Related papers: Tailoring Table Retrieval from a Field-aware Hybri…
Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal…
Unionable table search techniques input a query table from a user and search for data lake tables that can contribute additional rows to the query table. The definition of unionability is generally based on similarity measures which may…
This paper introduces a novel method for closed information extraction. The method employs a discriminative approach that incorporates type and entity-specific information to improve relation extraction accuracy, particularly benefiting…
Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking. The retrieval step, also known as candidate selection, often involves extracting standardized entities, creating an…
Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically…
Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with…
As the last stage of recommender systems, re-ranking generates a re-ordered list that aligns with the user's preference. However, previous works generally focus on item-level positive feedback as history (e.g., only clicked items) and…
Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse…
Retrieving and extracting knowledge from extensive research documents and large databases presents significant challenges for researchers, students, and professionals in today's information-rich era. Existing retrieval systems, which rely…
This paper describes a new type of spreadsheet which mitigates the errors caused by incorrect range referencing in formulae. This spreadsheet is composed of structured worksheets called tables which contain a hierarchical organization of…
Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…
Enabling question answering over tables and databases in natural language has become a key capability in the democratization of insights from tabular data sources. These systems first require retrieval of data that is relevant to a given…
One of the major challenges in enterprise data analysis is the task of finding joinable tables that are conceptually related and provide meaningful insights. Traditionally, joinable tables have been discovered through a search for similar…
Tabular data constitute a dominant form of information in modern data lakes and repositories, yet discovering the relevant tables to answer user questions remains challenging. Existing data discovery systems assume that each question can be…
With the rapid advancement of Large Language Models (LLMs), there is an increasing need for challenging benchmarks to evaluate their capabilities in handling complex tabular data. However, existing benchmarks are either based on outdated…
In this report, we unify two quite distinct approaches to information retrieval: region models and language models. Region models were developed for structured document retrieval. They provide a well-defined behaviour as well as a simple…
Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little about the model's…
Open-domain table question answering aims to provide answers to a question by retrieving and extracting information from a large collection of tables. Existing studies of open-domain table QA either directly adopt text retrieval methods or…
Data tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how…
Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table…