Related papers: Uni-Retrieval: A Multi-Style Retrieval Framework f…
Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…
In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in…
Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and…
In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding,…
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference…
Scene text retrieval has made significant progress with the assistance of accurate text localization. However, existing approaches typically require costly bounding box annotations for training. Besides, they mostly adopt a customized…
Academic Search is a search task aimed to manage and retrieve scientific documents like journal articles and conference papers. Personalization in this context meets individual researchers' needs by leveraging, through user profiles, the…
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…
The paper introduces the UniMER dataset, marking the first study on Mathematical Expression Recognition (MER) targeting complex real-world scenarios. The UniMER dataset includes a large-scale training set, UniMER-1M, which offers…
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…
As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key…
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…
Multimodal retrieval methods have limitations in handling complex, compositional queries that require reasoning about the visual content of both the query and the retrieved entities. On the other hand, Large Multimodal Models (LMMs) can…
Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…
Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-level descriptions,…
Education materials for K-12 students often consist of multiple modalities, such as text and images, posing challenges for models to fully understand nuanced information in these materials. In this paper, we propose a unified language and…
Recently, there have been significant advances in neural methods for tackling knowledge-intensive tasks such as open domain question answering (QA). These advances are fueled by combining large pre-trained language models with learnable…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…