Search Results for author:
Found 48 papers, 28 papers with code
MilaNLP @ WASSA: Does BERT Feel Sad When You Cry?
The paper describes the MilaNLP team’s submission (Bocconi University, Milan) in the WASSA 2021 Shared Task on Empathy Detection and Emotion Classification.
HATE-ITA: New Baselines for Hate Speech Detection in Italian
Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly.
MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities
In this paper, we describe the system proposed by the MilaNLP team for the Multimedia Automatic Misogyny Identification (MAMI) challenge.
XLM-EMO: Multilingual Emotion Prediction in Social Media Text
Detecting emotion in text allows social and computational scientists to study how people behave and react to online events.
“Does it come in black?” CLIP-like models are zero-shot recommenders
Product discovery is a crucial component for online shopping.
Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
Current language technology is ubiquitous and directly influences individuals’ lives worldwide.
Pipelines for Social Bias Testing of Large Language Models
We hope to open a discussion on the best methodologies to handle social bias testing in language models.
Universal Joy A Data Set and Results for Classifying Emotions Across Languages
While emotions are universal aspects of human psychology, they are expressed differently across different languages and cultures.
FEEL-IT: Emotion and Sentiment Classification for the Italian Language
While sentiment analysis is a popular task to understand people’s reactions online, we often need more nuanced information: is the post negative because the user is angry or sad?
Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion
We find that the diversity scores for both Fragmentation and Representation are lower for immigration than for DST.
Contrastive language and vision learning of general fashion concepts
The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models.
SocioProbe: What, When, and Where Language Models Learn about Sociodemographics
Our results show that PLMs do encode these sociodemographics, and that this knowledge is sometimes spread across the layers of some of the tested PLMs.
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Machine learning models are now able to convert user-written text descriptions into naturalistic images.
"It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online
Well-annotated data is a prerequisite for good Natural Language Processing models.
ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds
The most common ways to explore latent document dimensions are topic models and clustering methods.
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
More data is needed, but annotating hateful content is expensive, time-consuming and potentially harmful to annotators.
Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training
Language is constantly changing and evolving, leaving language models to quickly become outdated, both factually and linguistically.
When and why vision-language models behave like bags-of-words, and what to do about it?
ARO consists of Visual Genome Attribution, to test the understanding of objects' properties; Visual Genome Relation, to test for relational understanding; and COCO & Flickr30k-Order, to test for order sensitivity.
Real-Time Oil Leakage Detection on Aftermarket Motorcycle Damping System with Convolutional Neural Networks
In this work, we describe in detail how Deep Learning and Computer Vision can help to detect fault events of the AirTender system, an aftermarket motorcycle damping system component.
EvalRS: a Rounded Evaluation of Recommender Systems
Much of the complexity of Recommender Systems (RSs) comes from the fact that they are used as part of more complex applications and affect user experience through a varied range of user interfaces.
FashionCLIP: Connecting Language and Images for Product Representations
The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models.
"Does it come in black?" CLIP-like models are zero-shot recommenders
Product discovery is a crucial component for online shopping.
Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data
Twitter data have become essential to Natural Language Processing (NLP) and social science research, driving various scientific discoveries in recent years.
Beyond NDCG: behavioral testing of recommender systems with RecList
As with most Machine Learning systems, recommender systems are typically evaluated through performance metrics computed over held-out data points.
Language Invariant Properties in Natural Language Processing
We introduce language invariant properties: i. e., properties that should not change when we transform text, and how they can be used to quantitatively evaluate the robustness of transformation algorithms.
SWEAT: Scoring Polarization of Topics across Different Corpora
Understanding differences of viewpoints across corpora is a fundamental task for computational social sciences.
Contrastive Language-Image Pre-training for the Italian Language
CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts.
HONEST: Measuring Hurtful Sentence Completion in Language Models
Our results show that 4. 3{\%} of the time, language models complete a sentence with a hurtful word.
Ranked #1 on
Hurtful Sentence Completion
on HONEST
Query2Prod2Vec: Grounded Word Embeddings for eCommerce
We present Query2Prod2Vec, a model that grounds lexical representations for product search in product embeddings: in our model, meaning is a mapping between words and a latent space of products in a digital shop.
Words with Consistent Diachronic Usage Patterns are Learned Earlier: A Computational Analysis Using Temporally Aligned Word Embeddings
In this study, we use temporally aligned word embeddings and a large diachronic corpus of English to quantify language change in a data-driven, scalable way, which is grounded in language use.
SIGIR 2021 E-Commerce Workshop Data Challenge
The 2021 SIGIR workshop on eCommerce is hosting the Coveo Data Challenge for "In-session prediction for purchase intent and recommendations".
Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction
We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines; in particular, we explore the emergence of semantic generalization from unsupervised dense representations outside of synthetic environments.
Query2Prod2Vec Grounded Word Embeddings for eCommerce
We present Query2Prod2Vec, a model that grounds lexical representations for product search in product embeddings: in our model, meaning is a mapping between words and a latent space of products in a digital shop.
BERTective: Language Models and Contextual Information for Deception Detection
In most cases, however, the target texts{'} preceding context is not considered.
BERT Goes Shopping: Comparing Distributional Models for Product Representations
Word embeddings (e. g., word2vec) have been applied successfully to eCommerce products through~\textit{prod2vec}.
Tough Tables: Carefully Evaluating Entity Linking for Tabular Data
Table annotation is a key task to improve querying the Web and support the Knowledge Graph population from legacy sources (tables).
Fantastic Embeddings and How to Align Them: Zero-Shot Inference in a Multi-Shop Scenario
This paper addresses the challenge of leveraging multiple embedding spaces for multi-shop personalization, proving that zero-shot inference is possible by transferring shopping intent from one website to another without manual intervention.
``You Sound Just Like Your Father'' Commercial Machine Translation Systems Include Stylistic Biases
The main goal of machine translation has been to convey the correct content.
Knowledge Graph Embeddings and Explainable AI
Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces.
Cross-lingual Contextualized Topic Models with Zero-shot Learning
They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models.
Compass-aligned Distributional Embeddings for Studying Semantic Differences across Corpora
In this paper, we present a general framework to support cross-corpora language studies with word embeddings, where embeddings generated from different corpora can be compared to find correspondences and differences in meaning across the corpora.
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data.
"An Image is Worth a Thousand Features": Scalable Product Representations for In-Session Type-Ahead Personalization
We address the problem of personalizing query completion in a digital commerce setting, in which the bounce rate is typically high and recurring users are rare.
What the [MASK]? Making Sense of Language-Specific BERT Models
Driven by the potential of BERT models, the NLP community has started to investigate and generate an abundant number of BERT models that are trained on a particular language, and tested on a specific data domain and task.
Training Temporal Word Embeddings with a Compass
Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages.
Experimental neural network enhanced quantum tomography
We compared the neural network state reconstruction protocol with a protocol treating SPAM errors by process tomography, as well as to a SPAM-agnostic protocol with idealized measurements.
Reasoning over RDF Knowledge Bases using Deep Learning
Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field.
