AZMAT: Sentence Similarity Using Associative Matrices
نویسندگان
چکیده
This work uses recursive autoencoders (Socher et al., 2011), word embeddings (Pennington et al., 2014), associative matrices (Schuler, 2014) and lexical overlap features to model human judgments of sentential similarity on SemEval-2015 Task 2: English STS (Agirre et al., 2015). Results show a modest positive correlation between system predictions and human similarity scores, ranking 69th out of 74 submitted systems.
منابع مشابه
Problems of classifying associative or Lie algebras and triples of symmetric or skew-symmetric matrices are wild
We prove that the problems of classifying triples of symmetric or skew-symmetric matrices up to congruence, local commutative associative algebras with zero cube radical and square radical of dimension 3, and Lie algebras with central commutator subalgebra of dimension 3 are hopeless since each of them reduces to the problem of classifying pairs of n-by-n matrices up to simultaneous similarity....
متن کاملمقایسه روشهای مختلف یادگیری ماشین در خلاصهسازی استخراجی گفتار به گفتار فارسی بدون استفاده از رونوشت
In this paper, extractive speech summarization using different machine learning algorithms was investigated. The task of Speech summarization deals with extracting important and salient segments from speech in order to access, search, extract and browse speech files easier and in a less costly manner. In this paper, a new method for speech summarization without using automatic speech recognitio...
متن کاملComparing Meaning in Language and Cognition: P-Hyponymy, Concept Combination, Asymmetric Similarity
In this dissertation we work in the framework of compositional distributional models of meaning to examine a number of asymmetric linguistic phenomena that manifest themselves in language and cognition. These include overextension with respect to concept combination, asymmetry of similarity judgment and hyponymy and typicality. In particular, we make use of the formalism of density matrices, wh...
متن کاملAn Activation-Based Model of Sentence Processing as Skilled Memory Retrieval
We present a detailed process theory of the moment-by-moment working-memory retrievals and associated control structure that subserve sentence comprehension. The theory is derived from the application of independently motivated principles of memory and cognitive skill to the specialized task of sentence parsing. The resulting theory construes sentence processing as a series of skilled associati...
متن کاملKSU Team’s Dialogue System at the NTCIR-13 Short Text Conversation Task 2
In this paper, the methods and results by the team KSU for STC-2 task at NTCIR-13 are described. We implemented both retrieval-based methods and a generation-based method. In the retrieval-based methods, a comment text with high similarity with the given utterance text is obtained from Yahoo! News comments data, and the reply text to the comment text is returned as the response to the input. Tw...
متن کامل