Related papers: Pre-training for Ad-hoc Retrieval: Hyperlink is Al…

Recent years have witnessed great progress on applying pre-trained language models, e.g., BERT, to information retrieval (IR) tasks. Hyperlinks, which are commonly used in Web pages, have been leveraged for designing pre-training…

Pretrained language models have improved effectiveness on numerous tasks, including ad-hoc retrieval. Recent work has shown that continuing to pretrain a language model with auxiliary objectives before fine-tuning on the retrieval task can…

Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR). However, pre-training objectives tailored for ad-hoc retrieval have not been…

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the…

Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces…

Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm…

Deep neural networks have been successfully applied to many text matching tasks, such as paraphrase identification, question answering, and machine translation. Although ad-hoc retrieval can also be formalized as a text matching task, few…

In this work, we present an unsupervised retrieval method with contrastive learning on web anchors. The anchor text describes the content that is referenced from the linked page. This shows similarities to search queries that aim to…

We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two…

Pre-trained language models have achieved great success in various large-scale information retrieval tasks. However, most of pretraining tasks are based on counterfeit retrieval data where the query produced by the tailored rule is assumed…

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications. However, pretraining usually leverages predefined task sequences to learn general linguistic clues. The lack of…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is…

To retrieve more relevant, appropriate and useful documents given a query, finding clues about that query through the text is crucial. Recent deep learning models regard the task as a term-level matching problem, which seeks exact or…

Quality pretraining data is often seen as the key to high-performance language models. However, progress in understanding pretraining data has been slow due to the costly pretraining runs required for data selection experiments. We present…

The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On the other hand, Machine Translation Systems are mostly…

We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs. Through a comprehensive study along three axes of the pretraining pipeline -- model architecture, optimization objective, and…

Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information retrieval, where additional pre-training has so far failed to…