Related papers: DESIRE-ME: Domain-Enhanced Supervised Information …
In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains. Such solutions are sub-optimal as…
The combination and aggregation of knowledge from multiple neural networks can be commonly seen in the form of mixtures of experts. However, such combinations are usually done using networks trained on the same tasks, with little mention of…
Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization…
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In…
Open-domain question answering aims at solving the task of locating the answers to user-generated questions in massive collections of documents. There are two families of solutions available: retriever-readers, and knowledge-graph-based…
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…
Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We…
A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even…
Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data…
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research…
Mixture of Experts (MoE) models constitute a widely utilized class of ensemble learning approaches in statistics and machine learning, known for their flexibility and computational efficiency. They have become integral components in…
While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be…
We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…
Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical…
Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP)…
State-of-the-art systems in deep question answering proceed as follows: (1) an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer. Yet the exact…
Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods…
Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs have been successfully applied to image classification and…