Related papers: Morphological Inflection with Phonological Feature…

Metric functions for phoneme perception capture the similarity structure among phonemes in a given language and therefore play a central role in phonology and psycho-linguistics. Various phenomena depend on phoneme similarity, such as…

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features…

In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically reduces as the amount of training data is increased. In this…

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…

In contrast to their word- or sentence-level counterparts, character embeddings are still poorly understood. We aim at closing this gap with an in-depth study of English character embeddings. For this, we use resources from research on…

We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, where the encoder is a pattern matching network. Each pattern…

Despite major advances in multilingual modeling, large quality disparities persist across languages. Besides the obvious impact of uneven training resources, typological properties have also been proposed to determine the intrinsic…

In this paper, we introduce two resources: (i) G2P+, a tool for converting orthographic datasets to a consistent phonemic representation; and (ii) IPA CHILDES, a phonemic dataset of child-centered speech across 31 languages. Prior tools for…

Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors concentrated in rare morphological subclasses. We examine Japanese past-tense verb…

This paper describes the results of some experiments exploring statistical methods to infer syntactic behavior of words and morphemes from a raw corpus in an unsupervised fashion. It shares certain points in common with Brown et al (1992)…

Human speech perception involves transforming a countinous acoustic signal into discrete linguistically meaningful units, such as phonemes, while simultaneously causing a listener to activate words that are similar to the spoken utterance…

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the…

The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P…

Large language models demonstrate proficiency on phonetic tasks, such as rhyming, without explicit phonetic or auditory grounding. In this work, we investigate how \verb|Llama-3.2-1B-Instruct| represents token-level phonetic information.…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages. Having long been multilingual, the…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

This paper describes a modular connectionist model of the acquisition of receptive inflectional morphology. The model takes inputs in the form of phones one at a time and outputs the associated roots and inflections. Simulations using…

Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized…

There are a few reasons for the recent increased interest in the study of local features of speech files. It is stated that many essential features of the speaker language used can appear in the form of the speech signal. The traditional…