Named Entity Recognition in Twitter using Images and Text
This addresses the challenge of NER in short, noisy social media text for information extraction applications, but it is incremental as it builds on existing methods with a novel feature combination.
The paper tackles the problem of Named Entity Recognition in noisy Twitter text by proposing a multi-level architecture that uses both image and text features, achieving a competitive F-measure of 0.59 on the Ritter dataset.
Named Entity Recognition (NER) is an important subtask of information extraction that seeks to locate and recognise named entities. Despite recent achievements, we still face limitations with correctly detecting and classifying entities, prominently in short and noisy text, such as Twitter. An important negative aspect in most of NER approaches is the high dependency on hand-crafted features and domain-specific knowledge, necessary to achieve state-of-the-art results. Thus, devising models to deal with such linguistically complex contexts is still challenging. In this paper, we propose a novel multi-level architecture that does not rely on any specific linguistic resource or encoded rule. Unlike traditional approaches, we use features extracted from images and text to classify named entities. Experimental tests against state-of-the-art NER for Twitter on the Ritter dataset present competitive results (0.59 F-measure), indicating that this approach may lead towards better NER models.