+ This System was built in the process of the research conducted by the Author Ahmad Shallouf for his Master Thesis
+ at the University of Hamburg.
+
+ The purpose of this system is to provide a Benchmark for the 4 main tasks of Comparative Question Answering in the
+ English Language.
+
+ The system is built using the Angular Framework for the Frontend and FastAPI Framework for the Backend with a
+ PostgreSQL Database.
+
| Name: | +Ahmad Shallouf | +
| Position: | +Master Student | +
| Email: | +{{ '7shallou@informatik.uni-hamburg.de' }} | +
| Phone: | ++49 1762405080 | +
+ The comparative question identification task involves detecting and classifying questions that aim to compare
+ entities, such as products or services. This task is important for applications like review summarization,
+ recommendation systems, and opinion mining. Researchers have developed methods involving natural language
+ processing techniques to accurately identify and categorize comparative questions from user-generated content.
+ These methods often require syntactic and semantic analysis to understand the nuances and patterns in language
+ that indicate comparisons.
+
+ Recent advancements in this field include the use of machine learning models and neural networks to improve
+ the accuracy of identifying comparative questions. These models are trained on large datasets to recognize
+ both explicit and implicit comparisons. Challenges in this area include handling context-dependent comparisons
+ and refining algorithms to better capture the intent behind complex linguistic structures. This work enhances
+ applications by providing deeper insights into user preferences and opinions through effective comparison
+ detection.
+
+
+ Object and Aspect Labeling is a sequence tagging task aimed at identifying entities such as objects, aspects, and predicates in comparative questions.
+
+ There are at least three different datasets for this task. The dataset by Li et al. focuses on extracting objects of comparison but is not publicly available. The other two datasets, by Beloucif et al. and Bondarenko et al., have different annotation schemas and tags. Another dataset by Chekalina et al. includes labeled affirmative sentences.
+
+
+ Stance classification is one of the crucial subtasks of the whole pipeline, as we select relevant arguments and detect, in favor of which object the choice is made thanks to the class assigned at this step.
+
+ There is a dataset published by Panchenko et al. along with the baseline classifier, which is outperformed by Ma et al. Bondarenko et al. also introduces datasets and tests them on several models. However, their text excerpts are quite large and are not consistent with the argumentative sentences for our task.
+
+
+ Comparative Summary Generation is a relatively recent and less widespread task.
+
+ To the best of our knowledge, only two papers introduce datasets and baseline approaches. Chekalina et al. (2021) presents comparative questions with their best answers from Yahoo! Answers and tests several unsupervised approaches, including CTRL and template-based answers. Yu et al. (2023) pre-trains LLMs for comparative reasoning using prompts and introduces a dataset called “Diffen” that works with summarizing arguments for an object pair, though it is not publicly available.
+
+ 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.
++ 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. +
++ Here's an example of a comparative question being processes by the + CAM 2.0 System + introduced in the paper + "CAM 2.0: End-to-End Open Domain Comparative Question + Answering System" + by our team and accepted at + LREC-Coling 2024. +
+
+ 
+ 
+ 
+ dashboard works!
diff --git a/src/app/components/body/dashboard/dashboard.component.spec.ts b/src/app/components/body/dashboard/dashboard.component.spec.ts new file mode 100644 index 0000000000000000000000000000000000000000..815d1b8e55f200d282a066423c50e5ab6ee70179 --- /dev/null +++ b/src/app/components/body/dashboard/dashboard.component.spec.ts @@ -0,0 +1,23 @@ +import { ComponentFixture, TestBed } from '@angular/core/testing'; + +import { DashboardComponent } from './dashboard.component'; + +describe('DashboardComponent', () => { + let component: DashboardComponent; + let fixture: ComponentFixture{{ datasetModel.description }}
++ This dataset was introduced in the following paper: + {{ datasetModel.paper }} +
+ + + + + + + + + + + +{{dataset.description}}
+