Search Results for author:
Found 28 papers, 6 papers with code
A Word-and-Paradigm Workflow for Fieldwork Annotation
There are many challenges in morphological fieldwork annotation, it heavily relies on segmentation and feature labeling (which have both practical and theoretical drawbacks), it’s time-intensive, and the annotator needs to be linguistically trained and may still annotate things inconsistently.
What transfers in morphological inflection? Experiments with analogical models
We show that this model is capable of near-baseline performance on the SigMorphon 2020 inflection challenge.
OSU at SigMorphon 2022: Analogical Inflection With Rule Features
OSU’s inflection system is a transformer whose input is augmented with an analogical exemplar showing how to inflect a different word into the target cell.
Exploring How Generative Adversarial Networks Learn Phonological Representations
This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena.
Analogy in Contact: Modeling Maltese Plural Inflection
Maltese is often described as having a hybrid morphological system resulting from extensive contact between Semitic and Romance language varieties.
Privacy Policy Question Answering Assistant: A Query-Guided Extractive Summarization Approach
We address these problems by paraphrasing to bring the style and language of the user's question closer to the language of privacy policies.
Fairness-aware Summarization for Justified Decision-Making
In other words, decision-relevant features should provide sufficient information for the predicted outcome and should be independent of the membership of individuals in protected groups such as race and gender.
Acquiring language from speech by learning to remember and predict
Classical accounts of child language learning invoke memory limits as a pressure to discover sparse, language-like representations of speech, while more recent proposals stress the importance of prediction for language learning.
The Paradigm Discovery Problem
Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm.
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders
In this paper, we deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages (Xitsonga and English).
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities
Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora.
Lexical Networks in !Xung
We investigate the lexical network properties of the large phoneme inventory Southern African language Mangetti Dune ! Xung as it compares to English and other commonly-studied languages.
Breaking NLP: Using Morphosyntax, Semantics, Pragmatics and World Knowledge to Fool Sentiment Analysis Systems
This paper describes our {``}breaker{''} submission to the 2017 EMNLP {``}Build It Break It{''} shared task on sentiment analysis.
Speech segmentation with a neural encoder model of working memory
We present the first unsupervised LSTM speech segmenter as a cognitive model of the acquisition of words from unsegmented input.
Challenges and Solutions for Latin Named Entity Recognition
Although spanning thousands of years and genres as diverse as liturgy, historiography, lyric and other forms of prose and poetry, the body of Latin texts is still relatively sparse compared to English.
You Talking to Me? A Corpus and Algorithm for Conversation Disentanglement
We present a corpus of Internet Relay Chat (IRC) dialogue in which the various conversations have been manually disentangled, and evaluate annotator reliability.
