Search Results for author:
Found 8 papers, 4 papers with code
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Under-Documented Languages
With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available.
One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes
Data augmentation strategies are increasingly important in NLP pipelines for low-resourced and endangered languages, and in neural morphological inflection, augmentation by so called data hallucination is a popular technique.
An Inflectional Database for Gitksan
We use Gitksan data in interlinear glossed format, stemming from language documentation efforts, to build a database of partial inflection tables.
The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language
In this project, we demonstrate that phoneme-based models for speech processing can achieve strong crosslinguistic generalizability to unseen languages.
Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection
In this study, we aim to shed light on the theoretical aspects of the prominent data augmentation strategy StemCorrupt (Silfverberg et al., 2017; Anastasopoulos and Neubig, 2019), a method that generates synthetic examples by randomly substituting stem characters in gold standard training examples.
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages
With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available.
Quantifying Cognitive Factors in Lexical Decline
Specifically, we propose a variety of psycholinguistic factors -- semantic, distributional, and phonological -- that we hypothesize are predictive of lexical decline, in which words greatly decrease in frequency over time.
