The bag of visual words representation has attracted a lot of attention in the computer vision community. In particular, Probabilistic Latent Semantic Analysis (PLSA) has been applied to object recognition as an unsupervised technique built on top of the bag of visual words representation. PLSA, however, does not explicitly consider the spatial information of the visual words. In this paper, we propose an iterative technique, where a modified form of PLSA provides location and scale estimates of the foreground object through the estimated latent semantic. In return, the updated location and scale estimates will improve the estimate of the latent semantic. We call this iterative algorithm Semantic-Shift. We show results with significant improvements over PLSA.
This paper develops an analysis of the syntax-semantics interface of two types of split coordination structures. In the first type, two bare singular count nouns appear as arguments in a coordinated structure, as in bride and groom were happy. We call this the N&N construction. In the second type, the determiner shows agreement with the first conjunct, while the second conjunct is bare, as in the Spanish example el hornero y hornera cobraban en panes ('thesg.m bakersg.m and bakersg.f were p1 paid in bread loaves'). We call this the DN&N construction. Both N&N and DN&N constructions are common in languages that otherwise require an article or determiner on singular count nouns in regular argument position, and give rise to 'split' readings that cannot be accounted for by the standard semantics of conjunction in terms of set intersection. Furthermore, they are restricted to instances of 'natural' coordination. We formalize the semantics of split conjunction in terms of intersection between sets of matching pairs, which correlates with the lexical semantics and pragmatics of natural coordination. We maintain that an N&N construction gets either a definite or an indefinite interpretation by covert type-shifting, because projection of an article ranging over the coordination as a whole is blocked in languages like English and Spanish. For DN&N structures, we propose a syntactic structure in which D is in construction with the first conjunct. Coordination with a second, bare conjunct requires a covert type-shift that is licensed only under the special matchmaking semantics of conjunction. The analysis addresses a range of issues these coordinate structures raise about syntactic and semantic agreement, in particular with respect to number. Next to English and Spanish we will look into Dutch and French in detail.
Abstract This paper gives an overview of distributional modelling of word meaning for contemporary lexicography. We also apply it in a case study on automatic semantic shift detection in Slovene tweets. We use word embeddings to compare the semantic behaviour of frequent words from a reference corpus of Slovene with their behaviour on Twitter. Words with the highest model distance between the corpora are considered as semantic shift candidates. They are manually analysed and classified in order to evaluate the proposed approach as well as to gain a better qualitative understanding of the problem. Apart from the noise due to pre-processing errors (45%), the approach yields a lot of valuable candidates, especially the novel senses occurring due to daily events and the ones produced in informal communication settings.
Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts to uncovering change over time, thus neglecting other valuable dimensions such as social or political variability. We propose an approach for detecting semantic shifts between different viewpoints-broadly defined as a set of texts that share a specific metadata feature, which can be a time-period, but also a social entity such as a political party. For each viewpoint, we learn a semantic space in which each word is represented as a low dimensional neural embedded vector. The challenge is to compare the meaning of a word in one space to its meaning in another space and measure the size of the semantic shifts. We compare the effectiveness of a measure based on optimal transformations between the two spaces with a measure based on the similarity of the neighbors of the word in the respective spaces. Our experiments demonstrate that the combination of these two performs best. We show that the semantic shifts not only occur over time but also along different viewpoints in a short period of time. For evaluation, we demonstrate how this approach captures meaningful semantic shifts and can help improve other tasks such as the contrastive viewpoint summarization and ideology detection (measured as classification accuracy) in political texts. We also show that the two laws of semantic change which were empirically shown to hold for temporal shifts also hold for shifts across viewpoints. These laws state that frequent words are less likely to shift meaning while words with many senses are more likely to do so.
This paper present a method to discover the semantic shift detection(SSD) in semantic. In the way we can detect the shift with the link consisted in Web. By usage of topic shifts techniques as terms frequently occurring in documents. Our experiments results show that a number of topics can shift along in a group of terms with same semantic.