Search Results for author: Malvina Nissim

Found 63 papers, 34 papers with code

Human Perception in Natural Language Generation

no code implementations ACL (GEM) 2021 Lorenzo De Mattei, Huiyuan Lai, Felice Dell’Orletta, Malvina Nissim

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.

Text Generation

AGILe: The First Lemmatizer for Ancient Greek Inscriptions

no code implementations LREC 2022 Evelien de Graaf, Silvia Stopponi, Jasper K. Bos, Saskia Peels-Matthey, Malvina Nissim

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.

Lemmatization

Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages

1 code implementation ACL 2022 Wietse de Vries, Martijn Wieling, Malvina Nissim

Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data.

Part-Of-Speech Tagging POS +3

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias

1 code implementation GeBNLP (COLING) 2020 Marion Bartl, Malvina Nissim, Albert Gatt

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.

counterfactual Word Embeddings

Combining the Strengths of Dutch Survey and Register Data in a Data Challenge to Predict Fertility (PreFer)

1 code implementation1 Feb 2024 Elizaveta Sivak, Paulina Pankowska, Adrienne Mendrik, Tom Emery, Javier Garcia-Bernardo, Seyit Hocuk, Kasia Karpinska, Angelica Maineri, Joris Mulder, Malvina Nissim, Gert Stulp

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

2 code implementations2 Oct 2023 Gabriele Sarti, Grzegorz Chrupała, Malvina Nissim, Arianna Bisazza

Establishing whether language models can use contextual information in a human-plausible way is important to ensure their trustworthiness in real-world settings.

Machine Translation Translation

Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence

1 code implementation1 Sep 2023 Daniel Scalena, Gabriele Sarti, Malvina Nissim, Elisabetta Fersini

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences.

Language Modelling reinforcement-learning

Responsibility Perspective Transfer for Italian Femicide News

1 code implementation1 Jun 2023 Gosse Minnema, Huiyuan Lai, Benedetta Muscato, Malvina Nissim

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

1 code implementation31 May 2023 Chunliu Wang, Huiyuan Lai, Malvina Nissim, Johan Bos

Pre-trained language models (PLMs) have achieved great success in NLP and have recently been used for tasks in computational semantics.

Cross-Lingual Transfer DRS Parsing +2

Multilingual Multi-Figurative Language Detection

1 code implementation31 May 2023 Huiyuan Lai, Antonio Toral, Malvina Nissim

Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging.

Language Modelling Sentence

DUMB: A Benchmark for Smart Evaluation of Dutch Models

2 code implementations22 May 2023 Wietse de Vries, Martijn Wieling, Malvina Nissim

The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks.

XLM-R

Multidimensional Evaluation for Text Style Transfer Using ChatGPT

1 code implementation26 Apr 2023 Huiyuan Lai, Antonio Toral, Malvina Nissim

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.

Style Transfer Text Style Transfer

Inseq: An Interpretability Toolkit for Sequence Generation Models

2 code implementations27 Feb 2023 Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar van der Wal, Malvina Nissim, Arianna Bisazza

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.

Feature Importance Machine Translation +2

Dead or Murdered? Predicting Responsibility Perception in Femicide News Reports

1 code implementation24 Sep 2022 Gosse Minnema, Sara Gemelli, Chiara Zanchi, Tommaso Caselli, Malvina Nissim

We then train regression models that predict the salience of GBV participants with respect to different dimensions of perceived responsibility.

regression

Multi-Figurative Language Generation

1 code implementation COLING 2022 Huiyuan Lai, Malvina Nissim

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.

Language Modelling Sentence +1

Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer

1 code implementation HumEval (ACL) 2022 Huiyuan Lai, Jiali Mao, Antonio Toral, Malvina Nissim

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.

Navigate Style Transfer +1

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

3 code implementations7 Mar 2022 Gabriele Sarti, Malvina Nissim

The T5 model and its unified text-to-text paradigm contributed in advancing the state-of-the-art for many natural language processing tasks.

Headline Generation News Summarization +4

SOCIOFILLMORE: A Tool for Discovering Perspectives

no code implementations ACL 2022 Gosse Minnema, Sara Gemelli, Chiara Zanchi, Tommaso Caselli, Malvina Nissim

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.

A dissemination workshop for introducing young Italian students to NLP

1 code implementation NAACL (TeachingNLP) 2021 Lucio Messina, Lucia Busso, Claudia Roberta Combei, Ludovica Pannitto, Alessio Miaschi, Gabriele Sarti, Malvina Nissim

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.

Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students

1 code implementation NAACL (TeachingNLP) 2021 Ludovica Pannitto, Lucia Busso, Claudia Roberta Combei, Lucio Messina, Alessio Miaschi, Gabriele Sarti, Malvina Nissim

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.

On the interaction of automatic evaluation and task framing in headline style transfer

1 code implementation ACL (EvalNLGEval, INLG) 2020 Lorenzo De Mattei, Michele Cafagna, Huiyuan Lai, Felice Dell'Orletta, Malvina Nissim, Albert Gatt

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.

Style Transfer

As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages

1 code implementation Findings (ACL) 2021 Wietse de Vries, Malvina Nissim

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

1 code implementation16 Nov 2020 Gaetana Ruggiero, Albert Gatt, Malvina Nissim

Existing research on Authorship Attribution (AA) focuses on texts for which a lot of data is available (e. g novels), mainly in English.

Authorship Attribution Authorship Verification

Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality

1 code implementation COLING (PEOPLES) 2020 Elisa Bassignana, Malvina Nissim, Viviana Patti

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.

Personal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian

1 code implementation11 Nov 2020 Elisa Bassignana, Malvina Nissim, Viviana Patti

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.

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias

1 code implementation27 Oct 2020 Marion Bartl, Malvina Nissim, Albert Gatt

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.

counterfactual Word Embeddings

MAGPIE: A Large Corpus of Potentially Idiomatic Expressions

no code implementations LREC 2020 Hessel Haagsma, Johan Bos, Malvina Nissim

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.

Lower Bias, Higher Density Abusive Language Datasets: A Recipe

no code implementations LREC 2020 Juliet van Rosendaal, Tommaso Caselli, Malvina Nissim

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.

Abusive Language

GePpeTto Carves Italian into a Language Model

1 code implementation29 Apr 2020 Lorenzo De Mattei, Michele Cafagna, Felice Dell'Orletta, Malvina Nissim, Marco Guerini

We provide a thorough analysis of GePpeTto's quality by means of both an automatic and a human-based evaluation.

Language Modelling Sentence +1

BERTje: A Dutch BERT Model

2 code implementations19 Dec 2019 Wietse de Vries, Andreas van Cranenburgh, Arianna Bisazza, Tommaso Caselli, Gertjan van Noord, Malvina Nissim

The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks.

Language Modelling named-entity-recognition +5

Casting a Wide Net: Robust Extraction of Potentially Idiomatic Expressions

no code implementations20 Nov 2019 Hessel Haagsma, Malvina Nissim, Johan Bos

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

no code implementations ACL 2019 Angelo Basile, Albert Gatt, Malvina Nissim

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

1 code implementation23 May 2019 Malvina Nissim, Rik van Noord, Rob van der Goot

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.

Bias Detection Word Embeddings

The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses

no code implementations COLING 2018 Hessel Haagsma, Malvina Nissim, Johan Bos

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.

Machine Translation Sentiment Analysis +1

Discriminator at SemEval-2018 Task 10: Minimally Supervised Discrimination

no code implementations SEMEVAL 2018 Artur Kulmizev, Mostafa Abdou, Vinit Ravishankar, Malvina Nissim

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

1 code implementation ACL 2018 Rob van der Goot, Nikola Ljubešić, Ian Matroos, Malvina Nissim, Barbara Plank

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent.

Gender Prediction

The Power of Character N-grams in Native Language Identification

no code implementations WS 2017 Artur Kulmizev, Bo Blankers, Johannes Bjerva, Malvina Nissim, Gertjan van Noord, Barbara Plank, Martijn Wieling

In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017.

Native Language Identification Text Classification

N-GrAM: New Groningen Author-profiling Model

no code implementations12 Jul 2017 Angelo Basile, Gareth Dwyer, Maria Medvedeva, Josine Rawee, Hessel Haagsma, Malvina Nissim

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.

POS

Tracing metaphors in time through self-distance in vector spaces

no code implementations10 Nov 2016 Marco Del Tredici, Malvina Nissim, Andrea Zaninello

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.

Distant supervision for emotion detection using Facebook reactions

no code implementations WS 2016 Chris Pool, Malvina Nissim

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.

When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter

no code implementations9 Nov 2016 Barbara Plank, Malvina Nissim

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.

TAG

Leveraging Native Data to Correct Preposition Errors in Learners' Dutch

no code implementations LREC 2016 Lennart Kloppenburg, Malvina Nissim

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

no code implementations LREC 2014 Marco Del Tredici, Malvina Nissim

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.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.