Search Results for author:
Found 109 papers, 32 papers with code
UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling
Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available.
XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning Techniques
Abstract Meaning Representation (AMR) is a popular formalism of natural language that represents the meaning of a sentence as a semantic graph.
With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation
Contextualized word embeddings have been employed effectively across several tasks in Natural Language Processing, as they have proved to carry useful semantic information.
Ranked #11 on
Word Sense Disambiguation
on Supervised:
Generationary or ``How We Went beyond Word Sense Inventories and Learned to Gloss''
Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory.
Universal Semantic Annotator: the First Unified API for WSD, SRL and Semantic Parsing
In this paper, we present the Universal Semantic Annotator (USeA), which offers the first unified API for high-quality automatic annotations of texts in 100 languages through state-of-the-art systems for Word Sense Disambiguation, Semantic Role Labeling and Semantic Parsing.
Reducing Disambiguation Biases in NMT by Leveraging Explicit Word Sense Information
Recent studies have shed some light on a common pitfall of Neural Machine Translation (NMT) models, stemming from their struggle to disambiguate polysemous words without lapsing into their most frequently occurring senses in the training corpus. In this paper, we first provide a novel approach for automatically creating high-precision sense-annotated parallel corpora, and then put forward a specifically tailored fine-tuning strategy for exploiting these sense annotations during training without introducing any additional requirement at inference time. The use of explicit senses proved to be beneficial to reduce the disambiguation bias of a baseline NMT model, while, at the same time, leading our system to attain higher BLEU scores than its vanilla counterpart in 3 language pairs.
ID10M: Idiom Identification in 10 Languages
Idioms are phrases which present a figurative meaning that cannot be (completely) derived by looking at the meaning of their individual components. Identifying and understanding idioms in context is a crucial goal and a key challenge in a wide range of Natural Language Understanding tasks.
MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)
Named Entity Recognition (NER) is the task of identifying named entities in texts and classifying them through specific semantic categories, a process which is crucial for a wide range of NLP applications.
SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering
In this task, we identify a challenge that is reflective of linguistic and cognitive competencies that humans have when speaking and reasoning.
NER4ID at SemEval-2022 Task 2: Named Entity Recognition for Idiomaticity Detection
Idioms are lexically-complex phrases whose meaning cannot be derived by compositionally interpreting their components.
Invited Talk: Generationary or: “How We Went beyond Sense Inventories and Learned to Gloss”
In this talk I present Generationary, an approach that goes beyond the mainstream assumption that word senses can be represented as discrete items of a predefined inventory, and put forward a unified model which produces contextualized definitions for arbitrary lexical items, from words to phrases and even sentences.
Nibbling at the Hard Core of Word Sense Disambiguation
With state-of-the-art systems having finally attained estimated human performance, Word Sense Disambiguation (WSD) has now joined the array of Natural Language Processing tasks that have seemingly been solved, thanks to the vast amounts of knowledge encoded into Transformer-based pre-trained language models.
Probing for Predicate Argument Structures in Pretrained Language Models
Thanks to the effectiveness and wide availability of modern pretrained language models (PLMs), recently proposed approaches have achieved remarkable results in dependency- and span-based, multilingual and cross-lingual Semantic Role Labeling (SRL).
SRL4E – Semantic Role Labeling for Emotions: A Unified Evaluation Framework
In the field of sentiment analysis, several studies have highlighted that a single sentence may express multiple, sometimes contrasting, sentiments and emotions, each with its own experiencer, target and/or cause.
DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation
Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation.
ExtEnD: Extractive Entity Disambiguation
Local models for Entity Disambiguation (ED) have today become extremely powerful, in most part thanks to the advent of large pre-trained language models.
Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation
A language-independent representation of meaning is one of the most coveted dreams in Natural Language Understanding.
InVeRo-XL: Making Cross-Lingual Semantic Role Labeling Accessible with Intelligible Verbs and Roles
Notwithstanding the growing interest in cross-lingual techniques for Natural Language Processing, there has been a surprisingly small number of efforts aimed at the development of easy-to-use tools for cross-lingual Semantic Role Labeling.
AMuSE-WSD: An All-in-one Multilingual System for Easy Word Sense Disambiguation
Over the past few years, Word Sense Disambiguation (WSD) has received renewed interest: recently proposed systems have shown the remarkable effectiveness of deep learning techniques in this task, especially when aided by modern pretrained language models.
SPRING Goes Online: End-to-End AMR Parsing and Generation
In this paper we present SPRING Online Services, a Web interface and RESTful APIs for our state-of-the-art AMR parsing and generation system, SPRING (Symmetric PaRsIng aNd Generation).
GeneSis: A Generative Approach to Substitutes in Context
The lexical substitution task aims at generating a list of suitable replacements for a target word in context, ideally keeping the meaning of the modified text unchanged.
Integrating Personalized PageRank into Neural Word Sense Disambiguation
Neural Word Sense Disambiguation (WSD) has recently been shown to benefit from the incorporation of pre-existing knowledge, such as that coming from the WordNet graph.
ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension
Supervised systems have nowadays become the standard recipe for Word Sense Disambiguation (WSD), with Transformer-based language models as their primary ingredient.
Ranked #1 on
Word Sense Disambiguation
on Supervised:
IR like a SIR: Sense-enhanced Information Retrieval for Multiple Languages
With the advent of contextualized embeddings, attention towards neural ranking approaches for Information Retrieval increased considerably.
Named Entity Recognition for Entity Linking: What Works and What’s Next
Entity Linking (EL) systems have achieved impressive results on standard benchmarks mainly thanks to the contextualized representations provided by recent pretrained language models.
Ranked #4 on
Entity Disambiguation
on ACE2004
WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER
Multilingual Named Entity Recognition (NER) is a key intermediate task which is needed in many areas of NLP.
Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures
One of the common traits of past and present approaches for Semantic Role Labeling (SRL) is that they rely upon discrete labels drawn from a predefined linguistic inventory to classify predicate senses and their arguments.
EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation
We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection.
Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation
Entity disambiguation (ED) is the task of mapping an ambiguous entity mention to the corresponding entry in a structured knowledge base.
Entity Disambiguation with Entity Definitions
Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions.
AMR Alignment: Paying Attention to Cross-Attention
With the surge of Transformer models, many have investigated how attention acts on the learned representations.
REBEL: Relation Extraction By End-to-end Language generation
Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks.
Ranked #1 on
Joint Entity and Relation Extraction
on DocRED
(using extra training data)
SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC)
We illustrate our task, as well as the construction of our manually-created dataset including five languages, namely Arabic, Chinese, English, French and Russian, and the results of the participating systems.
AAA: Fair Evaluation for Abuse Detection Systems Wanted
In this work, we introduce Adversarial Attacks against Abuse (AAA), a new evaluation strategy and associated metric that better captures a model’s performance on certain classes of hard-to-classify microposts, and for example penalises systems which are biased on low-level lexical features.
Ranked #1 on
Hate Speech Detection
on Waseem et al., 2018
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources
While cross-lingual techniques are finding increasing success in a wide range of Natural Language Processing tasks, their application to Semantic Role Labeling (SRL) has been strongly limited by the fact that each language adopts its own linguistic formalism, from PropBank for English to AnCora for Spanish and PDT-Vallex for Czech, inter alia.
ESC: Redesigning WSD with Extractive Sense Comprehension
By means of an extensive array of experiments, we show that ESC unleashes the full potential of our model, leading it to outdo all of its competitors and to set a new state of the art on the English WSD task.
Ranked #4 on
Word Sense Disambiguation
on Supervised:
SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation
Graph-based semantic parsing aims to represent textual meaning through directed graphs.
One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline
In Text-to-AMR parsing, current state-of-the-art semantic parsers use cumbersome pipelines integrating several different modules or components, and exploit graph recategorization, i. e., a set of content-specific heuristics that are developed on the basis of the training set.
Ranked #1 on
AMR-to-Text Generation
on The Little Prince
(BLEURT metric)
Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration
Recent studies treat Word Sense Disambiguation (WSD) as a single-label classification problem in which one is asked to choose only the best-fitting sense for a target word, given its context.
Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach
Recent research indicates that taking advantage of complex syntactic features leads to favorable results in Semantic Role Labeling.
Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations
To date, the most successful word, word sense, and concept modelling techniques have used large corpora and knowledge resources to produce dense vector representations that capture semantic similarities in a relatively low-dimensional space.
InVeRo: Making Semantic Role Labeling Accessible with Intelligible Verbs and Roles
Semantic Role Labeling (SRL) is deeply dependent on complex linguistic resources and sophisticated neural models, which makes the task difficult to approach for non-experts.
Breaking Through the 80\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information
Neural architectures are the current state of the art in Word Sense Disambiguation (WSD).
Ranked #6 on
Word Sense Disambiguation
on Supervised:
Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation
Exploiting syntagmatic information is an encouraging research focus to be pursued in an effort to close the gap between knowledge-based and supervised Word Sense Disambiguation (WSD) performance.
Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts
Thanks to the wealth of high-quality annotated images available in popular repositories such as ImageNet, multimodal language-vision research is in full bloom.
Building Semantic Grams of Human Knowledge
Word senses are typically defined with textual definitions for human consumption and, in computational lexicons, put in context via lexical-semantic relations such as synonymy, antonymy, hypernymy, etc.
Sense-Annotated Corpora for Word Sense Disambiguation in Multiple Languages and Domains
This limits the range of action of deep-learning approaches, which today are at the base of any NLP task and are hungry for data.
Knowledge Graphs
In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data.
Game Theory Meets Embeddings: a Unified Framework for Word Sense Disambiguation
They represent ambiguous words as the players of a non cooperative game and their senses as the strategies that the players can select in order to play the games.
VerbAtlas: a Novel Large-Scale Verbal Semantic Resource and Its Application to Semantic Role Labeling
We present VerbAtlas, a new, hand-crafted lexical-semantic resource whose goal is to bring together all verbal synsets from WordNet into semantically-coherent frames.
SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations
Current research in knowledge-based Word Sense Disambiguation (WSD) indicates that performances depend heavily on the Lexical Knowledge Base (LKB) employed.
Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation
While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet.
LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories
While word embeddings are now a de facto standard representation of words in most NLP tasks, recently the attention has been shifting towards vector representations which capture the different meanings, i. e., senses, of words.
Just ``OneSeC'' for Producing Multilingual Sense-Annotated Data
The well-known problem of knowledge acquisition is one of the biggest issues in Word Sense Disambiguation (WSD), where annotated data are still scarce in English and almost absent in other languages.
SemEval-2018 Task 9: Hypernym Discovery
This paper describes the SemEval 2018 Shared Task on Hypernym Discovery.
Huge Automatically Extracted Training Sets for Multilingual Word Sense Disambiguation
We release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation.
Towards a Seamless Integration of Word Senses into Downstream NLP Applications
Lexical ambiguity can impede NLP systems from accurate understanding of semantics.
Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data
Annotating large numbers of sentences with senses is the heaviest requirement of current Word Sense Disambiguation.
Neural Sequence Learning Models for Word Sense Disambiguation
Word Sense Disambiguation models exist in many flavors.
Ranked #19 on
Word Sense Disambiguation
on Supervised:
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity
This paper introduces a new task on Multilingual and Cross-lingual SemanticThis paper introduces a new task on Multilingual and Cross-lingual Semantic Word Similarity which measures the semantic similarity of word pairs within and across five languages: English, Farsi, German, Italian and Spanish.
EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text
Parallel corpora are widely used in a variety of Natural Language Processing tasks, from Machine Translation to cross-lingual Word Sense Disambiguation, where parallel sentences can be exploited to automatically generate high-quality sense annotations on a large scale.
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup.
Ranked #4 on
Word Sense Disambiguation
on Knowledge-based:
BabelDomains: Large-Scale Domain Labeling of Lexical Resources
In this paper we present BabelDomains, a unified resource which provides lexical items with information about domains of knowledge.
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora.
A Large-Scale Multilingual Disambiguation of Glosses
Linking concepts and named entities to knowledge bases has become a crucial Natural Language Understanding task.
Natural Language Understanding
Open Information Extraction
+2
Semantic Representations of Word Senses and Concepts
Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days.
Multilinguality at Your Fingertips : BabelNet, Babelfy and Beyond !
Multilinguality is a key feature of today{'}s Web, and it is this feature that we leverage and exploit in our research work at the Sapienza University of Rome{'}s Linguistic Computing Laboratory, which I am going to overview and showcase in this talk.
Large-Scale Information Extraction from Textual Definitions through Deep Syntactic and Semantic Analysis
The output of DefIE is a high-quality knowledge base consisting of several million automatically acquired semantic relations.
Annotating the MASC Corpus with BabelNet
Finally, we estimate the quality of our annotations using both manually-tagged named entities and word senses, obtaining an accuracy of roughly 70{\%} for both named entities and word sense annotations.
Representing Multilingual Data as Linked Data: the Case of BabelNet 2.0
Recent years have witnessed a surge in the amount of semantic information published on the Web.
The CQC Algorithm: Cycling in Graphs to Semantically Enrich and Enhance a Bilingual Dictionary
Bilingual machine-readable dictionaries are knowledge resources useful in many automatic tasks.
Entity Linking meets Word Sense Disambiguation: a Unified Approach
Entity Linking (EL) and Word Sense Disambiguation (WSD) both address the lexical ambiguity of language.
Ranked #3 on
Word Sense Disambiguation
on Knowledge-based:
It's All Fun and Games until Someone Annotates: Video Games with a Purpose for Linguistic Annotation
Annotated data is prerequisite for many NLP applications.
A New Method for Evaluating Automatically Learned Terminological Taxonomies
Our method assigns a similarity value B{\textasciicircum}i{\_}(l, r) to the learned (l) and reference (r) taxonomy for each cut i of the corresponding anonymised hierarchies, starting from the topmost nodes down to the leaf concepts.
