Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Research Papers — Othmane KABAL</title> | |
| <link href="https://fonts.googleapis.com/css2?family=Playfair+Display:wght@400;700&family=DM+Mono:wght@400;500&family=DM+Sans:wght@300;400;500&display=swap" rel="stylesheet"> | |
| <style> | |
| *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; } | |
| :root { | |
| --bg: #0a0e1a; | |
| --surface: #111827; | |
| --border: #1e2d45; | |
| --accent: #3b82f6; | |
| --accent2: #06b6d4; | |
| --gold: #f59e0b; | |
| --text: #e2e8f0; | |
| --muted: #64748b; | |
| --tag-bg: #1e3a5f; | |
| } | |
| body { | |
| background: var(--bg); | |
| color: var(--text); | |
| font-family: 'DM Sans', sans-serif; | |
| min-height: 100vh; | |
| overflow-x: hidden; | |
| } | |
| /* Animated background grid */ | |
| body::before { | |
| content: ''; | |
| position: fixed; | |
| inset: 0; | |
| background-image: | |
| linear-gradient(rgba(59,130,246,0.04) 1px, transparent 1px), | |
| linear-gradient(90deg, rgba(59,130,246,0.04) 1px, transparent 1px); | |
| background-size: 48px 48px; | |
| pointer-events: none; | |
| z-index: 0; | |
| } | |
| /* Glowing orbs */ | |
| .orb { | |
| position: fixed; | |
| border-radius: 50%; | |
| filter: blur(120px); | |
| pointer-events: none; | |
| z-index: 0; | |
| opacity: 0.18; | |
| } | |
| .orb-1 { width: 600px; height: 600px; background: #3b82f6; top: -200px; left: -200px; } | |
| .orb-2 { width: 400px; height: 400px; background: #06b6d4; bottom: -100px; right: -100px; } | |
| .container { | |
| position: relative; | |
| z-index: 1; | |
| max-width: 860px; | |
| margin: 0 auto; | |
| padding: 60px 24px 80px; | |
| } | |
| /* Header */ | |
| header { | |
| text-align: center; | |
| margin-bottom: 64px; | |
| } | |
| .affiliation { | |
| display: inline-flex; | |
| align-items: center; | |
| gap: 8px; | |
| font-family: 'DM Mono', monospace; | |
| font-size: 11px; | |
| letter-spacing: 0.12em; | |
| text-transform: uppercase; | |
| color: var(--accent); | |
| margin-bottom: 20px; | |
| padding: 6px 16px; | |
| border: 1px solid rgba(59,130,246,0.3); | |
| border-radius: 100px; | |
| background: rgba(59,130,246,0.07); | |
| } | |
| .affiliation::before { | |
| content: ''; | |
| width: 6px; height: 6px; | |
| background: var(--accent); | |
| border-radius: 50%; | |
| animation: pulse 2s ease-in-out infinite; | |
| } | |
| @keyframes pulse { | |
| 0%, 100% { opacity: 1; transform: scale(1); } | |
| 50% { opacity: 0.4; transform: scale(0.8); } | |
| } | |
| h1 { | |
| font-family: 'Playfair Display', serif; | |
| font-size: clamp(26px, 4vw, 40px); | |
| font-weight: 700; | |
| line-height: 1.25; | |
| color: #fff; | |
| margin-bottom: 16px; | |
| letter-spacing: -0.02em; | |
| } | |
| h1 em { | |
| font-style: italic; | |
| background: linear-gradient(135deg, var(--accent), var(--accent2)); | |
| -webkit-background-clip: text; | |
| -webkit-text-fill-color: transparent; | |
| background-clip: text; | |
| } | |
| .authors { | |
| font-size: 14px; | |
| color: var(--muted); | |
| letter-spacing: 0.02em; | |
| } | |
| .authors strong { | |
| color: var(--text); | |
| font-weight: 500; | |
| } | |
| /* Section label */ | |
| .section-label { | |
| display: flex; | |
| align-items: center; | |
| gap: 12px; | |
| margin-bottom: 24px; | |
| } | |
| .section-label span { | |
| font-family: 'DM Mono', monospace; | |
| font-size: 10px; | |
| letter-spacing: 0.15em; | |
| text-transform: uppercase; | |
| color: var(--muted); | |
| } | |
| .section-label::after { | |
| content: ''; | |
| flex: 1; | |
| height: 1px; | |
| background: var(--border); | |
| } | |
| /* Paper cards */ | |
| .papers { | |
| display: flex; | |
| flex-direction: column; | |
| gap: 20px; | |
| } | |
| .paper-card { | |
| background: var(--surface); | |
| border: 1px solid var(--border); | |
| border-radius: 16px; | |
| padding: 32px; | |
| position: relative; | |
| overflow: hidden; | |
| transition: border-color 0.3s, transform 0.3s, box-shadow 0.3s; | |
| cursor: pointer; | |
| text-decoration: none; | |
| display: block; | |
| color: inherit; | |
| } | |
| .paper-card::before { | |
| content: ''; | |
| position: absolute; | |
| inset: 0; | |
| background: linear-gradient(135deg, rgba(59,130,246,0.06), transparent 60%); | |
| opacity: 0; | |
| transition: opacity 0.3s; | |
| } | |
| .paper-card:hover { | |
| border-color: rgba(59,130,246,0.5); | |
| transform: translateY(-3px); | |
| box-shadow: 0 20px 60px rgba(0,0,0,0.5), 0 0 0 1px rgba(59,130,246,0.2); | |
| } | |
| .paper-card:hover::before { opacity: 1; } | |
| /* Accent bar left */ | |
| .paper-card::after { | |
| content: ''; | |
| position: absolute; | |
| left: 0; top: 20%; bottom: 20%; | |
| width: 3px; | |
| border-radius: 0 4px 4px 0; | |
| transition: top 0.3s, bottom 0.3s; | |
| } | |
| .card-gt2kg::after { background: linear-gradient(to bottom, var(--accent), var(--accent2)); } | |
| .card-gssl1::after { background: linear-gradient(to bottom, #8b5cf6, #ec4899); } | |
| .card-gssl2::after { background: linear-gradient(to bottom, #10b981, #06b6d4); } | |
| .paper-card:hover::after { top: 8%; bottom: 8%; } | |
| .card-header { | |
| display: flex; | |
| align-items: flex-start; | |
| justify-content: space-between; | |
| gap: 16px; | |
| margin-bottom: 16px; | |
| } | |
| .card-number { | |
| font-family: 'DM Mono', monospace; | |
| font-size: 11px; | |
| color: var(--muted); | |
| letter-spacing: 0.1em; | |
| flex-shrink: 0; | |
| margin-top: 3px; | |
| } | |
| .tags { | |
| display: flex; | |
| flex-wrap: wrap; | |
| gap: 6px; | |
| margin-left: auto; | |
| } | |
| .tag { | |
| font-family: 'DM Mono', monospace; | |
| font-size: 10px; | |
| letter-spacing: 0.08em; | |
| padding: 3px 10px; | |
| border-radius: 100px; | |
| border: 1px solid; | |
| } | |
| .tag-blue { color: #60a5fa; border-color: rgba(96,165,250,0.3); background: rgba(59,130,246,0.1); } | |
| .tag-purple { color: #a78bfa; border-color: rgba(167,139,250,0.3); background: rgba(139,92,246,0.1); } | |
| .tag-teal { color: #34d399; border-color: rgba(52,211,153,0.3); background: rgba(16,185,129,0.1); } | |
| .tag-pink { color: #f472b6; border-color: rgba(244,114,182,0.3); background: rgba(236,72,153,0.1); } | |
| .paper-title { | |
| font-family: 'Playfair Display', serif; | |
| font-size: 18px; | |
| font-weight: 700; | |
| color: #fff; | |
| line-height: 1.4; | |
| margin-bottom: 10px; | |
| letter-spacing: -0.01em; | |
| } | |
| .paper-venue { | |
| font-size: 12px; | |
| color: var(--gold); | |
| font-family: 'DM Mono', monospace; | |
| letter-spacing: 0.06em; | |
| margin-bottom: 14px; | |
| } | |
| .paper-abstract { | |
| font-size: 14px; | |
| color: #94a3b8; | |
| line-height: 1.7; | |
| margin-bottom: 20px; | |
| } | |
| .paper-footer { | |
| display: flex; | |
| align-items: center; | |
| justify-content: space-between; | |
| gap: 12px; | |
| flex-wrap: wrap; | |
| } | |
| .paper-authors { | |
| font-size: 12px; | |
| color: var(--muted); | |
| font-style: italic; | |
| } | |
| .read-btn { | |
| display: inline-flex; | |
| align-items: center; | |
| gap: 8px; | |
| font-size: 12px; | |
| font-weight: 500; | |
| font-family: 'DM Mono', monospace; | |
| letter-spacing: 0.08em; | |
| color: var(--accent); | |
| transition: gap 0.2s; | |
| text-decoration: none; | |
| } | |
| .paper-card:hover .read-btn { gap: 12px; } | |
| .read-btn svg { width: 14px; height: 14px; } | |
| /* Divider with number */ | |
| .divider { | |
| display: flex; | |
| align-items: center; | |
| gap: 16px; | |
| margin: 40px 0 32px; | |
| } | |
| .divider::before, .divider::after { | |
| content: ''; flex: 1; height: 1px; background: var(--border); | |
| } | |
| .divider-text { | |
| font-family: 'DM Mono', monospace; | |
| font-size: 10px; | |
| letter-spacing: 0.15em; | |
| text-transform: uppercase; | |
| color: var(--muted); | |
| white-space: nowrap; | |
| } | |
| /* Footer */ | |
| footer { | |
| text-align: center; | |
| margin-top: 64px; | |
| padding-top: 32px; | |
| border-top: 1px solid var(--border); | |
| } | |
| .footer-text { | |
| font-size: 12px; | |
| color: var(--muted); | |
| font-family: 'DM Mono', monospace; | |
| letter-spacing: 0.06em; | |
| } | |
| .footer-text a { color: var(--accent); text-decoration: none; } | |
| /* Responsive */ | |
| @media (max-width: 600px) { | |
| .paper-card { padding: 24px 20px; } | |
| .card-header { flex-direction: column; } | |
| h1 { font-size: 22px; } | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <div class="orb orb-1"></div> | |
| <div class="orb orb-2"></div> | |
| <div class="container"> | |
| <header> | |
| <div class="affiliation">Nantes University · LS2N · JDOC 2025</div> | |
| <h1>Combining <em>Knowledge Graph Embedding</em><br>and Prior Knowledge Based<br>Semi-Supervised Learning</h1> | |
| <p class="authors"> | |
| <strong>Othmane KABAL</strong>, Mounira HARAZALLAH, Fabrice GUILLET<br> | |
| Nantes University, LS2N, Nantes, 44300, France | |
| </p> | |
| </header> | |
| <!-- GT2KG Section --> | |
| <div class="section-label"> | |
| <span>Publication 01 — Knowledge Graph Construction</span> | |
| </div> | |
| <div class="papers"> | |
| <a class="paper-card card-gt2kg" href="https://www.sciencedirect.com/science/article/pii/S1877050924024761" target="_blank" rel="noopener"> | |
| <div class="card-header"> | |
| <span class="card-number">01</span> | |
| <div class="tags"> | |
| <span class="tag tag-blue">GT2KG</span> | |
| <span class="tag tag-blue">Knowledge Graph</span> | |
| <span class="tag tag-blue">Information Extraction</span> | |
| </div> | |
| </div> | |
| <div class="paper-title">GT2KG: A Domain-Independent Knowledge Graph Construction Pipeline from Textual Corpora</div> | |
| <div class="paper-venue">Procedia Computer Science · ScienceDirect · 2024</div> | |
| <p class="paper-abstract"> | |
| A domain-independent pipeline for constructing knowledge graphs from raw text. GT2KG combines coreference resolution, open information extraction, rule-based cleaning, and LLM-based validation (GPT-4) to produce structured (subject, predicate, object) triplets, evaluated on Computer Science and Music corpora. | |
| </p> | |
| <div class="paper-footer"> | |
| <span class="paper-authors">Kabal, Harazallah, Guillet</span> | |
| <span class="read-btn"> | |
| Read paper | |
| <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M5 12h14M12 5l7 7-7 7"/></svg> | |
| </span> | |
| </div> | |
| </a> | |
| </div> | |
| <!-- GSSL Section --> | |
| <div class="divider"><span class="divider-text">Publications 02 & 03 — Representation Learning</span></div> | |
| <div class="section-label"> | |
| <span>Graph Self-Supervised Learning & Noise Analysis</span> | |
| </div> | |
| <div class="papers"> | |
| <a class="paper-card card-gssl1" href="https://arxiv.org/abs/2605.05463" target="_blank" rel="noopener"> | |
| <div class="card-header"> | |
| <span class="card-number">02</span> | |
| <div class="tags"> | |
| <span class="tag tag-purple">GSSL</span> | |
| <span class="tag tag-purple">Graph Learning</span> | |
| <span class="tag tag-pink">Ontology Learning</span> | |
| </div> | |
| </div> | |
| <div class="paper-title">Graph Self-Supervised Learning for Ontology Learning from Text-Derived Knowledge Graphs</div> | |
| <div class="paper-venue">arXiv · 2605.05463 · 2025</div> | |
| <p class="paper-abstract"> | |
| Evaluation of graph self-supervised learning (GSSL) methods — feature reconstruction, relation reconstruction, and contrastive learning — on text-derived knowledge graphs for ontology learning tasks, using multiple GNN backbones with different message-passing mechanisms. | |
| </p> | |
| <div class="paper-footer"> | |
| <span class="paper-authors">Kabal, Harazallah, Guillet</span> | |
| <span class="read-btn"> | |
| Read paper | |
| <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M5 12h14M12 5l7 7-7 7"/></svg> | |
| </span> | |
| </div> | |
| </a> | |
| <a class="paper-card card-gssl2" href="https://arxiv.org/abs/2605.05476" target="_blank" rel="noopener"> | |
| <div class="card-header"> | |
| <span class="card-number">03</span> | |
| <div class="tags"> | |
| <span class="tag tag-teal">Graph Noise</span> | |
| <span class="tag tag-teal">Text-Derived KG</span> | |
| <span class="tag tag-teal">Representation Learning</span> | |
| </div> | |
| </div> | |
| <div class="paper-title">Impact of Graph Noise on Representation Learning from Text-Derived Knowledge Graphs</div> | |
| <div class="paper-venue">arXiv · 2605.05476 · 2025</div> | |
| <p class="paper-abstract"> | |
| Analysis of the impact of structural and semantic noise — fragmentation, sparsity, incorrect triplets, duplicated entities — in automatically constructed text-derived knowledge graphs on downstream representation learning and entity typing performance. | |
| </p> | |
| <div class="paper-footer"> | |
| <span class="paper-authors">Kabal, Harazallah, Guillet</span> | |
| <span class="read-btn"> | |
| Read paper | |
| <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M5 12h14M12 5l7 7-7 7"/></svg> | |
| </span> | |
| </div> | |
| </a> | |
| </div> | |
| <footer> | |
| <p class="footer-text"> | |
| Nantes University · LS2N Laboratory · 2025<br><br> | |
| <a href="mailto:othmane.kabal@univ-nantes.fr">othmane.kabal@univ-nantes.fr</a> | |
| </p> | |
| </footer> | |
| </div> | |
| </body> | |
| </html> | |