Related papers: Hierarchical corpus encoder: Fusing generative ret…

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between generative retrieval and other retrieval methods, especially those…

We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings;…

Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is this document retrieved?''. To address this limitation, we…

Generative retrieval seeks to replace traditional search index data structures with a single large-scale neural network, offering the potential for improved efficiency and seamless integration with generative large language models. As an…

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy.…

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence…

Generative retrieval (GR) directly predicts the identifiers of relevant documents (i.e., docids) based on a parametric model. It has achieved solid performance on many ad-hoc retrieval tasks. So far, these tasks have assumed a static…

Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However,…

Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Current state-of-the-art document retrieval solutions mainly follow an index-retrieve paradigm, where the index is hard to be directly optimized for the final retrieval target. In this paper, we aim to show that an end-to-end deep neural…

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image…

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for…

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embedding Fusion (HEF), a…