no code implementations • SIGDIAL (ACL) 2021 • Vevake Balaraman, Seyedmostafa Sheikhalishahi, Bernardo Magnini
This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems.
no code implementations • RANLP 2021 • Tiziano Labruna, Bernardo Magnini
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge.
no code implementations • GWC 2016 • Anna Feltracco, Lorenzo Gatti, Elisabetta Jezek, Bernardo Magnini, Simone Magnolini
We present a methodology for building lexical sets for argument slots of Italian verbs.
no code implementations • EMNLP (insights) 2020 • Samuel Louvan, Bernardo Magnini
Although several works have addressed the role of data selection to improve transfer learning for various NLP tasks, there is no consensus about its real benefits and, more generally, there is a lack of shared practices on how it can be best applied.
no code implementations • 4 Feb 2025 • Bernardo Magnini, Roberto Zanoli, Michele Resta, Martin Cimmino, Paolo Albano, Marco Madeddu, Viviana Patti
We describe Evalita-LLM, a new benchmark designed to evaluate Large Language Models (LLMs) on Italian tasks.
no code implementations • 16 Jul 2024 • Tiziano Labruna, Bernardo Magnini
Task-oriented dialogues must maintain consistency both within the dialogue itself, ensuring logical coherence across turns, and with the conversational domain, accurately reflecting external knowledge.
no code implementations • 11 Apr 2024 • Iker García-Ferrero, Rodrigo Agerri, Aitziber Atutxa Salazar, Elena Cabrio, Iker de la Iglesia, Alberto Lavelli, Bernardo Magnini, Benjamin Molinet, Johana Ramirez-Romero, German Rigau, Jose Maria Villa-Gonzalez, Serena Villata, Andrea Zaninello
While these LLMs display competitive performance on automated medical texts benchmarks, they have been pre-trained and evaluated with a focus on a single language (English mostly).
no code implementations • 23 May 2023 • Tiziano Labruna, Sofia Brenna, Andrea Zaninello, Bernardo Magnini
Large pre-trained language models have exhibited unprecedented capabilities in producing high-quality text via prompting techniques.
no code implementations • COLING 2020 • Samuel Louvan, Bernardo Magnini
In recent years, fostered by deep learning technologies and by the high demand for conversational AI, various approaches have been proposed that address the capacity to elicit and understand user's needs in task-oriented dialogue systems.
no code implementations • PACLIC 2020 • Samuel Louvan, Bernardo Magnini
Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available.
no code implementations • LREC 2020 • Bernardo Magnini, Alberto Lavelli, Simone Magnolini
We present a comparison between deep learning and traditional machine learning methods for various NLP tasks in Italian.
no code implementations • LREC 2020 • Georg Rehm, Katrin Marheinecke, Stefanie Hegele, Stelios Piperidis, Kalina Bontcheva, Jan Hajič, Khalid Choukri, Andrejs Vasiļjevs, Gerhard Backfried, Christoph Prinz, José Manuel Gómez Pérez, Luc Meertens, Paul Lukowicz, Josef van Genabith, Andrea Lösch, Philipp Slusallek, Morten Irgens, Patrick Gatellier, Joachim köhler, Laure Le Bars, Dimitra Anastasiou, Albina Auksoriūtė, Núria Bel, António Branco, Gerhard Budin, Walter Daelemans, Koenraad De Smedt, Radovan Garabík, Maria Gavriilidou, Dagmar Gromann, Svetla Koeva, Simon Krek, Cvetana Krstev, Krister Lindén, Bernardo Magnini, Jan Odijk, Maciej Ogrodniczuk, Eiríkur Rögnvaldsson, Mike Rosner, Bolette Sandford Pedersen, Inguna Skadiņa, Marko Tadić, Dan Tufiş, Tamás Váradi, Kadri Vider, Andy Way, François Yvon
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality.
1 code implementation • 21 Jan 2020 • Vevake Balaraman, Bernardo Magnini
In task-oriented dialogue systems the dialogue state tracker (DST) component is responsible for predicting the state of the dialogue based on the dialogue history.
no code implementations • 1 Nov 2019 • Vevake Balaraman, Bernardo Magnini
This makes extending the candidate list for a slot without model retaining infeasible and also has limitations in modelling for low resource domains where training data for slot values are expensive.
1 code implementation • 22 Oct 2019 • Vevake Balaraman, Bernardo Magnini
A Dialogue State Tracker (DST) is a key component in a dialogue system aiming at estimating the beliefs of possible user goals at each dialogue turn.
Ranked #6 on
Dialogue State Tracking
on Wizard-of-Oz
no code implementations • WS 2019 • Samuel Louvan, Bernardo Magnini
Slot filling is a core operation for utterance understanding in task-oriented dialogue systems.
1 code implementation • ACL 2019 • Serra Sinem Tekiroglu, Bernardo Magnini, Marco Guerini
We present a novel abstraction framework called FASTDial for designing task oriented dialogue agents, built on top of the OpenDial toolkit.
no code implementations • WS 2018 • Marco Guerini, Sara Falcone, Bernardo Magnini
In task-oriented conversational agents, more attention has been usually devoted to assessing task effectiveness, rather than to \textit{how} the task is achieved.
no code implementations • WS 2018 • Samuel Louvan, Bernardo Magnini
Slot filling is a crucial task in the Natural Language Understanding (NLU) component of a dialogue system.
no code implementations • WS 2018 • Marco Guerini, Simone Magnolini, Vevake Balaraman, Bernardo Magnini
We present a domain portable zero-shot learning approach for entity recognition in task-oriented conversational agents, which does not assume any annotated sentences at training time.
no code implementations • COLING 2016 • Bernardo Magnini, Anne-Lyse Minard, Mohammed R. H. Qwaider, Manuela Speranza
This paper presents TextPro-AL (Active Learning for Text Processing), a platform where human annotators can efficiently work to produce high quality training data for new domains and new languages exploiting Active Learning methodologies.
no code implementations • 3 Oct 2016 • Edoardo Maria Ponti, Elisabetta Jezek, Bernardo Magnini
Lexical sets contain the words filling an argument slot of a verb, and are in part determined by selectional preferences.
no code implementations • LREC 2016 • Anna Feltracco, Simone Magnolini, Elisabetta Jezek, Bernardo Magnini
We describe an experiment for the acquisition of opposition relations among Italian verb senses, based on a crowdsourcing methodology.
no code implementations • LREC 2014 • Elisabetta Jezek, Bernardo Magnini, Anna Feltracco, Alessia Bianchini, Octavian Popescu
The goal of this paper is to introduce T-PAS, a resource of typed predicate argument structures for Italian, acquired from corpora by manual clustering of distributional information about Italian verbs, to be used for linguistic analysis and semantic processing tasks.
no code implementations • LREC 2014 • Georg Rehm, Hans Uszkoreit, Sophia Ananiadou, N{\'u}ria Bel, Audron{\.e} Bielevi{\v{c}}ien{\.e}, Lars Borin, Ant{\'o}nio Branco, Gerhard Budin, Nicoletta Calzolari, Walter Daelemans, Radovan Garab{\'\i}k, Marko Grobelnik, Carmen Garc{\'\i}a-Mateo, Josef van Genabith, Jan Haji{\v{c}}, Inma Hern{\'a}ez, John Judge, Svetla Koeva, Simon Krek, Cvetana Krstev, Krister Lind{\'e}n, Bernardo Magnini, Joseph Mariani, John McNaught, Maite Melero, Monica Monachini, Asunci{\'o}n Moreno, Jan Odijk, Maciej Ogrodniczuk, Piotr P{\k{e}}zik, Stelios Piperidis, Adam Przepi{\'o}rkowski, Eir{\'\i}kur R{\"o}gnvaldsson, Michael Rosner, Bolette Pedersen, Inguna Skadi{\c{n}}a, Koenraad De Smedt, Marko Tadi{\'c}, Paul Thompson, Dan Tufi{\c{s}}, Tam{\'a}s V{\'a}radi, Andrejs Vasi{\c{l}}jevs, Kadri Vider, Jolanta Zabarskaite
This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics.
no code implementations • LREC 2014 • Stelios Piperidis, Harris Papageorgiou, Christian Spurk, Georg Rehm, Khalid Choukri, Olivier Hamon, Nicoletta Calzolari, Riccardo Del Gratta, Bernardo Magnini, Christian Girardi
This paper presents META-SHARE (www. meta-share. eu), an open language resource infrastructure, and its usage since its Europe-wide deployment in early 2013.
no code implementations • LREC 2012 • Ramona Bongelli, Carla Canestrari, Ilaria Riccioni, Andrzej Zuczkowski, Cinzia Buldorini, Ricardo Pietrobon, Alberto Lavelli, Bernardo Magnini
Uncertainty language permeates biomedical research and is fundamental for the computer interpretation of unstructured text.
no code implementations • LREC 2012 • Roldano Cattoni, Francesco Corcoglioniti, Christian Girardi, Bernardo Magnini, Luciano Serafini, Roberto Zanoli
The system allows (i) to import background knowledge about entities, in form of annotated RDF triples; (ii) to associate resources to entities by automatically recognizing, coreferring and linking mentions of named entities; and (iii) to derive new entities based on knowledge extracted from mentions.