Related papers: Optimized Table Tokenization for Table Structure R…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on…

One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i.e., tables and columns) and…

Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume the table structure keeps fixed in training and testing. Before ML modeling, heavy data cleaning is required to merge…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell at the same time. However, the existing methods are…

In deep neural networks, better results can often be obtained by increasing the complexity of previously developed basic models. However, it is unclear whether there is a way to boost performance by decreasing the complexity of such models.…

The task of condensing large chunks of textual information into concise and structured tables has gained attention recently due to the emergence of Large Language Models (LLMs) and their potential benefit for downstream tasks, such as text…

We study LLMs for tabular prediction with mixed text, numeric, and categorical fields. We introduce TabGemma, a schema-agnostic in-context learner that treats rows as sequences and tackles two practical hurdles when adapting pretrained LLMs…

Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text…

There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities. In this scenario,…

We present a new table structure recognition (TSR) approach, called TSRFormer, to robustly recognizing the structures of complex tables with geometrical distortions from various table images. Unlike previous methods, we formulate table…

Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of…

Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipelines. While semi-supervised learning (SSL) can leverage…

We present the design of a structured search engine which returns a multi-column table in response to a query consisting of keywords describing each of its columns. We answer such queries by exploiting the millions of tables on the Web…

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Dataset discovery from data lakes is essential in many real application scenarios. In this paper, we propose Starmie, an end-to-end framework for dataset discovery from data lakes (with table union search as the main use case). Our proposed…

Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and…