Eric Rosen


2022

pdf bib
Modeling human-like morphological prediction
Eric Rosen
Proceedings of the Society for Computation in Linguistics 2022

2021

pdf bib
Emergent Gestural Scores in a Recurrent Neural Network Model of Vowel Harmony
Caitlin Smith | Charlie O’Hara | Eric Rosen | Paul Smolensky
Proceedings of the Society for Computation in Linguistics 2021

pdf bib
Inflectional paradigms as interacting systems
Eric Rosen
Proceedings of the Society for Computation in Linguistics 2021

pdf bib
Lexical strata and phonotactic perplexity minimization
Eric Rosen
Proceedings of the Society for Computation in Linguistics 2021

pdf bib
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos | Sudha Rao | Caitlin Smith | Eric Rosen | Asli Celikyilmaz | R. Thomas McCoy | Yichen Jiang | Coleman Haley | Roland Fernandez | Hamid Palangi | Jianfeng Gao | Paul Smolensky
Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)

Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.