Related papers: Learning Contextualized Document Representations f…
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc…
Coreference resolution across multiple documents poses a significant challenge in natural language processing, particularly within the domain of knowledge graphs. This study introduces an innovative method aimed at identifying and resolving…
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or…
We study retrieving a set of documents that covers various perspectives on a complex and contentious question (e.g., will ChatGPT do more harm than good?). We curate a Benchmark for Retrieval Diversity for Subjective questions (BERDS),…
A system is described that uses a mixed-level representation of (part of) meaning of natural language documents (based on standard Horn Clause Logic) and a variable-depth search strategy that distinguishes between the different levels of…
Distributed representations of words learned from text have proved to be successful in various natural language processing tasks in recent times. While some methods represent words as vectors computed from text using predictive model…
Learning to represent free text is a core task in many clinical machine learning (ML) applications, as clinical text contains observations and plans not otherwise available for inference. State-of-the-art methods use large language models…
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…
The burgeoning integration of 3D medical imaging into healthcare has led to a substantial increase in the workload of medical professionals. To assist clinicians in their diagnostic processes and alleviate their workload, the development of…
Large Language Models are increasingly being used for various tasks including content generation and as chatbots. Despite their impressive performances in general tasks, LLMs need to be aligned when applying for domain specific tasks to…
In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to…
Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large…
In this dissertation we report results of our research on dense distributed representations of text data. We propose two novel neural models for learning such representations. The first model learns representations at the document level,…
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities. The visual cues offered by their complex layouts play a…
The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN)…
Due to globalization, geographic boundaries no longer serve as effective shields for the spread of infectious diseases. In order to aid bio-surveillance analysts in disease tracking, recent research has been devoted to developing…
We propose a document retrieval method for question answering that represents documents and questions as weighted centroids of word embeddings and reranks the retrieved documents with a relaxation of Word Mover's Distance. Using biomedical…
Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ…
Although transformer-based models have shown strong performance in word- and sentence-level tasks, effectively representing long documents, especially in fields like law and medicine, remains difficult. Sparse attention mechanisms can…
Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggregation process and suppressing the discriminative features in…