1,721,917 research outputs found
A Survey of NLP Methods and Resources for Analyzing the Collaborative Writing Process in Wikipedia
No full textCognate Production using Character-based Machine Translation
No full textCognates are words in different languages that are associated with each other by language learners. Thus, cognates are important indicators for the prediction of the perceived difficulty of a text. We introduce a method for automatic cognate production using character-based machine translation. We show that our approach
is able to learn production patterns from noisy training data and that it works for a wide range of language pairs. It even works across different alphabets, e.g. we obtain good results on the tested language pairs English-Russian, English-Greek, and English-Farsi. Our method performs significantly better than similarity measures used in previous work on cognates
Collective Intelligence and Language Resources: Introduction to the Special Issue on Collaboratively Constructed Language Resources
No full text
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement
Get PDFThe behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable.We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the mosteffective explanation methods and recommend them for explaining DNNs in NLP
Multimodal Grounding for Language Processing
No full textThis survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language. We categorize the information flow in multimodal processing with respect to cognitive models of human information processing and analyze different methods for combining multimodal representations. Based on this methodological inventory, we discuss the benefit of multimodal grounding for a variety of language processing tasks and the challenges that arise. We particularly focus on multimodal grounding of verbs which play a crucial role for the compositional power of language
A domain-agnostic approach for opinion prediction on speech
No full textWe explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction. We represent the speech signal by mel-frequency cepstral coefficients and apply long short-term memory neural networks to automatically learn temporal regularities in speech. In contrast to previous work, our approach does not require complex feature engineering and works without textual transcripts. As a consequence, it can easily be applied on various speech analysis tasks for different languages and the results show that it can nevertheless be competitive to the state-of-the-art in opinion prediction. In a detailed error analysis for opinion mining we find that our approach performs well in identifying speaker-specific characteristics, but should be combined with additional information if subtle differences in the linguistic content need to be identified
Introduction to Ubiquitous Computing
No full textThe present chapter is intended as a lightweight introduction to ubiquitous computing as a whole, in preparation for the more specific book parts and chapters that cover selected aspects. This chapter thus assumes the preface of this book to be prior knowledge. In the following, a brief history of ubiquitous computing (UC) is given first, concentrating on selected facts considered as necessary background for understanding the rest of the book. Some terms and a few important standards are subsequently mentioned that are considered necessary for understanding related literature. For traditional standards like those widespread in the computer networks world, at least superficial knowledge must be assumed since their coverage is impractical for a field with such diverse roots as UC. In the last part of this chapter, we will discuss two kinds of reference architectures, explain why they are important for the furthering of Ubiquitous Computing and for the reader’s understanding, and briefly sketch a few of these architectures by way of example
- …
