1 code implementation • NAACL (SIGMORPHON) 2022 • Micha Elsner, Sara Court
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.
no code implementations • ComputEL (ACL) 2022 • Maria Copot, Sara Court, Noah Diewald, Stephanie Antetomaso, Micha Elsner
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.
no code implementations • ACL (SIGMORPHON) 2021 • Micha Elsner
We show that this model is capable of near-baseline performance on the SigMorphon 2020 inflection challenge.
no code implementations • 21 May 2023 • Jingyi Chen, Micha Elsner
This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena.
no code implementations • 20 May 2023 • Sara Court, Andrea D. Sims, Micha Elsner
Maltese is often described as having a hybrid morphological system resulting from extensive contact between Semitic and Romance language varieties.
no code implementations • 29 Sep 2021 • Moniba Keymanesh, Micha Elsner, Srinivasan Parthasarathy
We address these problems by paraphrasing to bring the style and language of the user's question closer to the language of privacy policies.
no code implementations • 13 Jul 2021 • Moniba Keymanesh, Tanya Berger-Wolf, Micha Elsner, Srinivasan Parthasarathy
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.
1 code implementation • CONLL 2020 • Cory Shain, Micha Elsner
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.
1 code implementation • ACL 2020 • Alexander Erdmann, Micha Elsner, Shijie Wu, Ryan Cotterell, Nizar Habash
Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm.
no code implementations • NAACL 2019 • Cory Shain, Micha Elsner
In this paper, we deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages (Xitsonga and English).
2 code implementations • NAACL 2019 • Alex Erdmann, er, David Joseph Wrisley, Benjamin Allen, Christopher Brown, Sophie Cohen-Bod{\'e}n{\`e}s, Micha Elsner, Yukun Feng, Brian Joseph, B{\'e}atrice Joyeux-Prunel, Marie-Catherine de Marneffe
Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora.
no code implementations • WS 2018 • Syed-Amad Hussain, Micha Elsner, Am Miller, a
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.
no code implementations • WS 2017 • Taylor Mahler, Willy Cheung, Micha Elsner, David King, Marie-Catherine de Marneffe, Cory Shain, Symon Stevens-Guille, Michael White
This paper describes our {``}breaker{''} submission to the 2017 EMNLP {``}Build It Break It{''} shared task on sentiment analysis.
no code implementations • EMNLP 2017 • Micha Elsner, Cory Shain
We present the first unsupervised LSTM speech segmenter as a cognitive model of the acquisition of words from unsegmented input.
no code implementations • WS 2016 • Alex Erdmann, er, Christopher Brown, Brian Joseph, Mark Janse, Petra Ajaka, Micha Elsner, Marie-Catherine de Marneffe
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.
no code implementations • ACL 2014 • Marten van Schijndel, Micha Elsner
no code implementations • 1 Jun 2008 • Micha Elsner, Eugene Charniak
We present a corpus of Internet Relay Chat (IRC) dialogue in which the various conversations have been manually disentangled, and evaluate annotator reliability.