arXiv research

SAFE detects fake news by analyzing text and image similarities.

A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted to similarity measures between these embeddings, with cosine similari…

We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual re…

A CBR system investigates the TS-SS metric for document similarity.

A new test assesses text similarity between two groups of documents.

We propose a novel learning framework to answer questions such as "if a user is purchasing a shirt, what other items will (s)he need with the shirt?" Our framework learns distributed representations for items from available textual data, with the learned representations representing items in a latent space expressing f…

Textual data predicts electricity consumption and weather.

Paper presents a technique using Spearman's Rank Correlation Coefficient for KE in TDs.

SFBoW provides sentence embeddings with predefined dimensions.

A new method learns text network embeddings by combining generative autoencoder and homophilic priors.

An increasing number of people are using online social networking services (SNSs), and a significant amount of information related to experiences in consumption is shared in this new media form. Text mining is an emerging technique for mining useful information from the web. We aim at discovering in particular tweets s…

A new topology design improves zero-shot classification performance in contrastive learning.

We introduce a probabilistic framework for quantifying the semantic similarity between two groups of embeddings. We formulate the task of semantic similarity as a model comparison task in which we contrast a generative model which jointly models two sentences versus one that does not. We illustrate how this framework c…

Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…

R package sentometrics analyzes text sentiment for predictions.

Interpretable semantic textual similarity (iSTS) task adds a crucial explanatory layer to pairwise sentence similarity. We address various components of this task: chunk level semantic alignment along with assignment of similarity type and score for aligned chunks with a novel system presented in this paper. We propose…

MGM improves media profiling by integrating textual and structural features.

Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by introducing multimodal data. This is especially important in sparse datasets, maki…

The paper proposes a new recommender system combining ratings and textual reviews.

Distributed representations of words, better known as word embeddings, have become important building blocks for natural language processing tasks. Numerous studies are devoted to transferring the success of unsupervised word embeddings to sentence embeddings. In this paper, we introduce a simple representation of sent…

FRED explains text model predictions by identifying key words and providing counterfactual examples.

Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that l…

Benchmark assesses forecasting models' ability to use textual context.

Examines parallels between human subjects and texts for causal inference.

Proposes Textual Echo Cancellation to improve speech recognition.

Paper proposes active learning for mining conflict dynamics from textual data.

Interpretable text-response modelling for structured outcomes

BERTopic improves financial text analysis with FinTextSim's contextual embeddings.

While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called \emph{Word Mover's Distance…

Taxicab correspondence analysis visualizes sparse text data sets.

A new framework predicts stock movements using news sentiment and relational data.

Dynamic Embedding learns text node representations in evolving graphs.

New model uses financial filings to predict bankruptcy, even without MDA sections.

Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram features when learning from textual data. They are also compatible with the use of word embeddings so that word similarities can be accounted for. While the original any-gram kernels are implemented on top of tree kernels, we propose a new approa…

Since datasets with annotation for novelty at the document and/or word level are not easily available, we present a simulation framework that allows us to create different textual datasets in which we control the way novelty occurs. We also present a benchmark of existing methods for novelty detection in textual data s…

Surveying machine learning methods for economic forecasting.

Paper explores different models for fake news detection.

Paper introduces a benchmark for predicting bankruptcy from text data.

MoleculeSTM learns from molecule structures and texts for better drug design.

A vast amount of textual web streams is influenced by events or phenomena emerging in the real world. The social web forms an excellent modern paradigm, where unstructured user generated content is published on a regular basis and in most occasions is freely distributed. The present Ph.D. Thesis deals with the problem …

An integrated approach is proposed across visual and textual data to both determine and justify a medical diagnosis by a neural network. As deep learning techniques improve, interest grows to apply them in medical applications. To enable a transition to workflows in a medical context that are aided by machine learning,…

Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research exploits the relationship of texts on the same edge to graphically embed text. How…

Distributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence representations: Given a sequence of corpora, we aim to optimize the sentence encoder with respect to the new corpus while maintaining its accuracy …

Algorithm reduces audit costs by identifying best service configurations from biased textual evidence.

Mixtures of Unigrams are one of the simplest and most efficient tools for clustering textual data, as they assume that documents related to the same topic have similar distributions of terms, naturally described by Multinomials. When the classification task is particularly challenging, such as when the document-term ma…

Study investigates micro-event detection on FLOSS version releases from Stack Overflow.

Paper proposes a new softmax loss for better performance in Positive and Unlabeled data tasks.

This study improves stock price prediction using multimodal data.