CompUGE-Bench / src /app /components /body /body.component.html
Ahmad Shallouf
updated some conditions
3a89ad3
<div class="container">
<mat-card>
<mat-card-header>
<mat-card-title>
<h1>Welcome to CompUGE</h1>
</mat-card-title>
</mat-card-header>
<mat-card-content>
<section>
<h2>What is Comparative Question Answering?</h2>
<p>Comparative question answering (CQA) is a specialized field within natural language processing (NLP) focused
on generating responses to questions that require comparing two or more entities across specific attributes or
dimensions. This involves identifying the entities and attributes in the query, retrieving relevant
information from various sources, and synthesizing this data into a coherent comparison. CQA systems are
particularly useful in domains such as e-commerce, healthcare, education, and technology, where users seek
detailed comparisons to make informed decisions. These systems face challenges such as handling ambiguous
queries, understanding context, ensuring data quality, and developing robust evaluation metrics to assess the
accuracy and relevance of the comparisons generated.</p>
<section>
<br><br>
<h2>What is CompUGE?</h2>
<p>
CompUGE is an acronym for Comparative Understanding and Generation Evaluation, a platform designed to
facilitate research and development in the field of comparative question answering (CQA). The platform
provides access to benchmark datasets, evaluation metrics, leaderboards, and submission guidelines for
researchers and practitioners working on CQA systems. By offering a centralized hub for sharing resources
and comparing performance across different models, CompUGE aims to advance the state of the art in CQA and
foster collaboration within the research community.
</p>
</section>
<p>
Here's an example of a comparative question being processes by the
<a href="https://cam-v2.ltdemos.informatik.uni-hamburg.de">CAM 2.0 System</a>
introduced in the paper
<a href="https://aclanthology.org/2024.lrec-main.238">"CAM 2.0: End-to-End Open Domain Comparative Question
Answering System"</a>
by our team which was presented at
<a href="https://lrec-coling-2024.org">LREC-Coling 2024</a>.
</p>
<div class="section-content">
<mat-expansion-panel>
<mat-expansion-panel-header>
<mat-panel-title>
<h2 style="text-align: center; margin-top: 15px">What is better: Harry Potter or Lord of the Rings?</h2>
</mat-panel-title>
</mat-expansion-panel-header>
<div class="image-grid">
<div class="image-grid-item image1">
<img src="assets/hp.jpg" alt="Image 1">
</div>
<div class="image-grid-item image2">
<img src="assets/cam_response1.jpg" alt="Image 2">
</div>
<div class="image-grid-item image3">
<img src="assets/cam_response2.jpg" alt="Image 3">
</div>
<div class="image-grid-item image4">
<img src="assets/lotr.jpg" alt="Image 4">
</div>
</div>
</mat-expansion-panel>
</div>
</section>
<div class="task-buttons">
<button
*ngFor="let task of (tasks | async)"
mat-raised-button color="primary"
routerLink="/tasks/{{ task.name }}"
>{{ task.name }}
</button>
</div>
<nav class="nav-buttons">
<button mat-button routerLink="/leaderboards">Leaderboards</button>
<button mat-button routerLink="/datasets">Datasets</button>
<button mat-button routerLink="/submissions">Submissions List</button>
</nav>
<button mat-raised-button routerLink="/submitting" color="accent" class="submit-button">Submit a Model</button>
</mat-card-content>
</mat-card>
</div>