Named Entity Recognition and Disambiguation (NERD) systems are foundational for information retrieval, question answering, event detection, and other natural language processing (NLP) applications. We introduce TweetNERD, a dataset of 340K+ Tweets across 2010-2021, for benchmarking NERD systems on Tweets. This is the largest and most temporally diverse open sourced dataset benchmark for NERD on Tweets and can be used to facilitate research in this area. We describe evaluation setup with TweetNERD for three NERD tasks: Named Entity Recognition (NER), Entity Linking with True Spans (EL), and End to End Entity Linking (End2End); and provide performance of existing publicly available methods on specific TweetNERD splits.

Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead.

Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations. We introduce the Factorio Learning Environment (FLE), based on the game of Factorio, that tests agents in long-term planning, program synthesis, and resource optimization. FLE provides exponentially scaling challenges -- from basic automation to complex factories processing millions of resource units per second. We provide two settings: (1) lab-play consisting of eight structured tasks with fixed resources, and (2) open-play with the unbounded task of building the largest factory on an procedurally generated map. We demonstrate across both settings that models still lack strong spatial reasoning. In lab-play, we find that LLMs exhibit promising short-horizon skills, yet are unable to operate effectively in constrained environments, reflecting limitations in error analysis. In open-play, while LLMs discover automation strategies that improve growth (e.g electric-powered drilling), they fail to achieve complex automation (e.g electronic-circuit manufacturing).

Trivia is any fact about an entity which is interesting due to its unusualness, uniqueness, unexpectedness or weirdness. In this paper, we propose a novel approach for mining entity trivia from their Wikipedia pages. Given an entity, our system extracts relevant sentences from its Wikipedia page and produces a list of sentences ranked based on their interestingness as trivia. At the heart of our system lies an interestingness ranker which learns the notion of interestingness, through a rich set of domain-independent linguistic and entity based features. Our ranking model is trained by leveraging existing user-generated trivia data available on the Web instead of creating new labeled data. We evaluated our system on movies domain and observed that the system performs significantly better than the defined baselines. A thorough qualitative analysis of the results revealed that our rich set of features indeed help in surfacing interesting trivia in the top ranks.

Speech acts provide good insights into the communicative behavior of tweeters on Twitter. This paper is mainly concerned with speech act recognition in Twitter as a multi-class classification problem, for which we propose a set of word-based and character-based features. Inexpensive, robust and efficient, our method achieves an average F1 score of nearly 0.7 with the existence of much noise in our annotated Twitter data. In view of the deficiency of training data for the task, we experimented extensively with different configurations of training and test data, leading to empirical findings that may provide valuable reference for building benchmark datasets for sustained research on speech act recognition in Twitter.

Entity linking maps name mentions in the documents to entries in a knowledge base through resolving the name variations and ambiguities. In this paper, we propose three advancements for entity linking. Firstly, expanding acronyms can effectively reduce the ambiguity of the acronym mentions. However, only rule-based approaches relying heavily on the presence of text markers have been used for entity linking. In this paper, we propose a supervised learning algorithm to expand more complicated acronyms encountered, which leads to 15.1% accuracy improvement over state-of-the-art acronym expansion methods. Secondly, as entity linking annotation is expensive and labor intensive, to automate the annotation process without compromise of accuracy, we propose an instance selection strategy to effectively utilize the automatically generated annotation. In our selection strategy, an informative and diverse set of instances are selected for effective disambiguation. Lastly, topic modeling is used to model the semantic topics of the articles. These advancements give statistical significant improvement to entity linking individually. Collectively they lead the highest performance on KBP-2010 task.

Discriminatively trained undirected graphical models have had wide empirical success, and there has been increasing interest in toolkits that ease their application to complex relational data. The power in relational models is in their repeated structure and tied parameters; at issue is how to define these structures in a powerful and flexible way. Rather than using a declarative language, such as SQL or first-order logic, we advocate using an imperative language to express various aspects of model structure, inference, and learning. By combining the traditional, declarative, statistical semantics of factor graphs with imperative definitions of their construction and operation, we allow the user to mix declarative and procedural domain knowledge, and also gain significant efficiencies. We have implemented such imperatively defined factor graphs in a system we call Factorie, a software library for an object-oriented, strongly-typed, functional language. In experimental comparisons to Markov Logic Networks on joint segmentation and coreference, we find our approach to be 3-15 times faster while reducing error by 20-25%-achieving a new state of the art.

Over two decades ago a "quite revolution" overwhelmingly replaced knowledgebased approaches in natural language processing (NLP) by quantitative (e.g., statistical, corpus-based, machine learning) methods. Although it is our firm belief that purely quantitative approaches cannot be the only paradigm for NLP, dissatisfaction with purely engineering approaches to the construction of large knowledge bases for NLP are somewhat justified. In this paper we hope to demonstrate that both trends are partly misguided and that the time has come to enrich logical semantics with an ontological structure that reflects our commonsense view of the world and the way we talk about in ordinary language. In this paper it will be demonstrated that assuming such an ontological structure a number of challenges in the semantics of natural language (e.g., metonymy, intensionality, copredication, nominal compounds, etc.) can be properly and uniformly addressed.