no code implementations • ECNLP (ACL) 2022 • Xiaoyu Shen, Gianni Barlacchi, Marco del Tredici, Weiwei Cheng, Bill Byrne, Adrià Gispert
In this paper, we build a benchmark with annotations for both evidence selection and answer generation covering 6 information sources.
no code implementations • ECNLP (ACL) 2022 • Xiaoyu Shen, Gianni Barlacchi, Marco del Tredici, Weiwei Cheng, Adrià Gispert
To fill in this blank, here we study how to effectively incorporate semi-structured answer sources for PQA and focus on presenting answers in a natural, fluent sentence.
no code implementations • 5 Aug 2022 • Xiaoyu Shen, Svitlana Vakulenko, Marco del Tredici, Gianni Barlacchi, Bill Byrne, Adrià De Gispert
Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-answering systems.
no code implementations • NLP4ConvAI (ACL) 2022 • Marco del Tredici, Xiaoyu Shen, Gianni Barlacchi, Bill Byrne, Adrià De Gispert
In conversational QA, models have to leverage information in previous turns to answer upcoming questions.
no code implementations • COLING 2020 • Marco del Tredici, Raquel Fernández
Cognitive and social traits of individuals are reflected in language use.
1 code implementation • ACL 2020 • Mario Giulianelli, Marco del Tredici, Raquel Fernández
This paper presents the first unsupervised approach to lexical semantic change that makes use of contextualised word representations.
no code implementations • IJCNLP 2019 • Marco Del Tredici, Diego Marcheggiani, Sabine Schulte im Walde, Raquel Fernández
Information about individuals can help to better understand what they say, particularly in social media where texts are short.
1 code implementation • ACL 2019 • Dominik Schlechtweg, Anna Hätty, Marco del Tredici, Sabine Schulte im Walde
We perform an interdisciplinary large-scale evaluation for detecting lexical semantic divergences in a diachronic and in a synchronic task: semantic sense changes across time, and semantic sense changes across domains.
no code implementations • NAACL 2019 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
Abuse on the Internet represents a significant societal problem of our time.
no code implementations • 14 Feb 2019 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of abusive and offensive language on the Internet.
1 code implementation • NAACL 2019 • Marco Del Tredici, Raquel Fernández, Gemma Boleda
We present the first exploration of meaning shift over short periods of time in online communities using distributional representations.
1 code implementation • COLING 2018 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of hateful and offensive language on the Internet.
no code implementations • COLING 2018 • Marco Del Tredici, Raquel Fernández
We investigate the birth and diffusion of lexical innovations in a large dataset of online social communities.
no code implementations • WS 2017 • Marco Del Tredici, Raquel Fernández
We introduce a framework for quantifying semantic variation of common words in Communities of Practice and in sets of topic-related communities.
no code implementations • 10 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.
no code implementations • LREC 2016 • Marco Del Tredici, N{\'u}ria Bel
The work moves from the observation that while some verbs can be used to create highly metaphoric expressions, others can not.
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.