Related papers: Morphological Inflection with Phonological Feature…
This paper presents the submissions by the University of Zurich to the SIGMORPHON 2017 shared task on morphological reinflection. The task is to predict the inflected form given a lemma and a set of morpho-syntactic features. We focus on…
Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…
Machine transliteration is a method for automatically converting words in one language into phonetically equivalent ones in another language. Machine transliteration plays an important role in natural language applications such as…
When translating into morphologically rich languages, Statistical MT approaches face the problem of data sparsity. The severity of the sparseness problem will be high when the corpus size of morphologically richer language is less. Even…
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. In its simplest…
We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the…
We present a study of morphological irregularity. Following recent work, we define an information-theoretic measure of irregularity based on the predictability of forms in a language. Using a neural transduction model, we estimate this…
This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably…
Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level…
Recent advancements in morpheme segmentation primarily emphasize word-level segmentation, often neglecting the contextual relevance within the sentence. In this study, we redefine the morpheme segmentation task as a sequence-to-sequence…
Lemmatization of standard languages is concerned with (i) abstracting over morphological differences and (ii) resolving token-lemma ambiguities of inflected words in order to map them to a dictionary headword. In the present paper we aim to…
Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…
Phonological features provide a language-general and linguistically grounded representation of speech. We present PhonoQ-2.0, a multilingual frame-level phonological feature recognizer built on self-supervised speech models. The system…
Morphological and syntactic changes in word usage (as captured, e.g., by grammatical profiles) have been shown to be good predictors of a word's meaning change. In this work, we explore whether large pre-trained contextualised language…
Existing methods in relation extraction have leveraged the lexical features in the word sequence and the syntactic features in the parse tree. Though effective, the lexical features extracted from the successive word sequence may introduce…
Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers…
We study the representation and encoding of phonemes in a recurrent neural network model of grounded speech. We use a model which processes images and their spoken descriptions, and projects the visual and auditory representations into the…
Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc. In this work, we propose a neural architecture coupled with a…
The generation of complex derived word forms has been an overlooked problem in NLP; we fill this gap by applying neural sequence-to-sequence models to the task. We overview the theoretical motivation for a paradigmatic treatment of…
End-to-end models, particularly Tacotron-based ones, are currently a popular solution for text-to-speech synthesis. They allow the production of high-quality synthesized speech with little to no text preprocessing. Indeed, they can be…