Related papers: Single-Pass Document Scanning for Question Answeri…
Principal component analysis (PCA) is a fundamental dimension reduction tool in statistics and machine learning. For large and high-dimensional data, computing the PCA (i.e., the singular vectors corresponding to a number of dominant…
Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems…
Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically adopt token pruning…
Handling large corpuses of documents is of significant importance in many fields, no more so than in the areas of crime investigation and defence, where an organisation may be presented with a large volume of scanned documents which need to…
In the real world, documents are organized in different formats and varied modalities. Traditional retrieval pipelines require tailored document parsing techniques and content extraction modules to prepare input for indexing. This process…
The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…
Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…
Joint vision and language tasks like visual question answering are fascinating because they explore high-level understanding, but at the same time, can be more prone to language biases. In this paper, we explore the biases in the MovieQA…
This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark for multi-document analytical QA, where questions require extracting and synthesizing…
Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…
Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks…
Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained…
Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a…
Modern day applications, especially information retrieval webapps that involve "search" as their use cases are gradually moving towards "answering" modules. Conversational chatbots which have been proved to be more engaging to users, use…
Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents.…
Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pretraining exclusively…
We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of…
Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly…
We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. In our study, 36 segmentation methods spanning…
We present 1-Pager the first system that answers a question and retrieves evidence using a single Transformer-based model and decoding process. 1-Pager incrementally partitions the retrieval corpus using constrained decoding to select a…