Related papers: An Update to the Minho Quotation Resource
Quotation extraction aims to extract quotations from written text. There are three components in a quotation: source refers to the holder of the quotation, cue is the trigger word(s), and content is the main body. Existing solutions for…
Here a collection of 1169 abstracts, which corresponds to articles that the Journal of Marketing Research has published from 2005 to 2014, are analysed under a novel approach. We apply several statistical methods, such as Principal…
MMEAD, or MS MARCO Entity Annotations and Disambiguations, is a resource for entity links for the MS MARCO datasets. We specify a format to store and share links for both document and passage collections of MS MARCO. Following this…
We present NEWSROOM, a summarization dataset of 1.3 million articles and summaries written by authors and editors in newsrooms of 38 major news publications. Extracted from search and social media metadata between 1998 and 2017, these…
The One Billion Word Benchmark is a dataset derived from the WMT 2011 News Crawl, commonly used to measure language modeling ability in natural language processing. We train models solely on Common Crawl web scrapes partitioned by year, and…
Current citation practices observed in articles are very noisy, confusing, and not standardised, making identifying the cited works problematic for hu-mans and any reference extraction software. In this work, we want to investigate such…
As Large Language Models (LLMs) continue to evolve, more are being designed to handle long-context inputs. Despite this advancement, most of them still face challenges in accurately handling long-context tasks, often showing the "lost in…
Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model…
Large language models (LLMs) have demonstrated remarkable capabilities in text analysis tasks, yet their evaluation on complex, real-world applications remains challenging. We define a set of tasks, Multi-Insight Multi-Document Extraction…
The goal of this working paper is to summarize the main empirical evidences provided by the scientific community as regards the comparison between the two main citation based academic search engines: Google Scholar and Microsoft Academic…
Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…
Accurate parsing of citations is necessary for machine-readable scholarly infrastructure. But, despite sustained interest in this problem, existing evaluation techniques are often not generalizable, based on synthetic data, or not publicly…
This paper presents the formal release of MedMentions, a new manually annotated resource for the recognition of biomedical concepts. What distinguishes MedMentions from other annotated biomedical corpora is its size (over 4,000 abstracts…
This report describes the feature introduced by Google to provide standardized access to institutional affiliations within Google Scholar Citations. First, this new tool is described, pointing out its main characteristics and functioning.…
This paper describes a method for multi-document update summarization that relies on a double maximization criterion. A Maximal Marginal Relevance like criterion, modified and so called Smmr, is used to select sentences that are close to…
An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated…
Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination:…
Finding previously debunked narratives involves identifying claims that have already undergone fact-checking. The issue intensifies when similar false claims persist in multiple languages, despite the availability of debunks for several…
Group Relative Policy Optimization (GRPO) is widely used for training reasoning models, but updating all sampled completions in each group incurs substantial cost and can reinforce verbose reasoning trajectories. In this paper, we study…
Using three years of the Journal Citation Reports (2011, 2012, and 2013), indicators of transitions in 2012 (between 2011 and 2013) are studied using methodologies based on entropy statistics. Changes can be indicated at the level of…