News from Sapienza NLP

SapienzaNLP @ IJCAI 2021

4 + 2 accepted papers at IJCAI 2021

We are proud to announce that our group will be at IJCAI 2021 with 6 accepted papers: 4 in the main track and 2 surveys! Once again, our papers touch several areas of Semantics in NLP ranging from multilingual alignment to Word Sense Disambiguation, Semantic Role Labeling and Lexical Substitution.

Here are our latest papers at the main track of IJCAI 2021:

  • Exemplification Modeling: Can You Give Me an Example, Please?
  • MultiMirror: Neural Cross-lingual Word Alignment for Multilingual Word Sense Disambiguation
  • ALaSca: an Automated approach for Large-Scale Lexical Substitution
  • Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

Here are our latest papers at the survey track of IJCAI 2021:

  • Ten Years of BabelNet: A Survey
  • Recent Trends in Word Sense Disambiguation: A Survey

Exemplification Modeling: Can You Give Me an Example, Please?

by Luigi Procopio, Edoardo Barba, Federico Martelli and Roberto Navigli

Word Sense Disambiguation (WSD), i.e., the task of assigning senses to words in context, has seen a surge of interest with the advent of neural models and a considerable increase in performance up to 80% F1 in English. However, when considering other languages, the availability of training data is limited, which hampers scaling WSD to many languages. To address this issue, we put forward MultiMirror, a sense projection approach for multilingual WSD based on a novel neural discriminative model for word alignment: given as input a pair of parallel sentences, our model -- trained with a low number of instances -- is capable of jointly aligning, at the same time, all source and target tokens with each other, surpassing its competitors across several language combinations. We demonstrate that projecting senses from English by leveraging the alignments produced by our model leads a simple mBERT-powered classifier to achieve a new state of the art on established WSD datasets in French, German, Italian, Spanish and Japanese. We release our software and all our datasets at

MultiMirror: Neural Cross-lingual Word Alignment for Multilingual Word Sense Disambiguation

by Edoardo Barba, Luigi Procopio, Caterina Lacerra, Tommaso Pasini and Roberto Navigli

Recently, generative approaches have been used effectively to provide definitions of words in their context. However, the opposite, i.e., generating a usage example given one or more words along with their definitions, has not yet been investigated. In this work, we introduce the novel task of Exemplification Modeling (ExMod), along with a sequence-to-sequence architecture and a training procedure for it. Starting from a set of (word, definition) pairs, our approach is capable of automatically generating high-quality sentences which express the requested semantics. As a result, we can drive the creation of sense-tagged data which cover the full range of meanings in any inventory of interest, and their interactions within sentences. Human annotators agree that the sentences generated are as fluent and semantically-coherent with the input definitions as the sentences in manually-annotated corpora. Indeed, when employed as training data for Word Sense Disambiguation, our examples enable the current state of the art to be outperformed, and higher results to be achieved than when using gold-standard datasets only. We release the pretrained model, the dataset and the software at

ALaSca: an Automated approach for Large-Scale Lexical Substitution

by Caterina Lacerra, Tommaso Pasini, Rocco Tripodi and Roberto Navigli

The lexical substitution task aims at finding suitable replacements for words in context. The paucity of annotated data has forced researchers to apply mainly unsupervised approaches, limiting the applicability of large pre-trained models and thus hampering the potential benefits of supervised approaches to the task. We mitigate this issue by proposing ALaSca, a novel approach to automatically creating large-scale datasets for English lexical substitution. ALaSca allows examples to be produced for potentially any word in a language vocabulary and to cover most of the meanings it lists. Thanks to this, we can unleash the full potential of neural architectures and finetune them on the lexical substitution task. Indeed, when using our data, a transformer-based model performs substantially better than when using manually-annotated data only.

Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

by Rexhina Blloshmi, Simone Conia, Rocco Tripodi and Roberto Navigli

Semantic role labeling (SRL) aims to discover the predicateargument structure of a sentence. End-to-end SRL without syntactic input has received great attention. However, most of them focus on either span-based or dependency-based semantic representation form and only show specific model optimization respectively. Meanwhile, handling these two SRL tasks uniformly was less successful. This paper presents an end-to-end model for both dependency and span SRL with a unified argument representation to deal with two different types of argument annotations in a uniform fashion. Furthermore, we jointly predict all predicates and arguments, especially including long-term ignored predicate identification subtask. Our single model achieves new state-of-the-art results on both span (CoNLL 2005, 2012) and dependency (CoNLL 2008, 2009) SRL benchmarks.

Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

by Rexhina Blloshmi, Simone Conia, Rocco Tripodi and Roberto Navigli

Despite the recent great success of the sequence-to-sequence paradigm in Natural Language Processing, the majority of current studies in Semantic Role Labeling (SRL) still frame the problem as a sequence labeling task. In this paper we go against the flow and propose GSRL (Generating Senses and RoLes), the first sequence-to-sequence model for end-to-end SRL. Our approach benefits from recently-proposed decoder-side pretraining techniques to generate both sense and role labels for all the predicates in an input sentence at once, in an end-to-end fashion. Evaluated on standard gold benchmarks, GSRL achieves state-of-the-art results in both dependency- and span-based English SRL, proving empirically that our simple generation-based model can learn to produce complex predicate-argument structures. Finally, we propose a framework for evaluating the robustness of an SRL model in a variety of synthetic low-resource scenarios which can aid human annotators in the creation of better, more diverse, and more challenging gold datasets. We release GSRL at

Ten Years of BabelNet: A Survey

by Roberto Navigli, Michele Bevilacqua, Simone Conia, Dario Montagnini and Francesco Cecconi

The intelligent manipulation of symbolic knowledge has been a long-sought goal of AI. However, when it comes to Natural Language Processing (NLP), symbols have to be mapped to words and phrases, which are not only ambiguous but also language-specific: multilinguality is indeed a desirable property for NLP systems, and one which enables the generalization of tasks where multiple languages need to be dealt with, without translating text. In this paper we survey BabelNet, a popular wide-coverage lexical-semantic knowledge resource obtained by merging heterogeneous sources into a unified semantic network that helps to scale tasks and applications to hundreds of languages. Over its ten years of existence, thanks to its promise to interconnect languages and resources in structured form, BabelNet has been employed in countless ways and directions. We first introduce the BabelNet model, its components and statistics, and then overview its successful use in a wide range of tasks in NLP as well as in other fields of AI.

Recent Trends in Word Sense Disambiguation: A Survey

by Michele Bevilacqua, Tommaso Pasini, Alessandro Raganato and Roberto Navigli

Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word in context by identifying the most suitable meaning from a predefined sense inventory. Recent breakthroughs in representation learning have fueled intensive WSD research, resulting in considerable performance improvements, breaching the 80% glass ceiling set by the inter-annotator agreement. In this survey, we provide an extensive overview of current advances in WSD, describing the state of the art in terms of i) resources for the task, i.e., sense inventories and reference datasets for training and testing, as well as ii) automatic disambiguation approaches, detailing their peculiarities, strengths and weaknesses. Finally, we highlight the current limitations of the task itself, but also point out recent trends that could help expand the scope and applicability of WSD, setting up new promising directions for the future.