in real-life multilingual classification datasets: an uneven distribution of labels across languages.
Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance
While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned.
Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
We also present a newly created corpus for Maltese, and determine the effect that the pre-training data size and domain have on the downstream performance.
Analysis of Data Augmentation Methods for Low-Resource Maltese ASR
Recent years have seen an increased interest in the computational speech processing of Maltese, but resources remain sparse.
On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning
Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one.
Annotating for Hate Speech: The MaNeCo Corpus and Some Input from Critical Discourse Analysis
In view of this, we suggest a multi-layer annotation scheme, which is pilot-tested against a binary +/- hate speech classification and appears to yield higher inter-annotator agreement.
MASRI-HEADSET: A Maltese Corpus for Speech Recognition
Maltese, the national language of Malta, is spoken by approximately 500, 000 people.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
The societal and ethical relevance of computational creativity
In this paper, we provide a philosophical account of the value of creative systems for individuals and society.
A blindspot of AI ethics: anti-fragility in statistical prediction
With this paper, we aim to put an issue on the agenda of AI ethics that in our view is overlooked in the current discourse.
Word Probability Findings in the Voynich Manuscript
The Voynich Manuscript has baffled scholars for centuries.
Learning to Predict Novel Noun-Noun Compounds
We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus.
Measuring the compositionality of noun-noun compounds over time
We present work in progress on the temporal progression of compositionality in noun-noun compounds.
Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions
To gain a better understanding of the variation we find in face description and the possible issues that this may raise, we also conducted an annotation study on a subset of the corpus.
Survey: Multiword Expression Processing: A Survey
The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs.
Evaluating Compound Splitters Extrinsically with Textual Entailment
Traditionally, compound splitters are evaluated intrinsically on gold-standard data or extrinsically on the task of statistical machine translation.
The Grammar of English Deverbal Compounds and their Meaning
We present an interdisciplinary study on the interaction between the interpretation of noun-noun deverbal compounds (DCs; e. g., task assignment) and the morphosyntactic properties of their deverbal heads in English.
