• Publications
  • Influence
Evaluating Neural Word Representations in Tensor-Based Compositional Settings
TLDR
In the more constrained tasks, co-occurrence vectors are competitive, although choice of compositional method is important; on the largerscale tasks, they are outperformed by neural word embeddings, which show robust, stable performance across the tasks. Expand
A Study of Entanglement in a Categorical Framework of Natural Language
TLDR
This paper examines a number of implementations of the categorical framework of Coecke et al. Expand
Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs
TLDR
The compositional model is an L STM equipped with a dynamic disambiguation mechanism on the input word embeddings (a Multi-Sense LSTM), addressing polysemy issues. Expand
A Unified Sentence Space for Categorical Distributional-Compositional Semantics: Theory and Experiments
This short paper summarizes a faithful implementation of the categorical framework of Coecke et al. (2010), the aim of which is to provide compositionality in distributional models of lexicalExpand
Prior Disambiguation of Word Tensors for Constructing Sentence Vectors
TLDR
This paper proposes disambiguation algorithms for a number of tensor-based models, and tests the effectiveness of these algorithms on a variety of tasks, showing that disambIGuation can provide better compositional representation even for the case of tensors. Expand
Reasoning about Meaning in Natural Language with Compact Closed Categories and Frobenius Algebras
TLDR
The Frobenius algebras enable us to work in a single space in which meanings of words, phrases, and sentences of any structure live and enhance the applicability of the theory. Expand
Distributional Inclusion Hypothesis for Tensor-based Composition
TLDR
This paper focuses on inclusion properties of tensors; its main contribution is a theoretical and experimental analysis of how feature inclusion works in different concrete models of verb tensors. Expand
Syntax-Aware Multi-Sense Word Embeddings for Deep Compositional Models of Meaning
TLDR
This work detail a compositional distributional framework based on a rich form of word embeddings that aims at facilitating the interactions between words in the context of a sentence that is demonstrated on the MSRPar task. Expand
Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models
TLDR
CAmbridge Rare word Dataset (Card-660) is proposed, an expert-annotated word similarity dataset which provides a highly reliable, yet challenging, benchmark for rare word representation techniques. Expand
Compositional distributional semantics with compact closed categories and Frobenius algebras
TLDR
In the proposed extension, the concept of a distributional vector is replaced with that of a density matrix, which compactly represents a probability distribution over the potential different meanings of the specific word. Expand
...
1
2
3
4
...