Learn More
This paper describes an annotated gold standard sample corpus of Early Modern German containing over 50,000 tokens of text manually annotated with POS tags, lemmas, and normalised spelling variants. The corpus is the first resource of its kind for this variant of German, and represents an ideal test bed for evaluating and adapting existing NLP tools on(More)
We describe experiments carried out at the University of Edinburgh for our TREC 2006 QA participation. Our main effort was to develop an approach to QA that is based on frame semantics. Two algorithms were implemented to this end, building on the lexical resources FrameNet, PropBank and VerbNet. The first algorithm uses the resources to generate potential(More)
The goal of this study is to evaluate an 'off-the-shelf' POS-tagger for modern German on historical data from the Early Modern period (1650-1800). With no specialised tagger available for this particular stage of the language, our findings will be of particular interest to smaller, humanities-based projects wishing to add POS annotations to their historical(More)
Human ratings are an important source for evaluating computational models that predict compositionality, but like many data sets of human semantic judgements, are often fraught with uncertainty and noise. However, despite their importance, to our knowledge there has been no extensive look at the effects of cleansing methods on human rating data. This paper(More)
This paper describes the SubCat-Extractor as a novel tool to obtain verb subcategori-sation data from parsed German web corpora. The SubCat-Extractor is based on a set of detailed rules that go beyond what is directly accessible in the parses. The extracted subcategorisation database is represented in a compact but linguistically detailed and flexible(More)
Footwear is supposed to have influence on postural control and is a potential aspect to address in the prevention of falls in the elderly. This study aimed to show whether measurements of static balance and gait are different with habitual shoes compared to new special senior shoes with different heel height and whether these results change after(More)
For many NLP applications such as Information Extraction and Sentiment Detection , it is of vital importance to distinguish between synonyms and antonyms. While the general assumption is that dis-tributional models are not suitable for this task, we demonstrate that using suitable features, differences in the contexts of synonymous and antonymous German(More)
I propose a computational treatment of superlatives , starting with superlative constructions and the main challenges in automatically recognising and extracting their components. Initial experimental evidence is provided for the value of the proposed work for Question Answering. I also briefly discuss its potential value for Sentiment Detection and Opinion(More)
A new collection of semantically related word pairs in German is presented, which was compiled via human judgement experiments and comprises (i) a representative selection of target lexical units balanced for semantic category, polysemy, and corpus frequency, (ii) a set of human-generated semantically related word pairs based on the target units, and (iii)(More)