Search Results for author:
Found 71 papers, 38 papers with code
Visually Grounded Interpretation of Noun-Noun Compounds in English
We find that adding visual vectors increases classification performance on our dataset in many cases.
Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages
Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data.
Breeding Fillmore’s Chickens and Hatching the Eggs: Recombining Frames and Roles in Frame-Semantic Parsing
Frame-semantic parsers traditionally predict predicates, frames, and semantic roles in a fixed order.
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.
AGILe: The First Lemmatizer for Ancient Greek Inscriptions
To facilitate corpus searches by classicists as well as to reduce data sparsity when training models, we focus on the automatic lemmatization of ancient Greek inscriptions, which have not received as much attention in this sense as literary text data has.
Human Perception in Natural Language Generation
We ask subjects whether they perceive as human-produced a bunch of texts, some of which are actually human-written, while others are automatically generated.
DALC: the Dutch Abusive Language Corpus
As socially unacceptable language become pervasive in social media platforms, the need for automatic content moderation become more pressing.
QE4PE: Word-level Quality Estimation for Human Post-Editing
Word-level quality estimation (QE) detects erroneous spans in machine translations, which can direct and facilitate human post-editing.
Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimation
In an educational setting, an estimate of the difficulty of multiple-choice questions (MCQs), a commonly used strategy to assess learning progress, constitutes very useful information for both teachers and students.
A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources.
Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence
We further experiment with having a single teacher (instead of an ensemble of two teachers) and implement additional optimization strategies to improve the distillation process.
Can Model Uncertainty Function as a Proxy for Multiple-Choice Question Item Difficulty?
Estimating the difficulty of multiple-choice questions would be great help for educators who must spend substantial time creating and piloting stimuli for their tests, and for learners who want to practice.
Multi-property Steering of Large Language Models with Dynamic Activation Composition
Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations.
Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
Results from both human and automatic evaluation show that the different quality of training data is clearly perceived and it has an impact also on the models trained on such data.
mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks.
Combining the Strengths of Dutch Survey and Register Data in a Data Challenge to Predict Fertility (PreFer)
We outline the ways in which measuring the predictability of fertility outcomes using these datasets and combining their strengths in the data challenge can advance our understanding of fertility behaviour and computational social science.
Quantifying the Plausibility of Context Reliance in Neural Machine Translation
Establishing whether language models can use contextual information in a human-plausible way is important to ensure their trustworthiness in real-world settings.
Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence
Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences.
Responsibility Perspective Transfer for Italian Femicide News
Different ways of linguistically expressing the same real-world event can lead to different perceptions of what happened.
Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation
Pre-trained language models (PLMs) have achieved great success in NLP and have recently been used for tasks in computational semantics.
Multilingual Multi-Figurative Language Detection
Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging.
DUMB: A Benchmark for Smart Evaluation of Dutch Models
The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks.
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible.
Multidimensional Evaluation for Text Style Transfer Using ChatGPT
We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing automatic metrics as well as human judgements.
Inseq: An Interpretability Toolkit for Sequence Generation Models
Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking generation settings, partly due to a lack of dedicated tools.
Dead or Murdered? Predicting Responsibility Perception in Femicide News Reports
We then train regression models that predict the salience of GBV participants with respect to different dimensions of perceived responsibility.
Multi-Figurative Language Generation
Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context.
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement.
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer.
IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
We introduce IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian.
SOCIOFILLMORE: A Tool for Discovering Perspectives
SOCIOFILLMORE is a multilingual tool which helps to bring to the fore the focus or the perspective that a text expresses in depicting an event.
Generic resources are what you need: Style transfer tasks without task-specific parallel training data
Style transfer aims to rewrite a source text in a different target style while preserving its content.
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content.
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
For many (minority) languages, the resources needed to train large models are not available.
Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students
To raise awareness, curiosity, and longer-term interest in young people, we have developed an interactive workshop designed to illustrate the basic principles of NLP and computational linguistics to high school Italian students aged between 13 and 18 years.
A dissemination workshop for introducing young Italian students to NLP
We describe and make available the game-based material developed for a laboratory run at several Italian science festivals to popularize NLP among young students.
On the interaction of automatic evaluation and task framing in headline style transfer
An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based metrics.
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages
Specifically, we describe the adaptation of English GPT-2 to Italian and Dutch by retraining lexical embeddings without tuning the Transformer layers.
Datasets and Models for Authorship Attribution on Italian Personal Writings
Existing research on Authorship Attribution (AA) focuses on texts for which a lot of data is available (e. g novels), mainly in English.
Personal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian
We present a novel corpus for personality prediction in Italian, containing a larger number of authors and a different genre compared to previously available resources.
Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality
As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits.
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.
Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor
Analogies such as man is to king as woman is to X are often used to illustrate the amazing power of word embeddings.
Lower Bias, Higher Density Abusive Language Datasets: A Recipe
Strategies used until now to increase density of abusive language and obtain more meaningful data overall, include data filtering on the basis of pre-selected keywords and hate-rich sources of data.
MAGPIE: A Large Corpus of Potentially Idiomatic Expressions
Given the limited size of existing idiom corpora, we aim to enable progress in automatic idiom processing and linguistic analysis by creating the largest-to-date corpus of idioms for English.
Invisible to People but not to Machines: Evaluation of Style-aware HeadlineGeneration in Absence of Reliable Human Judgment
We automatically generate headlines that are expected to comply with the specific styles of two different Italian newspapers.
GePpeTto Carves Italian into a Language Model
We provide a thorough analysis of GePpeTto's quality by means of both an automatic and a human-based evaluation.
What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models
Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers.
BERTje: A Dutch BERT Model
The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks.
Ranked #3 on
Sentiment Analysis
on DBRD
Casting a Wide Net: Robust Extraction of Potentially Idiomatic Expressions
To further progress on the extraction and disambiguation of potentially idiomatic expressions, larger corpora of PIEs are required.
You Write Like You Eat: Stylistic variation as a predictor of social stratification
Inspired by Labov's seminal work on stylistic variation as a function of social stratification, we develop and compare neural models that predict a person's presumed socio-economic status, obtained through distant supervision, from their writing style on social media.
Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor
However, beside the intrinsic problems with the analogy task as a bias detection tool, in this paper we show that a series of issues related to how analogies have been implemented and used might have yielded a distorted picture of bias in word embeddings.
The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses
Disambiguation of potentially idiomatic expressions involves determining the sense of a potentially idiomatic expression in a given context, e. g. determining that make hay in {`}Investment banks made hay while takeovers shone.
Discriminator at SemEval-2018 Task 10: Minimally Supervised Discrimination
We participated to the SemEval-2018 shared task on capturing discriminative attributes (Task 10) with a simple system that ranked 8th amongst the 26 teams that took part in the evaluation.
Bleaching Text: Abstract Features for Cross-lingual Gender Prediction
Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent.
The Power of Character N-grams in Native Language Identification
In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017.
To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging
Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data?
N-GrAM: New Groningen Author-profiling Model
We describe our participation in the PAN 2017 shared task on Author Profiling, identifying authors' gender and language variety for English, Spanish, Arabic and Portuguese.
Tracing metaphors in time through self-distance in vector spaces
From a diachronic corpus of Italian, we build consecutive vector spaces in time and use them to compare a term's cosine similarity to itself in different time spans.
When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter
We bootstrap a state-of-the-art part-of-speech tagger to tag Italian Twitter data, in the context of the Evalita 2016 PoSTWITA shared task.
Distant supervision for emotion detection using Facebook reactions
We exploit the Facebook reaction feature in a distant supervised fashion to train a support vector machine classifier for emotion detection, using several feature combinations and combining different Facebook pages.
Leveraging Native Data to Correct Preposition Errors in Learners' Dutch
The first is a binary model for detecting whether a preposition should be used at all in a given position or not.
A Modular System for Rule-based Text Categorisation
We introduce a modular rule-based approach to text categorisation which is more flexible and less time consuming to build than a standard rule-based system because it works with a hierarchical structure and allows for re-usability of rules.
