Search

Combining different input modalities beyond text is a key challenge for natural language processing. Previous work has been inconclusive as to the true utility of images as a supplementary information source for text classification tasks, motivating this large-scale human study of labelling performance given text-only, images-only, or both text and images. To this end, we create a new dataset accompanied with a novel annotation method—Japanese Entity Labeling with Dynamic Annotation—to deepen our understanding of the effectiveness of images for multi-modal text classification. By performing careful comparative analysis of human performance and the performance of state-of-the-art multi-modal text classification models, we gain valuable insights into differences between human and model performance, and the conditions under which images are beneficial for text classification.

Conversing about places with a computer poses a range of challenges to current AI.

In this article, we investigate word sense distributions in noun compounds (NCs). Our primary goal is to disambiguate the word sense of component words in NCs, based on investigation of “semantic collocation” between them. We use sense collocation and lexical substitution to build supervised and unsupervised word sense disambiguation (WSD) classifiers, and show our unsupervised learner to be superior to a benchmark WSD system. Further, we develop a word sense-based approach to interpreting the semantic relations in NCs.

We investigate the impact of preextracting and tokenizing bigram collocations on topic models. Using extensive experiments on four different corpora, we show that incorporating bigram collocations in the document representation creates more parsimonious models and improves topic coherence. We point out some problems in interpreting test likelihood and test perplexity to compare model fit, and suggest an alternate measure that penalizes model complexity. We show how the Akaike information criterion is a more appropriate measure, which suggests that using a modest number (up to 1000) of top-ranked bigrams is the optimal topic modelling configuration. Using these 1000 bigrams also results in improved topic quality over unigram tokenization. Further increases in topic quality can be achieved by using up to 10,000 bigrams, but this is at the cost of a more complex model. We also show that multiword (bigram and longer) named entities give consistent results, indicating that they should be represented as single tokens. This is the first work to explicitly study the effect of n -gram tokenization on LDA topic models, and the first work to make empirical recommendations to topic modelling practitioners, challenging the standard practice of unigram-based tokenization.

Exhibits within cultural heritage collections such as museums and art galleries are arranged by experts with intimate knowledge of the domain, but there may exist connections between individual exhibits that are not evident in this representation. For example, the visitors to such a space may have their own opinions on how exhibits relate to one another. In this article, we explore the possibility of estimating the perceived relatedness of exhibits by museum visitors through a variety of ontological and document similarity-based methods. Specifically, we combine the Wikipedia category hierarchy with lexical similarity measures, and evaluate the correlation with the relatedness judgements of visitors. We compare our measure with simple document similarity calculations, based on either Wikipedia documents or Web pages taken from the Web site for the museum of interest. We also investigate the hypothesis that physical distance in the museum space is a direct representation of the conceptual distance between exhibits. We demonstrate that ontological similarity measures are highly effective at capturing perceived relatedness and that the proposed RACO (Related Article Conceptual Overlap) method is able to achieve results closest to relatedness judgements provided by human annotators compared to existing state-of-the art measures of semantic relatedness.

This article reconsiders the task of MRD-based word sense disambiguation, in extending the basic Lesk algorithm to investigate the impact on WSD performance of different tokenization schemes and methods of definition extension. In experimentation over the Hinoki Sensebank and the Japanese Senseval-2 dictionary task, we demonstrate that sense-sensitive definition extension over hyponyms, hypernyms, and synonyms, combined with definition extension and word tokenization leads to WSD accuracy above both unsupervised and supervised baselines. In doing so, we demonstrate the utility of ontology induction and establish new opportunities for the development of baseline unsupervised WSD methods.

We propose a method for labelling prepositional phrases according to two different semantic role classifications, as contained in the Penn treebank and the CoNLL 2004 Semantic Role Labeling data set. Our results illustrate the difficulties in determining preposition semantics, but also demonstrate the potential for PP semantic role labelling to improve the performance of a holistic semantic role labelling system.