Related papers: Learning Contextualized Document Representations f…
Cross-document co-reference resolution (CDCR) is the task of identifying and linking mentions to entities and concepts across many text documents. Current state-of-the-art models for this task assume that all documents are of the same type…
Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…
Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…
The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a…
Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to…
We propose a representation learning framework for medical diagnosis domain. It is based on heterogeneous network-based model of diagnostic data as well as modified metapath2vec algorithm for learning latent node representation. We compare…
Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively…
Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise…
Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually…
Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…
Dense retrieval is widely used for entity linking to retrieve entities from large-scale knowledge bases. Mainstream techniques are based on a dual-encoder framework, which encodes mentions and entities independently and calculates their…
Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be…
Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the context-dependent queries. Previous studies achieve conversational…
Diagnostic Captioning (DC) automatically generates a diagnostic text from one or more medical images (e.g., X-rays, MRIs) of a patient. Treated as a draft, the generated text may assist clinicians, by providing an initial estimation of the…
Electronic health records (EHRs) are long, noisy, and often redundant, posing a major challenge for the clinicians who must navigate them. Large language models (LLMs) offer a promising solution for extracting and reasoning over this…
Visual question answering (VQA) in medical imaging aims to support clinical diagnosis by automatically interpreting complex imaging data in response to natural language queries. Existing studies typically rely on distinct visual and textual…
Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into…
Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance. This paper first studies the…
Latent topic models have been successfully applied as an unsupervised topic discovery technique in large document collections. With the proliferation of hypertext document collection such as the Internet, there has also been great interest…