Papers by Stefano Faralli
Evaluation Dataset and Methodology for Extracting Application-Specific Taxonomies from the Wikipedia Knowledge Graph (2020.lrec-1)
Copied to clipboard
| Challenge: | Recent efforts to extract hierarchical relations from unstructured text have been challenging. |
| Approach: | They propose an iterative method to extract an application-specific gold standard dataset from a Wikipedia knowledge graph and an evaluation framework to assess the quality of noisy automatically extracted taxonomies. |
| Outcome: | The proposed method reduces manual work and provides a first gold standard dataset and evaluation framework. |
Improving Hypernymy Extraction with Distributional Semantic Classes (L18-1)
Copied to clipboard
| Challenge: | Existing methods for extracting hypernyms focus on the acquisition of binary hypernies . |
| Approach: | They propose a distributionally-induced semantic class for extracting hypernyms . they also use distributional semantics to induce sense-aware semantic classes . |
| Outcome: | The proposed method improves the quality of the hypernymy extraction in terms of precision and recall. |
Multiple Knowledge GraphDB (MKGDB) (2020.lrec-1)
Copied to clipboard
| Challenge: | ConceptNet, DBpedia, WebIsAGraph, WordNet and Wikipedia category hierarchy are used to create a large-scale graph database. |
| Approach: | They propose to use multiple taxonomy backbones extracted from 5 existing knowledge graphs to create a large-scale graph database. |
| Outcome: | The proposed database is intended to favour and support the development of open-domain natural language processing applications relying on knowledge bases. |
Enriching Frame Representations with Distributionally Induced Senses (L18-1)
Copied to clipboard
| Challenge: | lexical resource that enriches Framester knowledge graph with semantic features from text corpora . paves way for development of novel, deeper semantic-aware applications . |
| Approach: | They propose a lexical resource that enriches the Framester knowledge graph with semantic features from text corpora. |
| Outcome: | The proposed resource enables the development of deeper semantic-aware applications . it combines knowledge from text and symbolic representations of events and participants . |
Universal Semantic Annotator: the First Unified API for WSD, SRL and Semantic Parsing (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to understanding textual information are still far from achieving true natural language understanding (NLU). |
| Approach: | They propose a 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 Semantics Parsing. |
| Outcome: | The proposed system can provide users with rich and diverse semantic information, help second-language learners, and integrate explicit semantic knowledge into downstream tasks and real-world applications. |
A Large Interlinked Knowledge Graph of the Italian Cultural Heritage (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing efforts to create knowledge bases are limited to relatively small resources, such as entities from libraries, archeological sites and museums. |
| Approach: | They propose to create a large knowledge graph linking Italian cultural heritage entities with concepts defined on well-known knowledge bases. |
| Outcome: | The proposed graph shows that the Italian cultural heritage entities are interlinked with concepts defined on well-known knowledge bases. |
MIsA: Multilingual “IsA” Extraction from Corpora (L18-1)
Copied to clipboard
| Challenge: | In this paper, we present a collection of hypernymy relations extracted from the Wikipedia corpus in five languages. |
| Approach: | They present a collection of hypernymy relations extracted from the Wikipedia corpus in five languages . they use existing or newly defined lexico-syntactic patterns to extract hyperniyms . |
| Outcome: | The proposed tool is based on a dictionary extracted from the full Wikipedia corpus. |
A Large Multilingual and Multi-domain Dataset for Recommender Systems (L18-1)
Copied to clipboard
| Challenge: | Existing algorithms for recommending items are limited and focused on specific domains. |
| Approach: | They propose a multi-domain interests dataset to train and test Recommender Systems . the english dataset includes an average of 90 preferences per user on music, books, movies, celebrities, sport, politics . |
| Outcome: | The proposed method exploits popular services such as Spotify, Goodreads and others to extract preferences from Twitter messages in Italian and English. |
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl (L18-1)
Copied to clipboard
| Challenge: | DepCC is the largest-to-date linguistically analyzed corpus in English . large corpora are essential for the modern data-driven approaches to natural language processing . |
| Approach: | They present a large-to-date linguistically analyzed corpus in English with 365 million documents . they build an index of all sentences and their linguistic meta-data enabling quick search across the corpus . |
| Outcome: | The proposed model outperforms state-of-the-art models on smaller corpora on the SimVerb3500 dataset. |