Related papers: Table Retrieval May Not Necessitate Table-specific…

Tabular representation learning has recently gained a lot of attention. However, existing approaches only learn a representation from a single table, and thus ignore the potential to learn from the full structure of relational databases,…

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision…

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…

The first phase of table recognition is to detect the tabular area in a document. Subsequently, the tabular structures are recognized in the second phase in order to extract information from the respective cells. Table detection and…

Diffusion models have demonstrated significant potential in achieving state-of-the-art performance across various text generation tasks. In this systematic study, we investigate their application to the table-to-text problem by adapting the…

Dense retrieval is a crucial task in Information Retrieval (IR), serving as the basis for downstream tasks such as re-ranking and augmenting generation. Recently, large language models (LLMs) have demonstrated impressive semantic…

Table Structure Recognition is an essential part of end-to-end tabular data extraction in document images. The recent success of deep learning model architectures in computer vision remains to be non-reflective in table structure…

Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells,…

Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the…

Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compromise retrieval quality. Query rewriting techniques are now…

Abstract--- Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging…

Tables are common and important in scientific documents, yet most text-based document search systems do not capture structures and semantics specific to tables. How to bridge different types of mismatch between keywords queries and…

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…

We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval. Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial…

Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning…

Large Language Models (LLMs) often struggle with requests related to information retrieval and data manipulation that frequently arise in real-world scenarios under multiple conditions. In this paper, we demonstrate that leveraging tabular…

Sorted Table Search Procedures are the quintessential query-answering tool, with widespread usage that now includes also Web Applications, e.g, Search Engines (Google Chrome) and ad Bidding Systems (AppNexus). Speeding them up, at very…

With the ubiquitous use of document corpora for question answering, one important aspect which is especially relevant for technical documents is the ability to extract information from tables which are interspersed with text. The major…

Long-tail question answering presents significant challenges for large language models (LLMs) due to their limited ability to acquire and accurately recall less common knowledge. Retrieval-augmented generation (RAG) systems have shown great…

Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However, these models often suffer from distribution shifts, as…