We propose IMAGINET, a model of learning visually grounded representations of language from coupled textual and visual input. The model consists of two Gated Recurrent Unit networks with shared word embeddings, and uses a multi-task objective by receiving a textual description of a scene and trying to concurrently predict its visual representation and the next word in the sentence. Mimicking an...

We apply the integrated syntactic graph feature extraction methodology to the task of automatic authorship detection. This graph-based representation allows integrating different levels of language description into a single structure. We extract textual patterns based on features obtained from shortest path walks over integrated syntactic graphs and apply them to determine the authors of docume...

A two-phase evaluation scheme is proposed for XML retrieval. In the first phase, a modified vector space model is employed to obtain similarity scores for the textual nodes of XML trees. In the second stage, the scores are propagated upward in the XML trees, with scores of the textual nodes being modified and scores of other nodes being generated. As a result, while a vector space ranking is us...

The objective of this paper is to present a textual similarity model for Information Retrieval (IR) based on the Distributional Semantic (DS) model. This model is an extension of the standard Vector Space model, which further takes into account the co-frequencies between the terms in a given reference corpus, that are considered to provide a distributional representation of the "semantics" of t...

Sentences that are syntactically quite different can often have similar or same meaning. The SemEval 2012 task of Semantic Textual Similarity aims at finding the semantic similarity between two sentences. The semantic representation of Universal Networking Language (UNL), represents only the inherent meaning in a sentence without any syntactic details. Thus, comparing the UNL graphs of two sent...

Selecting important information while accounting for repetitions is a hard task for both summarization and question answering. We propose a formal model that represents a collection of documents in a two-dimensional space of textual and conceptual units with an associated mapping between these two dimensions. This representation is then used to describe the task of selecting textual units for a...

The specification of a policy is performed in a policy language, usually following a textual representation. However, humans process images faster than text and they are prepared to process information presented in two or more dimensions: sometimes it is easier to explain things using figures and their graphical relations than writing textual representations. This paper describes a visual langu...

Academic dishonesty is a universal problem. Detecting duplicated text among natural language artifacts is a welldocumented task. However, performing similar analysis on source code presents unique problems. In this paper, I present a comparison of the application of various techniques in textual similarity processing on source code. Beyond this, I investigate the application of textual similari...

We present a method for automatic textual annotation of compressed video. Initially, cuts are detected in the video sequence where consecutive frames show a large difference. Key frames are then extracted to represent each shot. A video sequence is, thus, condensed into a few images, hence this forms a compact key frame representation of the video. Each key frame is compared with an annotated d...

This paper describes our approach to the SemEval-2017 “Semantic Textual Similarity” and “Multilingual Word Similarity” tasks. In the former, we test our approach in both English and Spanish, and use a linguistically-rich set of features. These move from lexical to semantic features. In particular, we try to take advantage of the recent Abstract Meaning Representation and SMATCH measure. Althoug...