Search Results for author: Coleman Haley

Found 7 papers, 1 papers with code

This is a BERT. Now there are several of them. Can they generalize to novel words?

no code implementations EMNLP (BlackboxNLP) 2020 Coleman Haley

This type of generalization is exhibited by humans, and is intimately related to morphology—humans are in many cases able to identify inflections of novel words in the appropriate context.

How to encode arbitrarily complex morphology in word embeddings, no corpus needed

no code implementations FieldMatters (COLING) 2022 Lane Schwartz, Coleman Haley, Francis Tyers

In this paper, we present a straightforward technique for constructing interpretable word embeddings from morphologically analyzed examples (such as interlinear glosses) for all of the world’s languages.

Word Embeddings

Morphology Matters: A Multilingual Language Modeling Analysis

1 code implementation11 Dec 2020 Hyunji Hayley Park, Katherine J. Zhang, Coleman Haley, Kenneth Steimel, Han Liu, Lane Schwartz

We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features.

Language Modelling Segmentation

Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme

no code implementations COLING 2020 Coleman Haley, Paul Smolensky

We present a novel method for embedding trees in a vector space based on Tensor-Product Representations (TPRs) which allows for inversion: the retrieval of the original tree structure and nodes from the vectorial embedding.

Position Retrieval +1

Cannot find the paper you are looking for? You can Submit a new open access paper.