One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated. One could also assume that such expressions usually consti
tute syntactically meaningful units; however, mention spans have been annotated simply by delimiting token intervals in most coreference projects, i.e., independently of any syntactic representation. We argue that it could be advantageous to make syntactic and coreference annotations convergent in the long term. We present a pilot empirical study focused on matches and mismatches between hand-annotated linear mention spans and automatically parsed syntactic trees that follow Universal Dependencies conventions. The study covers 9 datasets for 8 different languages.
Classical information retrieval systems such as BM25 rely on exact lexical match and can carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft matching all query document terms, but they lose the computati
on efficiency of exact match systems. This paper presents COIL, a contextualized exact match retrieval architecture, where scoring is based on overlapping query document tokens' contextualized representations. The new architecture stores contextualized token representations in inverted lists, bringing together the efficiency of exact match and the representation power of deep language models. Our experimental results show COIL outperforms classical lexical retrievers and state-of-the-art deep LM retrievers with similar or smaller latency.
The paper reports on the methodology and final results of a large-scale synset mapping between plWordNet and Princeton WordNet. Dedicated manual and semi-automatic mapping procedures as well as interlingual relation types for nouns, verbs, adjectives and adverbs are described. The statistics of all types of interlingual relations are also provided.
The way of soccer analysis by using videos recordings are considered as one of methods that help to study and analyze some of sport behaviors such as goal kick and play 1 vs 1, which is carried out by the player on pitch during the match. The aim of
this study is to continue presenting the newest and most important information about training method of goal kick. Thus this study focused on the goal kick case in soccer and analyzed it in many aspects in world cup 2014 in Brazil. All round of 16, Quarter -finals, Semi-finals and Final play have been recorded -16 plays in total- and then they were analyzed according to the thesis aims.
It showed that the average of goals in each game was 2,18 and the most important areas in which recorded goals were No. 3,2and 6 and one- third of goals scored were distributed on the last ten minutes of the match.
