Coleman Haley


2022

pdf bib
How to encode arbitrarily complex morphology in word embeddings, no corpus needed
Lane Schwartz | Coleman Haley | Francis Tyers
Proceedings of the first workshop on NLP applications to field linguistics

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. Currently, fewer than 300-400 languages out of approximately 7000 have have more than a trivial amount of digitized texts; of those, between 100-200 languages (most in the Indo-European language family) have enough text data for BERT embeddings of reasonable quality to be trained. The word embeddings in this paper are explicitly designed to be both linguistically interpretable and fully capable of handling the broad variety found in the world’s diverse set of 7000 languages, regardless of corpus size or morphological characteristics. We demonstrate the applicability of our representation through examples drawn from a typologically diverse set of languages whose morphology includes prefixes, suffixes, infixes, circumfixes, templatic morphemes, derivational morphemes, inflectional morphemes, and reduplication.

2021

pdf bib
Morphology Matters: A Multilingual Language Modeling Analysis
Hyunji Hayley Park | Katherine J. Zhang | Coleman Haley | Kenneth Steimel | Han Liu | Lane Schwartz
Transactions of the Association for Computational Linguistics, Volume 9

Abstract Prior studies in multilingual language modeling (e.g., Cotterell et al., 2018; Mielke et al., 2019) disagree on whether or not inflectional morphology makes languages harder to model. We attempt to resolve the disagreement and extend those studies. We compile a larger corpus of 145 Bible translations in 92 languages and a larger number of typological features.1 We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features. We find that several morphological measures are significantly associated with higher surprisal when LSTM models are trained with BPE-segmented data. We also investigate linguistically motivated subword segmentation strategies like Morfessor and Finite-State Transducers (FSTs) and find that these segmentation strategies yield better performance and reduce the impact of a language’s morphology on language modeling.

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.

pdf bib
Deep neural networks easily learn unnatural infixation and reduplication patterns
Coleman Haley | Colin Wilson
Proceedings of the Society for Computation in Linguistics 2021

2020

pdf bib
Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme
Coleman Haley | Paul Smolensky
Proceedings of the 28th International Conference on Computational Linguistics

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. Unlike previous attempts, this does not come at the cost of intractable representation size; we utilize a method for non-exact inversion, showing that it works well when there is sufficient randomness in the representation scheme for simple data and providing an upper bound on its error. To handle the huge number of possible tree positions without memoizing position representation vectors, we present a method (Cryptographic Role Embedding) using cryptographic hashing algorithms that allows for the representation of unboundedly many positions. Through experiments on parse tree data, we show a 30,000-dimensional Cryptographic Role Embedding of trees can provide invertibility with error < 1% that previous methods would require 8.6 × 1057 dimensions to represent.

pdf bib
This is a BERT. Now there are several of them. Can they generalize to novel words?
Coleman Haley
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Recently, large-scale pre-trained neural network models such as BERT have achieved many state-of-the-art results in natural language processing. Recent work has explored the linguistic capacities of these models. However, no work has focused on the ability of these models to generalize these capacities to novel words. 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. This type of morphological capacity has not been previously tested in BERT models, and is important for morphologically-rich languages, which are under-studied in the literature regarding BERT’s linguistic capacities. In this work, we investigate this by considering monolingual and multilingual BERT models’ abilities to agree in number with novel plural words in English, French, German, Spanish, and Dutch. We find that many models are not able to reliably determine plurality of novel words, suggesting potential deficiencies in the morphological capacities of BERT models.