If Sentences Could See: Investigating Visual Information for Semantic Textual Similarity
نویسندگان
چکیده
We investigate the effects of incorporating visual signal from images into unsupervised Semantic Textual Similarity (STS) measures. STS measures exploiting visual signal alone are shown to outperform, in some settings, linguistic-only measures by a wide margin, whereas multi-modal measures yield further performance gains. We also show that selective inclusion of visual information may further boost performance in the multi-modal setup.
منابع مشابه
Semantic Priming Effect on Relative Clause Attachment Ambiguity Resolution in L2
This study examined whether processing ambiguous sentences containing relative clauses (RCs) following a complex determiner phrase (DP) by Persian-speaking learners of L2 English with different proficiency and working memory capacities (WMCs) is affected by semantic priming. The semantic relationship studied was one between the subject/verb of the main clause and one of the DPs in the complex D...
متن کاملCFILT-CORE: Finding Semantic Textual Similarity using UNL
Semantic Textual Similarity is the task of finding the degree of similarity between a pair of sentences through semantics extraction. This is motivated by the fact that syntactically diverse sentences often convey the same meaning. This paper describes the approach that was used in the *SEM Shared Task 2013. The approach combines semantic, syntactic and lexical similarity measures for finding s...
متن کاملjanardhan: Semantic Textual Similarity using Universal Networking Language graph matching
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...
متن کاملSemantic Textual Similarity
Through this project, we will explore Semantic Textual Similarity a shared task in Sem Eval 2012. The problem involves comparing a pair of sentences for semantic equivalence, reporting the equivalence on a scale of 0 5 with 0 meaning no equivalence and 5 meaning semantically equivalent. This task is more challenging than determining if the two sentences are paraphrases (a simple yes/no answer),...
متن کاملSemantic Similarity of Arabic Sentences with Word Embeddings
Semantic textual similarity is the basis of countless applications and plays an important role in diverse areas, such as information retrieval, plagiarism detection, information extraction and machine translation. This article proposes an innovative word embedding-based system devoted to calculate the semantic similarity in Arabic sentences. The main idea is to exploit vectors as word represent...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017