Fiction and fantasy are archetypes of long-tail domains that lack comprehensive methods for automated language processing and knowledge extraction. We present ENTYFI, the first methodology for typing entities in fictional texts coming from books, fan ...

A lightweight method applies a few extraction patterns to the task of distinguishing Wikipedia articles that are classes ("Walled garden", "Garden") from other articles ("High Hazels Park"). The method acquires a set of classes, based on patterns ...

AI2's Project Aristo seeks to build a system that has a deep understanding of science, using knowledge captured mainly from large-scale text. Recently, Aristo achieved surprising success on the Grade 8 New York Regents Science Exams, scoring over 90% on ...

We investigate exploration as an alternative to explanation to improve user understanding of algorithms and algorithmic decision-making. Drawing on complex problem-solving as defined in cognitive science, we conducted a think-aloud study in the lab (N=...

Ontologies provide a means to store knowledge in a machine-readable format. Ontology population is the task of updating an ontology with new facts from an input knowledge resource. These facts are represented in a structured format and integrated ...

The authors have been coping with new computational methodologies such as rough sets, information incompleteness, data mining, granular computing, etc., and developed some software tools on association rules as well as new mathematical frameworks. They ...

Recent captioning models are limited in their ability to describe concepts unseen in paired image–sentence pairs. This study presents a framework of multi‐task learning for describing novel words not present in existing image‐captioning datasets. The ...

A supervised method relies on simple, lightweight features in order to distinguish Wikipedia articles that are classes (Shield volcano) from other articles (Kilauea). The features are lexical or semantic in nature. Experimental results in multiple ...

The operation of a modern city is inseparable from the underground pipelines, and mapping the buried pipelines has long been addressed as an issue. In this paper, a novel model is proposed to map the underground pipelines by taking GPR and GPS data as ...

This study is aimed to validate a text processing architecture for knowledge acquisition and analyze the performance of several populations under controlled validation studies by focusing on empirical methods. We report our experience by analyzing three ...

In recent years, there have been extensive studies and rapid progresses in text similarity computing that is one of the host and important techniques in many NLP applications. This paper first introduces the background, the basic computing process, the ...

Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors. In this paper, we study 20 Questions, an online interactive game ...

A lightweight method distinguishes articles within Wikipedia that are classes (Novel, Book) from other articles (Three Men in a Boat, Diary of a Pilgrimage). It exploits clues available within the article text and within categories associated with ...

We propose a new method for inducing a phrase-based translation model from a pair of unrelated monolingual corpora. Our method is able to deal with phrases of arbitrary length and to find phrase pairs that are useful for statistical machine translation, ...

Techniques for generating and recognizing paraphrases, i.e., semantically equivalent expressions, play an important role in a wide range of natural language processing tasks. In the last decade, the task of automatic acquisition of subsentential ...

Towards the goal of enhancing interpretability of Latent Dirichlet Allocation (LDA) topics, we propose WikiLDA, an enhancement to LDA using Wikipedia concepts. In WikiLDA, initially, for each document in a corpus we "sprinkle" (append) its most relevant ...

We propose a novel, semi-supervised approach towards domain taxonomy induction from an input vocabulary of seed terms. Unlike all previous approaches, which typically extract direct hypernym edges for terms, our approach utilizes a novel probabilistic ...

Knowledge acquisition (e.g. through labeling) is one of the most successful applications in crowdsourcing. In practice, collecting as specific as possible knowledge via crowdsourcing is very useful since specific knowledge can be generalized easily if we ...

It is a hot research topic today to find out the potential knowledge from the scattered urban data and take advantage of the relationship between the knowledge to solve the challenges of urban governance and smart city construction. The urban knowledge ...

This paper addresses the challenge of determining the identity of mathematical expressions in documents by linking these expressions to their corresponding Wikipedia articles. Math expressions are frequently used to describe important concepts in ...