Search Results for author:
Found 61 papers, 12 papers with code
How Universal is Metonymy? Results from a Large-Scale Multilingual Analysis
Metonymy is regarded by most linguists as a universal cognitive phenomenon, especially since the emergence of the theory of conceptual mappings.
Deep Attention Diffusion Graph Neural Networks for Text Classification
Text classification is a fundamental task with broad applications in natural language processing.
A Taxonomic Classification of WordNet Polysemy Types
WordNet represents polysemous terms by capturing the different meanings of these terms at the lexical level, but without giving emphasis on the polysemy types such terms belong to.
IndoUKC: A Concept-Centered Indian Multilingual Lexical Resource
We introduce the IndoUKC, a new multilingual lexical database comprised of eighteen Indian languages, with a focus on formally capturing words and word meanings specific to Indian languages and cultures.
ZiNet: Linking Chinese Characters Spanning Three Thousand Years
In addition, powered by the knowledge of radical systems in ZiNet, this paper introduces glyph similarity measurement between ancient Chinese characters, which could capture similar glyph pairs that are potentially related in origins or semantics.
MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology
Large-scale morphological databases provide essential input to a wide range of NLP applications.
Is this Enough?-Evaluation of Malayalam Wordnet
Quality of a product is the degree to which a product meets the customer’s expectation, which must also be valid for the case of lexical semantic resources.
Building the Mongolian WordNet
The manual evaluation of the resource1 estimated its quality at 96. 4%.
Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
Node classification is an essential problem in graph learning.
KAE: A Property-based Method for Knowledge Graph Alignment and Extension
A common solution to the semantic heterogeneity problem is to perform knowledge graph (KG) extension exploiting the information encoded in one or more candidate KGs, where the alignment between the reference KG and candidate KGs is considered the critical procedure.
Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference
By incorporating relevant visual information and leveraging linguistic knowledge, our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks.
Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification
Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach has received tremendous attention due to its powerful feature learning capability and robustness.
Layers of technology in pluriversal design. Decolonising language technology with the LiveLanguage initiative
Language technology is a complex and emerging field that presents challenges for co-design interventions due to enfolding in assemblages of global scale and diverse sites and its knowledge intensity.
Artificial Intelligence in Everyday Life 2.0: Educating University Students from Different Majors
With the surge in data-centric AI and its increasing capabilities, AI applications have become a part of our everyday lives.
Advancing the Arabic WordNet: Elevating Content Quality
High-quality WordNets are crucial for achieving high-quality results in NLP applications that rely on such resources.
From Knowledge Organization to Knowledge Representation and Back
Knowledge Organization (KO) and Knowledge Representation (KR) have been the two mainstream methodologies of knowledge modelling in the Information Science community and the Artificial Intelligence community, respectively.
TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification
However, these methods rely on unlabeled samples provided by the target domains, which renders the model ineffective when the target domain is agnostic.
From Knowledge Representation to Knowledge Organization and Back
Knowledge Representation (KR) and facet-analytical Knowledge Organization (KO) have been the two most prominent methodologies of data and knowledge modelling in the Artificial Intelligence community and the Information Science community, respectively.
Towards a Gateway for Knowledge Graph Schemas Collection, Analysis, and Embedding
One of the significant barriers to the training of statistical models on knowledge graphs is the difficulty that scientists have in finding the best input data to address their prediction goal.
Lexical Diversity in Kinship Across Languages and Dialects
The method is verified through two large-scale case studies on kinship terminology, a domain known to be diverse across languages and cultures: one case study deals with seven Arabic dialects, while the other one with three Indonesian languages.
A semantics-driven methodology for high-quality image annotation
Recent work in Machine Learning and Computer Vision has highlighted the presence of various types of systematic flaws inside ground truth object recognition benchmark datasets.
Diversity and Language Technology: How Techno-Linguistic Bias Can Cause Epistemic Injustice
It is well known that AI-based language technology -- large language models, machine translation systems, multilingual dictionaries, and corpora -- is currently limited to 2 to 3 percent of the world's most widely spoken and/or financially and politically best supported languages.
Towards Bridging the Digital Language Divide
It is a well-known fact that current AI-based language technology -- language models, machine translation systems, multilingual dictionaries and corpora -- focuses on the world's 2-3% most widely spoken languages.
Automatic Counterfactual Augmentation for Robust Text Classification Based on Word-Group Search
Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning.
Building Interoperable Electronic Health Records as Purpose-Driven Knowledge Graphs
When building a new application we are increasingly confronted with the need of reusing and integrating pre-existing knowledge.
Egocentric Hierarchical Visual Semantics
We achieve this goal by implementing an algorithm which, for any object, recursively recognizes its visual genus and its visual differentia.
Incremental Image Labeling via Iterative Refinement
Data quality is critical for multimedia tasks, while various types of systematic flaws are found in image benchmark datasets, as discussed in recent work.
Recognizing Entity Types via Properties
Thus, the entity type (etype) recognition task is proposed to deal with such heterogeneity, aiming to infer the class of entities and etypes by exploiting the information encoded in ontologies.
Towards Ranking Schemas by Focus
The main goal of this paper is to evaluate knowledge base schemas, modeled as a set of entity types, each such type being associated with a set of properties, according to their focus.
Representing Interlingual Meaning in Lexical Databases
In today's multilingual lexical databases, the majority of the world's languages are under-represented.
Aligning Visual and Lexical Semantics
We discuss two kinds of semantics relevant to Computer Vision (CV) systems - Visual Semantics and Lexical Semantics.
Popularity Driven Data Integration
The intuition is that data will be treated differently based on their popularity: the more a certain set of data have been reused, the more they will be reused and the less they will be changed across reuses, thus decreasing the overall data preprocessing costs, while increasing backward compatibility and future sharing
LiveSchema: A Gateway Towards Learning on Knowledge Graph Schemas
In this paper, we describe the LiveSchema initiative, namely a gateway that offers a family of services to easily access, analyze, transform and exploit knowledge graph schemas, with the main goal of facilitating the reuse of these resources in machine learning use cases.
Representation Heterogeneity
Semantic Heterogeneity is conventionally understood as the existence of variance in the representation of a target reality when modelled, by independent parties, in different databases, schemas and/ or data.
The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections.
Ranked #8 on
Morpheme Segmentaiton
on UniMorph 4.0
Concept-level Debugging of Part-Prototype Networks
We propose ProtoPDebug, an effective concept-level debugger for ProtoPNets in which a human supervisor, guided by the model's explanations, supplies feedback in the form of what part-prototypes must be forgotten or kept, and the model is fine-tuned to align with this supervision.
Lifelong Personal Context Recognition
We focus on the development of AIs which live in lifelong symbiosis with a human.
UniMorph 4.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship
We capture the phenomenon of diversity through the notions of lexical gap and language-specific word and use a systematic method to infer gaps semi-automatically on a large scale.
Language Diversity: Visible to Humans, Exploitable by Machines
The Universal Knowledge Core (UKC) is a large multilingual lexical database with a focus on language diversity and covering over a thousand languages.
Visual Ground Truth Construction as Faceted Classification
Recent work in Machine Learning and Computer Vision has provided evidence of systematic design flaws in the development of major object recognition benchmark datasets.
Object Recognition as Classification via Visual Properties
We base our work on the teleosemantic modelling of concepts as abilities implementing the distinct functions of recognition and classification.
Toward a Unified Framework for Debugging Concept-based Models
In this paper, we tackle interactive debugging of "gray-box" concept-based models (CBMs).
Streaming and Learning the Personal Context
The representation of the personal context is complex and essential to improve the help machines can give to humans for making sense of the world, and the help humans can give to machines to improve their efficiency.
Interactive Label Cleaning with Example-based Explanations
We tackle sequential learning under label noise in applications where a human supervisor can be queried to relabel suspicious examples.
iTelos -- Purpose Driven Knowledge Graph Generation
When building a new application we are more and more confronted with the need of reusing and integrating pre-existing knowledge, e. g., ontologies, schemas, data of any kind, from multiple sources.
Classifying concepts via visual properties
We assume that substances in the world are represented by two types of concepts, namely substance concepts and classification concepts, the former instrumental to (visual) perception, the latter to (language based) classification.
Stratified Data Integration
We propose a novel approach to the problem of semantic heterogeneity where data are organized into a set of stratified and independent representation layers, namely: conceptual(where a set of unique alinguistic identifiers are connected inside a graph codifying their meaning), language(where sets of synonyms, possibly from multiple languages, annotate concepts), knowledge(in the form of a graph where nodes are entity types and links are properties), and data(in the form of a graph of entities populating the previous knowledge graph).
Towards Visual Semantics
In this paper we provide a theory and an algorithm for how to build substance concepts which are in a one-to-one correspondence with classifications concepts, thus paving the way to the seamless integration between natural language descriptions and visual perception.
Topological Regularization for Graph Neural Networks Augmentation
The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision.
Human-in-the-loop Handling of Knowledge Drift
Motivated by this, we introduce TRCKD, a novel approach that combines automated drift detection and adaptation with an interactive stage in which the user is asked to disambiguate between different kinds of KD.
Exploring the Language of Data
We set out to uncover the unique grammatical properties of an important yet so far under-researched type of natural language text: that of short labels typically found within structured datasets.
Multi-Modal Subjective Context Modelling and Recognition
Second, existing models typically assume that context is objective, whereas in most applications context is best viewed from the user's perspective.
Learning in the Wild with Incremental Skeptical Gaussian Processes
The ability to learn from human supervision is fundamental for personal assistants and other interactive applications of AI.
A Major Wordnet for a Minority Language: Scottish Gaelic
We present a new wordnet resource for Scottish Gaelic, a Celtic minority language spoken by about 60, 000 speakers, most of whom live in Northwestern Scotland.
Continual egocentric object recognition
We present a framework capable of tackilng the problem of continual object recognition in a setting which resembles that under whichhumans see and learn.
CogNet: A Large-Scale Cognate Database
This paper introduces CogNet, a new, large-scale lexical database that provides cognates -words of common origin and meaning- across languages.
TrentoTeam at SemEval-2017 Task 3: An application of Grice Maxims in Ranking Community Question Answers
In this paper we present the Tren-toTeam system which participated to thetask 3 at SemEval-2017 (Nakov et al., 2017). We concentrated our work onapplying Grice Maxims(used in manystate-of-the-art Machine learning applica-tions(Vogel et al., 2013; Kheirabadiand Aghagolzadeh, 2012; Dale and Re-iter, 1995; Franke, 2011)) to ranking an-swers of a question by answers relevancy. Particularly, we created a ranker systembased on relevancy scores, assigned by 3main components: Named entity recogni-tion, similarity score, sentiment analysis. Our system obtained a comparable resultsto Machine learning systems.
BIG-bench Machine Learning
Named Entity Recognition (NER)
+1
Compositional Learning of Relation Path Embedding for Knowledge Base Completion
In this paper, we study the problem of how to better embed entities and relations of knowledge bases into different low-dimensional spaces by taking full advantage of the additional semantics of relation paths, and we propose a compositional learning model of relation path embedding (RPE).
