Related papers: ARQMath Lab: An Incubator for Semantic Formula Sea…
There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model…
Our work addresses the challenges of understanding tables. Existing methods often struggle with the unpredictable nature of table content, leading to a reliance on preprocessing and keyword matching. They also face limitations due to the…
Mathematical reasoning is a cornerstone of human intelligence and a key benchmark for advanced capabilities in large language models (LLMs). However, the research community still lacks an open, large-scale, high-quality corpus tailored to…
Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC…
The Web is our primary source of all kinds of information today. This includes information about software as well as associated materials, like source code, documentation, related publications and change logs. Such data is of particular…
We present an unsupervised approach for discovering semantic representations of mathematical equations. Equations are challenging to analyze because each is unique, or nearly unique. Our method, which we call equation embeddings, finds good…
Search agents, which integrate language models (LMs) with web search, are becoming crucial for answering complex user queries. Constructing training datasets for deep research tasks, involving multi-step retrieval and reasoning, remains…
As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of…
Understanding the connections between unstructured text and semi-structured table is an important yet neglected problem in natural language processing. In this work, we focus on content-based table retrieval. Given a query, the task is to…
The goal of entity matching is to find the corresponding records representing the same real-world entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain…
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…
We present ModelTables, a benchmark of tables in Model Lakes that captures the structured semantics of performance and configuration tables often overlooked by text only retrieval. The corpus is built from Hugging Face model cards, GitHub…
Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking. Conventional ranking-based KBQA models, which rely…
Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not natively present. Performing this analysis in a cost-efficient…
Formula retrieval is an important topic in Mathematical Information Retrieval. We propose SSEmb, a novel embedding framework capable of capturing both structural and semantic features of mathematical formulas. Structurally, we employ Graph…
Evaluating statement autoformalization, translating natural language mathematics into formal languages like Lean 4, remains a significant challenge, with few metrics, datasets, and standards to robustly measure progress. In this work, we…
Mathematical information retrieval (MathIR) applications such as semantic formula search and question answering systems rely on knowledge-bases that link mathematical expressions to their natural language names. For database population,…
The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task…
Mathematical information retrieval is a relatively new area, so the first search tools capable of retrieving mathematical formulas began to appear only a few years ago. The proposals made public so far mostly implement searches on internal…
Mathematical formulae represent complex semantic information in a concise form. Especially in Science, Technology, Engineering, and Mathematics, mathematical formulae are crucial to communicate information, e.g., in scientific papers, and…