no code implementations • NAACL 2022 • Danilo Croce, Simone Filice, Giuseppe Castellucci, Roberto Basili
Experiments in low resource settings show that augmenting the training material with the proposed strategy systematically improves the results on text classification and natural language inference tasks by up to 10% accuracy, outperforming existing DA approaches.
no code implementations • COLING 2022 • Jason Ingyu Choi, Saar Kuzi, Nikhita Vedula, Jie Zhao, Giuseppe Castellucci, Marcus Collins, Shervin Malmasi, Oleg Rokhlenko, Eugene Agichtein
Conversational Task Assistants (CTAs) are conversational agents whose goal is to help humans perform real-world tasks.
1 code implementation • 9 Apr 2024 • Nikhita Vedula, Giuseppe Castellucci, Eugene Agichtein, Oleg Rokhlenko, Shervin Malmasi
Conversational Task Assistants (CTAs) guide users in performing a multitude of activities, such as making recipes.
no code implementations • 3 Apr 2024 • Parth Patwa, Simone Filice, Zhiyu Chen, Giuseppe Castellucci, Oleg Rokhlenko, Shervin Malmasi
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.
no code implementations • 21 Nov 2023 • Simone Filice, Jason Ingyu Choi, Giuseppe Castellucci, Eugene Agichtein, Oleg Rokhlenko
Experiments on three tasks, i. e., Shopping Utterance Generation, Product Question Generation and Query Auto Completion, demonstrate that our metrics are effective for evaluating STG tasks, and improve the agreement with human judgement up to 20% with respect to common NLG metrics.
no code implementations • 25 Oct 2023 • Besnik Fetahu, Pedro Faustini, Giuseppe Castellucci, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi
Using a new dataset of 6681 input questions and human written hints, we evaluated the models with automatic metrics and human evaluation.
no code implementations • 22 Feb 2023 • Sudipta Kar, Giuseppe Castellucci, Simone Filice, Shervin Malmasi, Oleg Rokhlenko
In this paper, we approach the problem of incrementally expanding MTL models' capability to solve new tasks over time by distilling the knowledge of an already trained model on n tasks into a new one for solving n+1 tasks.
no code implementations • 13 Sep 2022 • Anna Gottardi, Osman Ipek, Giuseppe Castellucci, Shui Hu, Lavina Vaz, Yao Lu, Anju Khatri, Anjali Chadha, Desheng Zhang, Sattvik Sahai, Prerna Dwivedi, Hangjie Shi, Lucy Hu, Andy Huang, Luke Dai, Bofei Yang, Varun Somani, Pankaj Rajan, Ron Rezac, Michael Johnston, Savanna Stiff, Leslie Ball, David Carmel, Yang Liu, Dilek Hakkani-Tur, Oleg Rokhlenko, Kate Bland, Eugene Agichtein, Reza Ghanadan, Yoelle Maarek
Since its inception in 2016, the Alexa Prize program has enabled hundreds of university students to explore and compete to develop conversational agents through the SocialBot Grand Challenge.
no code implementations • ACL 2021 • Giuseppe Castellucci, Simone Filice, Danilo Croce, Roberto Basili
In real scenarios, a multilingual model trained to solve NLP tasks on a set of languages can be required to support new languages over time.
no code implementations • EACL 2021 • Simone Filice, Giuseppe Castellucci, Marcus Collins, Eugene Agichtein, Oleg Rokhlenko
This common user intent is usually available through a {``}filter-by{''} interface on online shopping websites, but is challenging to support naturally via voice, as the intent of refinements must be interpreted in the context of the original search, the initial results, and the available product catalogue facets.
2 code implementations • ACL 2020 • Danilo Croce, Giuseppe Castellucci, Roberto Basili
Recent Transformer-based architectures, e. g., BERT, provide impressive results in many Natural Language Processing tasks.
no code implementations • 17 Jul 2019 • Valentina Bellomaria, Giuseppe Castellucci, Andrea Favalli, Raniero Romagnoli
The widespread use of conversational and question answering systems made it necessary to improve the performances of speaker intent detection and understanding of related semantic slots, i. e., Spoken Language Understanding (SLU).
no code implementations • 5 Jul 2019 • Giuseppe Castellucci, Valentina Bellomaria, Andrea Favalli, Raniero Romagnoli
Moreover, we annotated a new dataset for the Italian language, and we observed similar performances without the need for changing the model.
no code implementations • ACL 2017 • Danilo Croce, Simone Filice, Giuseppe Castellucci, Roberto Basili
Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks.
no code implementations • LREC 2016 • Giuseppe Castellucci, Danilo Croce, Roberto Basili
Sentiment Analysis systems aims at detecting opinions and sentiments that are expressed in texts.
no code implementations • LREC 2014 • Emanuele Bastianelli, Giuseppe Castellucci, Danilo Croce, Luca Iocchi, Roberto Basili, Daniele Nardi
Recent years show the development of large scale resources (e. g. FrameNet for the Frame Semantics) that supported the definition of several state-of-the-art approaches in Natural Language Processing.