Search Results for author:
Found 25 papers, 14 papers with code
The Invalsi Benchmark: measuring Language Models Mathematical and Language understanding in Italian
This results in a lower number of available benchmarks to evaluate the performance of language models in Italian.
Detecting Images Generated by Diffusers
This paper explores the task of detecting images generated by text-to-image diffusion models.
Unravelling Interlanguage Facts via Explainable Machine Learning
We focus on a different facet of the NLI task, i. e., that of analysing the internals of an NLI classifier trained by an \emph{explainable} machine learning algorithm, in order to obtain explanations of its classification decisions, with the ultimate goal of gaining insight into which linguistic phenomena ``give a speaker's native language away''.
ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine Learning
The application uses machine learning to continuously fit automatic classification models that are in turn used to actively support its users with classification suggestions.
Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching
With the increased accessibility of web and online encyclopedias, the amount of data to manage is constantly increasing.
LeQua@CLEF2022: Learning to Quantify
LeQua 2022 is a new lab for the evaluation of methods for "learning to quantify" in textual datasets, i. e., for training predictors of the relative frequencies of the classes of interest in sets of unlabelled textual documents.
Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach
More in detail, we show that fairness under unawareness can be cast as a quantification problem and solved with proven methods from the quantification literature.
QuaPy: A Python-Based Framework for Quantification
prevalence values) of the classes of interest in a sample of unlabelled data.
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level.
Ranked #6 on
Image Retrieval
on Flickr30K 1K test
Transformer Reasoning Network for Image-Text Matching and Retrieval
State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms.
Word-Class Embeddings for Multiclass Text Classification
Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few.
Cross-Lingual Sentiment Quantification
Cross-lingual sentiment quantification (and cross-lingual \emph{text} quantification in general) has never been discussed before in the literature; we establish baseline results for the binary case by combining state-of-the-art quantification methods with methods capable of generating cross-lingual vectorial representations of the source and target documents involved.
Cross-Lingual Sentiment Classification
General Classification
+2
Building Automated Survey Coders via Interactive Machine Learning
We will show that, for the same amount of training effort, interactive learning delivers much better coding accuracy than standard "non-interactive" learning.
Learning to Weight for Text Classification
In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document.
Funnelling: A New Ensemble Method for Heterogeneous Transfer Learning and its Application to Cross-Lingual Text Classification
Funnelling consists of generating a two-tier classification system where all documents, irrespectively of language, are classified by the same (2nd-tier) classifier.
Revisiting Distributional Correspondence Indexing: A Python Reimplementation and New Experiments
This paper introduces PyDCI, a new implementation of Distributional Correspondence Indexing (DCI) written in Python.
Ranked #2 on
Sentiment Analysis
on Multi-Domain Sentiment Dataset
A Recurrent Neural Network for Sentiment Quantification
Quantification is a supervised learning task that consists in predicting, given a set of classes C and a set D of unlabelled items, the prevalence (or relative frequency) p(c|D) of each class c in C. Quantification can in principle be solved by classifying all the unlabelled items and counting how many of them have been attributed to each class.
JaTeCS an open-source JAva TExt Categorization System
JaTeCS is an open source Java library that supports research on automatic text categorization and other related problems, such as ordinal regression and quantification, which are of special interest in opinion mining applications.
Exploring epoch-dependent stochastic residual networks
The recently proposed stochastic residual networks selectively activate or bypass the layers during training, based on independent stochastic choices, each of which following a probability distribution that is fixed in advance.
Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions
We choose to implement the actual search process as a similarity search in a visual feature space, by learning to translate a textual query into a visual representation.
Utility-Theoretic Ranking for Semi-Automated Text Classification
\emph{Semi-Automated Text Classification} (SATC) may be defined as the task of ranking a set $\mathcal{D}$ of automatically labelled textual documents in such a way that, if a human annotator validates (i. e., inspects and corrects where appropriate) the documents in a top-ranked portion of $\mathcal{D}$ with the goal of increasing the overall labelling accuracy of $\mathcal{D}$, the expected increase is maximized.
Optimizing Text Quantifiers for Multivariate Loss Functions
We address the problem of \emph{quantification}, a supervised learning task whose goal is, given a class, to estimate the relative frequency (or \emph{prevalence}) of the class in a dataset of unlabelled items.
The User Feedback on SentiWordNet
With the release of SentiWordNet 3. 0 the related Web interface has been restyled and improved in order to allow users to submit feedback on the SentiWordNet entries, in the form of the suggestion of alternative triplets of values for an entry.
