Here you can find a consolidated (a.k.a. slowly updated) list of my publications. A frequently updated (and possibly noisy) list of works is available on my Google Scholar profile.
Please find below a short list of highlight publications for my recent activity.
Bacciu, Davide; Carta, Antonio Sequential Sentence Embeddings for Semantic Similarity Conference Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI'19), IEEE, 2019. Cafagna, Michele; Mattei, Lorenzo De; Bacciu, Davide; Nissim, Malvina Suitable doesn’t mean attractive. Human-based evaluation of automatically generated headlines Conference Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it 2019), vol. 2481 , AI*IA series CEUR, 2019. Davide, Bacciu; Vincenzo, Gervasi; Giuseppe, Prencipe An Investigation into Cybernetic Humor, or: Can Machines Laugh? Conference Proceedings of the 8th International Conference on Fun with Algorithms (FUN'16) , vol. 49, Leibniz International Proceedings in Informatics (LIPIcs) Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2016, ISSN: 1868-8969.@conference{ssci19,
title = {Sequential Sentence Embeddings for Semantic Similarity},
author = {Davide Bacciu and Antonio Carta},
doi = {10.1109/SSCI44817.2019.9002824},
year = {2019},
date = {2019-12-06},
urldate = {2019-12-06},
booktitle = {Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI'19)},
publisher = {IEEE},
abstract = { Sentence embeddings are distributed representations of sentences intended to be general features to be effectively used as input for deep learning models across different natural language processing tasks.
State-of-the-art sentence embeddings for semantic similarity are computed with a weighted average of pretrained word embeddings, hence completely ignoring the contribution of word ordering within a sentence in defining its semantics. We propose a novel approach to compute sentence embeddings for semantic similarity that exploits a linear autoencoder for sequences. The method can be trained in closed form and it is easy to fit on unlabeled sentences. Our method provides a grounded approach to identify and subtract common discourse from a sentence and its embedding, to remove associated uninformative features. Unlike similar methods in the literature (e.g. the popular Smooth Inverse Frequency approach), our method is able to account for word order. We show that our estimate of the common discourse vector improves the results on two different semantic similarity benchmarks when compared to related approaches from the literature.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
State-of-the-art sentence embeddings for semantic similarity are computed with a weighted average of pretrained word embeddings, hence completely ignoring the contribution of word ordering within a sentence in defining its semantics. We propose a novel approach to compute sentence embeddings for semantic similarity that exploits a linear autoencoder for sequences. The method can be trained in closed form and it is easy to fit on unlabeled sentences. Our method provides a grounded approach to identify and subtract common discourse from a sentence and its embedding, to remove associated uninformative features. Unlike similar methods in the literature (e.g. the popular Smooth Inverse Frequency approach), our method is able to account for word order. We show that our estimate of the common discourse vector improves the results on two different semantic similarity benchmarks when compared to related approaches from the literature.@conference{clic2019,
title = {Suitable doesn’t mean attractive. Human-based evaluation of automatically generated headlines},
author = {Michele Cafagna and Lorenzo {De Mattei} and Davide Bacciu and Malvina Nissim},
editor = {Raffaella Bernardi and Roberto Navigli and Giovanni Semeraro},
url = {http://ceur-ws.org/Vol-2481/paper13.pdf},
year = {2019},
date = {2019-11-15},
urldate = {2019-11-15},
booktitle = {Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it 2019)},
volume = {2481 },
publisher = {CEUR},
series = {AI*IA series},
abstract = {We train three different models to generate newspaper headlines from a portion of the corresponding article. The articles are obtained from two mainstream Italian newspapers. In order to assess the models’ performance, we set up a human-based evaluation where 30 different native speakers expressed their judgment over a variety of aspects. The outcome shows that (i) pointer networks perform better than standard sequence to sequence models, creating mostly correct and appropriate titles; (ii) the suitability of a headline to its article for pointer networks is on par or better than the gold headline; (iii) gold headlines are still by far more inviting than generated headlines to read the whole article, highlighting the contrast between human creativity and content appropriateness.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{fun2016,
title = {An Investigation into Cybernetic Humor, or: Can Machines Laugh?},
author = {Bacciu Davide and Gervasi Vincenzo and Prencipe Giuseppe},
editor = {Erik D. Demaine and Fabrizio Grandoni},
url = {http://drops.dagstuhl.de/opus/volltexte/2016/5882},
doi = {10.4230/LIPIcs.FUN.2016.3},
issn = {1868-8969},
year = {2016},
date = {2016-06-10},
booktitle = {Proceedings of the 8th International Conference on Fun with Algorithms (FUN'16) },
volume = {49},
pages = {1-15},
publisher = {Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
abstract = {The mechanisms of humour have been the subject of much study and investigation, starting with and up to our days. Much of this work is based on literary theories, put forward by some of the most eminent philosophers and thinkers of all times, or medical theories, investigating the impact of humor on brain activity or behaviour. Recent functional neuroimaging studies, for instance, have investigated the process of comprehending and appreciating humor by examining functional activity in distinctive regions of brains stimulated by joke corpora. Yet, there is precious little work on the computational side, possibly due to the less hilarious nature of computer scientists as compared to men of letters and sawbones. In this paper, we set to investigate whether literary theories of humour can stand the test of algorithmic laughter. Or, in other words, we ask ourselves the vexed question: Can machines laugh? We attempt to answer that question by testing whether an algorithm - namely, a neural network - can "understand" humour, and in particular whether it is possible to automatically identify abstractions that are predicted to be relevant by established literary theories about the mechanisms of humor. Notice that we do not focus here on distinguishing humorous from serious statements - a feat that is clearly way beyond the capabilities of the average human voter, not to mention the average machine - but rather on identifying the underlying mechanisms and triggers that are postulated to exist by literary theories, by verifying if similar mechanisms can be learned by machines. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}