Related papers: The Paradigm Discovery Problem
Neural node embeddings have recently emerged as a powerful representation for supervised learning tasks involving graph-structured data. We leverage this recent advance to develop a novel algorithm for unsupervised community discovery in…
Many programming tasks require using both domain-specific code and well-established patterns (such as routines concerned with file IO). Together, several small patterns combine to create complex interactions. This compounding effect, mixed…
Calculation of topological invariants for crystalline systems is well understood in reciprocal space, allowing for the topological classification of a wide spectrum of materials. In this work, we present a new technique based on the…
Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the…
This study addresses a series of methodological questions that arise when modeling inflectional morphology with Linear Discriminative Learning. Taking the semi-productive German noun system as example, we illustrate how decisions made about…
Word feature vectors have been proven to improve many NLP tasks. With recent advances in unsupervised learning of these feature vectors, it became possible to train it with much more data, which also resulted in better quality of learned…
Interpretability methods in NLP aim to provide insights into the semantics underlying specific system architectures. Focusing on word embeddings, we present a supervised-learning method that, for a given domain (e.g., sports, professions),…
Recent advances on the Vector Space Model have significantly improved some NLP applications such as neural machine translation and natural language generation. Although word co-occurrences in context have been widely used in…
We develop and test a novel unsupervised algorithm for word sense induction and disambiguation which uses topological data analysis. Typical approaches to the problem involve clustering, based on simple low level features of distance in…
Distributional text clustering delivers semantically informative representations and captures the relevance between each word and semantic clustering centroids. We extend the neural text clustering approach to text classification tasks by…
Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as a byproduct generate…
Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem…
Metaphor detection, a critical task in natural language processing, involves identifying whether a particular word in a sentence is used metaphorically. Traditional approaches often rely on supervised learning models that implicitly encode…
In this work we consider the task of relaxing the i.i.d assumption in pattern recognition (or classification), aiming to make existing learning algorithms applicable to a wider range of tasks. Pattern recognition is guessing a discrete…
This paper shows that a popular approach to the supervised embedding of documents for classification, namely, contrastive Word Mover's Embedding, can be significantly enhanced by adding interpretability. This interpretability is achieved by…
The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these…
Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard…
Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…
In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an…
In partial multi-label learning (PML), the true labels are unobserved, which makes label disambiguation important but difficult. A key challenge is that ambiguous candidate labels can propagate errors into downstream tasks such as feature…