paper-with-me

홈 › Papers

A Comparative Evaluation of Visual and Natural Language Question Answering Over Linked Data

2019-07-19 · Gerhard Wohlgenannt, Dmitry Mouromtsev, Dmitry Pavlov, Yury Emelyanov, Alexey Morozov

With the growing number and size of Linked Data datasets, it is crucial to make the data accessible and useful for users without knowledge of formal query languages. Two approaches towards this goal are knowledge graph visualization and natural language interfaces. Here, we investigate specifically question answering (QA) over Linked Data by comparing a diagrammatic visual approach with existing natural language-based systems. Given a QA benchmark (QALD7), we evaluate a visual method which is based on iteratively creating diagrams until the answer is found, against four QA systems that have natural language queries as input. Besides other benefits, the visual approach provides higher performance, but also requires more manual input. The results indicate that the methods can be used complementary, and that such a combination has a large positive impact on QA performance, and also facilitates additional features such as data exploration.

📄 PDF Abstract BibTeX arXiv:1907.08501

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language QueriesQuestion Answering

Similar Papers 제목 키워드 기반

Exploring Advanced Techniques for Visual Question Answering: A Comprehensive Comparison

2025-02-20 · Aiswarya Baby, Tintu Thankom Koshy

Visual Question Answering (VQA) has emerged as a pivotal task in the intersection of computer vision and natural language processing, requiring models to understand and reason about visual content in response to natural …

DiversityLanguage ModelingLanguage ModellingMultimodal Reasoning+3

Which is Better for Deep Learning: Python or MATLAB? Answering Comparative Questions in Natural Language

2021-04-01 · EACL 2021 2 · Viktoriia Chekalina, Alexander Bondarenko, Chris Biemann, Meriem Beloucif 외

We present a system for answering comparative questions (Is X better than Y with respect to Z?) in natural language. Answering such questions is important for assisting humans in making informed decisions. The key compon…

Visual question answering: from early developments to recent advances -- a survey

2025-01-07 · Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Sunil Aryal, Imran Razzak 외

Visual Question Answering (VQA) is an evolving research field aimed at enabling machines to answer questions about visual content by integrating image and language processing techniques such as feature extraction, object…

DescriptiveNatural Language Understandingobject-detectionObject Detection+5

LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models

2023-04-02 · Patrik Puchert, Poonam Poonam, Christian van Onzenoodt, Timo Ropinski

Large Language Models (LLMs) have revolutionized natural language processing and demonstrated impressive capabilities in various tasks. Unfortunately, they are prone to hallucinations, where the model exposes incorrect o…

Argument-Based Comparative Question Answering Evaluation Benchmark

2025-02-20 · Irina Nikishina, Saba Anwar, Nikolay Dolgov, Maria Manina 외

In this paper, we aim to solve the problems standing in the way of automatic comparative question answering. To this end, we propose an evaluation framework to assess the quality of comparative question answering summari…

Question Answering