COVER: a linguistic resource combining common sense and lexicographic information

Mensa, Enrico; Radicioni, Daniele Paolo; Lieto, Antonio

doi:10.1007/s10579-018-9417-z

Cited by 12 publications

(12 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…common features are the elements at the intersection of the two features sets, whilst distinctive features are owned by only one of the considered entities. This notion of similarity has been recently adjusted to model human similarity judgments for short texts (the Symmetrical Tversky Ratio Model [61]), and employed to compute semantic similarity of word pairs [62,63]. Another approach to similarity builds on the distinction between attributes and relations [64].…”

Section: Cognitively Plausible Semantic Distance Metricsmentioning

confidence: 99%

Novel metrics for computing semantic similarity with sense embeddings

Colla

Mensa

Radicioni

2020

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

In the last years many efforts have been spent to build word embeddings, a representational device in which word meanings are described through dense unit vectors of real numbers over a continuous, high-dimensional Euclidean space, where similarity can be interpreted as a metric. Afterwards, senselevel embeddings have been proposed to describe the meaning of senses, rather than terms. More recently, additional intermediate representations have been designed, providing a vector description for pairs ⟨term, sense⟩, and mapping both term and sense descriptions onto a shared semantic space. However, surprisingly enough, this wealth of approaches and resources has not been supported by a parallel refinement in the metrics used to compute semantic similarity: to date, the semantic similarity featuring two input entities is mostly computed as the maximization of some angular distance intervening between vector pairs, typically cosine similarity. In this work we introduce two novel similarity metrics to compare sense-level representations, and show that by exploiting the features of sense-embeddings it is possible to substantially improve on existing strategies, by obtaining enhanced correlation with human similarity ratings. Additionally, we argue that semantic similarity needs to be complemented by another task, involving the identification of the senses at the base of the similarity rating. We experimentally verified that the proposed metrics are beneficial when dealing with both semantic similarity task and sense identification task. The experimentation also provides a detailed how-to illustrating how six important sets of sense embeddings can be used to implement the proposed similarity metrics.

show abstract

Section: Cognitively Plausible Semantic Distance Metricsmentioning

confidence: 99%

Novel metrics for computing semantic similarity with sense embeddings

Colla

Mensa

Radicioni

2020

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, the nodes in the network represent concepts and entities (that is, persons, organisations and locations), and the edges intervening between each two nodes represent semantic relations (such as IsA, PartOf, etc.). Although further lexical resource exist containing different sorts of knowledge (such as, e.g., WordNet [27], ConceptNet [23], COVER [20,26], or a hybrid approach proposed by [12,21]), we chose to adopt BabelNet in that it ensures a broad coverage to concepts and entities as well, that in the present domain are particularly relevant. The semantic module aims at searching the terms present in the theses title, to individuate the underlying concept and then at checking whether they are either philosophical concepts (that is, linked to 'philosophy' in the BabelNet taxonomy) or philosophers.…”

Section: The Semantic Modulementioning

confidence: 99%

Semantically Aware Text Categorisation for Metadata Annotation

Carducci

Leontino

Radicioni

et al. 2019

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

In this paper we illustrate a system aimed at solving a longstanding and challenging problem: acquiring a classifier to automatically annotate bibliographic records by starting from a huge set of unbalanced and unlabelled data. We illustrate the main features of the dataset, the learning algorithm adopted, and how it was used to discriminate philosophical documents from documents of other disciplines. One strength of our approach lies in the novel combination of a standard learning approach with a semantic one: the results of the acquired classifier are improved by accessing a semantic network containing conceptual information. We illustrate the experimentation by describing the construction rationale of training and test set, we report and discuss the obtained results and conclude by drawing future work.

show abstract

“…In machine learning, decision trees [4] and sparse linear models [5] are popular examples of techniques that produce interpretable models. Also in the AI field, some sort of lexical resources have been employed to assist in the construction of the explanation of semantic similarity ratings between word pairs [6,7]. Many sorts of explanation can be drawn, responding to diverse needs underlying the general aim at providing more transparency to algorithms and systems.…”

Section: Introductionmentioning

confidence: 99%

Violence detection explanation via semantic roles embeddings

Mensa

Colla

Dalmasso

et al. 2020

BMC Med Inform Decis Mak

Self Cite

View full text Add to dashboard Cite

Background Emergency room reports pose specific challenges to natural language processing techniques. In this setting, violence episodes on women, elderly and children are often under-reported. Categorizing textual descriptions as containing violence-related injuries (V) vs. non-violence-related injuries (NV) is thus a relevant task to the ends of devising alerting mechanisms to track (and prevent) violence episodes. Methods We present ViDeS (so dubbed after Violence Detection System), a system to detect episodes of violence from narrative texts in emergency room reports. It employs a deep neural network for categorizing textual ER reports data, and complements such output by making explicit which elements corroborate the interpretation of the record as reporting about violence-related injuries. To these ends we designed a novel hybrid technique for filling semantic frames that employs distributed representations of terms herein, along with syntactic and semantic information. The system has been validated on real data annotated with two sorts of information: about the presence vs. absence of violence-related injuries, and about some semantic roles that can be interpreted as major cues for violent episodes, such as the agent that committed violence, the victim, the body district involved, etc.. The employed dataset contains over 150K records annotated with class (V,NV) information, and 200 records with finer-grained information on the aforementioned semantic roles. Results We used data coming from an Italian branch of the EU-Injury Database (EU-IDB) project, compiled by hospital staff. Categorization figures approach full precision and recall for negative cases and.97 precision and.94 recall on positive cases. As regards as the recognition of semantic roles, we recorded an accuracy varying from.28 to.90 according to the semantic roles involved. Moreover, the system allowed unveiling annotation errors committed by hospital staff. Conclusions Explaining systems’ results, so to make their output more comprehensible and convincing, is today necessary for AI systems. Our proposal is to combine distributed and symbolic (frame-like) representations as a possible answer to such pressing request for interpretability. Although presently focused on the medical domain, the proposed methodology is general and, in principle, it can be extended to further application areas and categorization tasks.

show abstract

COVER: a linguistic resource combining common sense and lexicographic information

Cited by 12 publications

References 57 publications

Novel metrics for computing semantic similarity with sense embeddings

Novel metrics for computing semantic similarity with sense embeddings

Semantically Aware Text Categorisation for Metadata Annotation

Violence detection explanation via semantic roles embeddings

Contact Info

Product

Resources

About