Related papers: Improving Numerical Reasoning Skills in the Modula…
The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional…
The goal of Question Answering over Knowledge Graphs (KGQA) is to find answers for natural language questions over a knowledge graph. Recent KGQA approaches adopt a neural machine translation (NMT) approach, where the natural language…
Recent advancements in Large Language Models (LLMs) have pushed the boundaries of natural language processing, especially in long-context understanding. However, the evaluation of these models' long-context abilities remains a challenge due…
The numerical reasoning in the financial domain -- performing quantitative analysis and summarizing the information from financial reports -- can greatly increase business efficiency and reduce costs of billions of dollars. Here, we propose…
Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering. One such architecture, the dynamic memory network (DMN), obtained high accuracy on a variety of…
Question answering (QA) system aims at retrieving precise information from a large collection of documents against a query. This paper describes the architecture of a Natural Language Question Answering (NLQA) system for a specific domain…
Visual Question Answering (VQA) is fundamentally compositional in nature, and many questions are simply answered by decomposing them into modular sub-problems. The recent proposed Neural Module Network (NMN) employ this strategy to question…
Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of interpretability limits their use in tasks that demand…
Large language models (LLMs) can solve an increasing number of complex reasoning tasks while making surprising mistakes in basic numerical understanding and processing (such as 9.11 > 9.9). The latter ability is essential for tackling…
While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects. First, we lack QA datasets covering…
Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…
Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground…
Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network…
Visual Question Answering (VQA) models have achieved significant success in recent times. Despite the success of VQA models, they are mostly black-box models providing no reasoning about the predicted answer, thus raising questions for…
Visual question answering (VQA) requires systems to perform concept-level reasoning by unifying unstructured (e.g., the context in question and answer; "QA context") and structured (e.g., knowledge graph for the QA context and scene;…
Question answering is an effective method for obtaining information from knowledge bases (KB). In this paper, we propose the Neural-Symbolic Complex Question Answering (NS-CQA) model, a data-efficient reinforcement learning framework for…
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge…
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural…
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios. Such capacity is not yet attained for machine learning systems. In this work, in the context of…
Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query…