Related papers: Passage-Mask: A Learnable Regularization Strategy …
Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network…
We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…
In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering. We explore four negative sampling strategies that complement the straightforward random sampling of…
According to common relevance-judgments regimes, such as TREC's, a document can be deemed relevant to a query even if it contains a very short passage of text with pertinent information. This fact has motivated work on passage-based…
Training of deep reinforcement learning agents is slowed considerably by the presence of input dimensions that do not usefully condition the reward function. Existing modules such as layer normalization can be trained with weight decay to…
Retrieval-augmented generation (RAG) has been widely adopted to augment large language models (LLMs) with external knowledge for knowledge-intensive tasks. However, its effectiveness is often undermined by the presence of noisy (i.e.,…
Retrieval-Augmented Language Models (RALMs) represent a classic paradigm where models enhance generative capabilities using external knowledge retrieved via a specialized module. Recent advancements in Agent techniques enable Large Language…
Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised approaches. However, it remains unclear how unsupervised and supervised methods can be used most effectively…
In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage…
With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on…
Many modern high-performing machine learning models such as GPT-3 primarily rely on scaling up models, e.g., transformer networks. Simultaneously, a parallel line of work aims to improve the model performance by augmenting an input instance…
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query…
Reinforcement Learning-based Recommender Systems (RLRS) have shown promise across a spectrum of applications, from e-commerce platforms to streaming services. Yet, they grapple with challenges, notably in crafting reward functions and…
Reading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge. Just as the process of knowledge accumulation is time-consuming for human readers, it is resource-demanding to…
Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…
Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…
In representation learning (RL), how to make the learned representations easy to interpret and less overfitted to training data are two important but challenging issues. To address these problems, we study a new type of regulariza- tion…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external documents at inference time, enabling up-to-date knowledge access without costly retraining. However, conventional RAG methods retrieve…
With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods based on DNA sequences have received increasing attention…
Generative retrieval stands out as a promising new paradigm in text retrieval that aims to generate identifier strings of relevant passages as the retrieval target. This generative paradigm taps into powerful generative language models,…