Ewan Dunbar


2021

pdf bib
Paraphrases do not explain word analogies
Louis Fournier | Ewan Dunbar
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between jump and jumped will be in a similar direction to that of walk and walked, and so on). Several attempts have been made to explain this fact. We respond to Allen and Hospedales’ recent (ICML, 2019) theoretical explanation, which claims that word2vec and GloVe will encode linguistic regularities whenever a specific relation of paraphrase holds between the four words involved in the regularity. We demonstrate that the explanation does not go through: the paraphrase relations needed under this explanation do not hold empirically

pdf bib
Predicting non-native speech perception using the Perceptual Assimilation Model and state-of-the-art acoustic models
Juliette Millet | Ioana Chitoran | Ewan Dunbar
Proceedings of the 25th Conference on Computational Natural Language Learning

Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation Model, which appeals to a mental classification of sounds into native phoneme categories, versus the idea that rich, fine-grained phonetic representations tuned to the statistics of the native language, are sufficient. We operationalise this idea using representations from two state-of-the-art speech models, a Dirichlet process Gaussian mixture model and the more recent wav2vec 2.0 model. We present a new, open dataset of French- and English-speaking participants’ speech perception behaviour for 61 vowel sounds from six languages. We show that phoneme assimilation is a better predictor than fine-grained phonetic modelling, both for the discrimination behaviour as a whole, and for predicting differences in discriminability associated with differences in native language background. We also show that wav2vec 2.0, while not good at capturing the effects of native language on speech perception, is complementary to information about native phoneme assimilation, and provides a good model of low-level phonetic representations, supporting the idea that both categorical and fine-grained perception are used during speech perception.

2020

pdf bib
Analogies minus analogy test: measuring regularities in word embeddings
Louis Fournier | Emmanuel Dupoux | Ewan Dunbar
Proceedings of the 24th Conference on Computational Natural Language Learning

Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose and empirically analyze the classic arithmetic word analogy test, to motivate two new metrics that address the issues with the standard test, and which distinguish between class-wise offset concentration (similar directions between pairs of words drawn from different broad classes, such as France-London, China-Ottawa,...) and pairing consistency (the existence of a regular transformation between correctly-matched pairs such as France:Paris::China:Beijing). We show that, while the standard analogy test is flawed, several popular word embeddings do nevertheless encode linguistic regularities.

pdf bib
Tensor Product Decomposition Networks: Uncovering Representations of Structure Learned by Neural Networks
R. Thomas McCoy | Tal Linzen | Ewan Dunbar | Paul Smolensky
Proceedings of the Society for Computation in Linguistics 2020