Related papers: A Statistical Model for Word Discovery in Transcri…
We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully}…
Understanding the complexity of human language requires an appropriate analysis of the statistical distribution of words in texts. We consider the information retrieval problem of detecting and ranking the relevant words of a text by means…
This dissertation presents several new methods of supervised and unsupervised learning of word sense disambiguation models. The supervised methods focus on performing model searches through a space of probabilistic models, and the…
This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and…
We propose a model of the speech perception of individual words in the presence of mishearings. This phenomenological approach is based on concepts used in linguistics, and provides a formalism that is universal across languages. We put…
Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…
The paper describes a parser of sequences of (English) part-of-speech labels which utilises a probabilistic grammar trained using the inside-outside algorithm. The initial (meta)grammar is defined by a linguist and further rules compatible…
We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the…
Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…
We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit…
Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unlabeled data is usually easy to collect and many high-quality…
This report characterized the suitability of existing datasets for devising new Machine Learning models, decision making methods, and analysis algorithms to improve Collaborative Problem Solving and then enumerated requirements for future…
Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-centric interpretability} in language models, focusing on the…
We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…
Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target…
This paper studies hypothesis testing and parameter estimation in the context of the divide and conquer algorithm. In a unified likelihood based framework, we propose new test statistics and point estimators obtained by aggregating various…
Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased…
We investigated word recognition in a Visually Grounded Speech model. The model has been trained on pairs of images and spoken captions to create visually grounded embeddings which can be used for speech to image retrieval and vice versa.…
We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words. Such linguistic shifts are especially prevalent on the Internet, where the rapid exchange of…