Related papers: Hierarchical corpus encoder: Fusing generative ret…
Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by…
This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed retrieval even in simple cases. To examine such behaviors,…
Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…
Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is…
Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…
There are settings in which reproducibility of ranked lists is desirable, such as when extracting a subset of an evolving document corpus for downstream research tasks or in domains such as patent retrieval or in medical systematic reviews,…
The success of contextual word representations and advances in neural information retrieval have made dense vector-based retrieval a standard approach for passage and document ranking. While effective and efficient, dual-encoders are…
Document-level RE requires reading, inferring and aggregating over multiple sentences. From our point of view, it is necessary for document-level RE to take advantage of multi-granularity inference information: entity level, sentence level…
As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original…
Translating renderings (e. g. PDFs, scans) into hierarchical document structures is extensively demanded in the daily routines of many real-world applications. However, a holistic, principled approach to inferring the complete hierarchical…
Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and…
Getting a robust time-series clustering with best choice of distance measure and appropriate representation is always a challenge. We propose a novel mechanism to identify the clusters combining learned compact representation of…
Zero-shot dense retrieval is a challenging setting where a document corpus is provided without relevant queries, necessitating a reliance on pretrained dense retrievers (DRs). However, since these DRs are not trained on the target corpus,…
Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target. At a cost, the identifier must be distinctive enough to represent a passage. Current…
In open-domain question answering, a model receives a text question as input and searches for the correct answer using a large evidence corpus. The retrieval step is especially difficult as typical evidence corpora have \textit{millions} of…
The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods typically treat LCR as a black-box semantic matching process,…
Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern…
Differentiable Search Indices (DSIs) encode a corpus of documents in model parameters and use the same model to answer user queries directly. Despite the strong performance of DSI models, deploying them in situations where the corpus…
Document retrieval is one of the best established information retrieval activities since the sixties, pervading all search engines. Its aim is to obtain, from a collection of text documents, those most relevant to a pattern query. Current…
This paper introduces and analyzes a search and retrieval model that adopts key semantic communication principles from retrieval-augmented generation. We specifically present an information-theoretic analysis of a remote document retrieval…