相关论文: Learning to Retrieve Passages without Supervision

Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains…

Large language models (LLMs) enable zero-shot approaches in open-domain question answering (ODQA), yet with limited advancements as the reader is compared to the retriever. This study aims at the feasibility of a zero-shot reader that…

In several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where only a few hundred…

For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised…

Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned…

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

Popular QA benchmarks like SQuAD have driven progress on the task of identifying answer spans within a specific passage, with models now surpassing human performance. However, retrieving relevant answers from a huge corpus of documents is…

Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not…

In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned…

The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised…

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…

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and…

Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose…

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…

Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner. However, data annotation cannot also be irresistible for its huge demand in an open domain. Though unsupervised QA or…

Learned sparse retrieval, which can efficiently perform retrieval through mature inverted-index engines, has garnered growing attention in recent years. Particularly, the inference-free sparse retrievers are attractive as they eliminate…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…

Unsupervised domain adaptation aims to leverage labeled data from a source domain to learn a classifier for an unlabeled target domain. Among its many variants, open set domain adaptation (OSDA) is perhaps the most challenging, as it…