اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDeep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning
143
0
0.0
(
0
)
تأليف
Kwwabena Nuamah
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
An important aspect of artificial intelligence (AI) is the ability to reason in a step-by-step algorithmic manner that can be inspected and verified for its correctness. This is especially important in the domain of question answering (QA). We argue that the challenge of algorithmic reasoning in QA can be effectively tackled with a systems approach to AI which features a hybrid use of symbolic and sub-symbolic methods including deep neural networks. Additionally, we argue that while neural network models with end-to-end training pipelines perform well in narrow applications such as image classification and language modelling, they cannot, on their own, successfully perform algorithmic reasoning, especially if the task spans multiple domains. We discuss a few notable exceptions and point out how they are still limited when the QA problem is widened to include other intelligence-requiring tasks. However, deep learning, and machine learning in general, do play important roles as components in the reasoning process. We propose an approach to algorithm reasoning for QA, Deep Algorithmic Question Answering (DAQA), based on three desirable properties: interpretability, generalizability and robustness which such an AI system should possess and conclude that they are best achieved with a combination of hybrid and compositional AI.
قيم البحث
اقرأ أيضاً
Automatic math problem solving has recently attracted increasing attention as a long-standing AI benchmark. In this paper, we focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams,
and theorem knowledge. However, the existing methods were highly dependent on handcraft rules and were merely evaluated on small-scale datasets. Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 5,010 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems. Compared with another publicly available dataset GeoS, GeoQA is 25 times larger, in which the program annotations can provide a practical testbed for future research on explicit and explainable numerical reasoning. Moreover, we introduce a Neural Geometric Solver (NGS) to address geometric problems by comprehensively parsing multimodal information and generating interpretable programs. We further add multiple self-supervised auxiliary tasks on NGS to enhance cross-modal semantic representation. Extensive experiments on GeoQA validate the effectiveness of our proposed NGS and auxiliary tasks. However, the results are still significantly lower than human performance, which leaves large room for future research. Our benchmark and code are released at https://github.com/chen-judge/GeoQA .
In the question answering(QA) task, multi-hop reasoning framework has been extensively studied in recent years to perform more efficient and interpretable answer reasoning on the Knowledge Graph(KG). However, multi-hop reasoning is inapplicable for a
nswering n-ary fact questions due to its linear reasoning nature. We discover that there are two feasible improvements: 1) upgrade the basic reasoning unit from entity or relation to fact; and 2) upgrade the reasoning structure from chain to tree. Based on these, we propose a novel fact-tree reasoning framework, through transforming the question into a fact tree and performing iterative fact reasoning on it to predict the correct answer. Through a comprehensive evaluation on the n-ary fact KGQA dataset introduced by this work, we demonstrate that the proposed fact-tree reasoning framework has the desired advantage of high answer prediction accuracy. In addition, we also evaluate the fact-tree reasoning framework on two binary KGQA datasets and show that our approach also has a strong reasoning ability compared with several excellent baselines. This work has direct implications for exploring complex reasoning scenarios and provides a preliminary baseline approach.
The Dependent Object Types (DOT) calculus formalizes key features of Scala. The D$_{<: }$ calculus is the core of DOT. To date, presentations of D$_{<: }$ have used declarative typing and subtyping rules, as opposed to algorithmic. Unfortunately, alg
orithmic typing for full D$_{<: }$ is known to be an undecidable problem. We explore the design space for a restricted version of D$_{<: }$ that has decidable typechecking. Even in this simplified D$_{<: }$ , algorithmic typing and subtyping are tricky, due to the bad bounds problem. The Scala compiler bypasses bad bounds at the cost of a loss in expressiveness in its type system. Based on the approach taken in the Scala compiler, we present the Step Typing and Step Subtyping relations for D$_{<: }$. We prove these relations sound and decidable. They are not complete with respect to the original D$_{<: }$ rules.
Increasingly, scholars seek to integrate legal and technological insights to combat bias in AI systems. In recent years, many different definitions for ensuring non-discrimination in algorithmic decision systems have been put forward. In this paper,
we first briefly describe the EU law framework covering cases of algorithmic discrimination. Second, we present an algorithm that harnesses optimal transport to provide a flexible framework to interpolate between different fairness definitions. Third, we show that important normative and legal challenges remain for the implementation of algorithmic fairness interventions in real-world scenarios. Overall, the paper seeks to contribute to the quest for flexible technical frameworks that can be adapted to varying legal and normative fairness constraints.
Deep neural networks have shown striking progress and obtained state-of-the-art results in many AI research fields in the recent years. However, it is often unsatisfying to not know why they predict what they do. In this paper, we address the problem
of interpreting Visual Question Answering (VQA) models. Specifically, we are interested in finding what part of the input (pixels in images or words in questions) the VQA model focuses on while answering the question. To tackle this problem, we use two visualization techniques -- guided backpropagation and occlusion -- to find important words in the question and important regions in the image. We then present qualitative and quantitative analyses of these importance maps. We found that even without explicit attention mechanisms, VQA models may sometimes be implicitly attending to relevant regions in the image, and often to appropriate words in the question.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
