paper-with-me

홈 › Papers

The Mechanism of Additive Composition

2015-11-26 · Ran Tian, Naoaki Okazaki, Kentaro Inui

Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitchell and Lapata, 2010) is a widely used method for computing meanings of phrases, which takes the average of vector representations of the constituent words. In this article, we prove an upper bound for the bias of additive composition, which is the first theoretical analysis on compositional frameworks from a machine learning point of view. The bound is written in terms of collocation strength; we prove that the more exclusively two successive words tend to occur together, the more accurate one can guarantee their additive composition as an approximation to the natural phrase vector. Our proof relies on properties of natural language data that are empirically verified, and can be theoretically derived from an assumption that the data is generated from a Hierarchical Pitman-Yor Process. The theory endorses additive composition as a reasonable operation for calculating meanings of phrases, and suggests ways to improve additive compositionality, including: transforming entries of distributional word vectors by a function that meets a specific condition, constructing a novel type of vector representations to make additive composition sensitive to word order, and utilizing singular value decomposition to train word vectors.

📄 PDF Abstract BibTeX arXiv:1511.08407

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime

2022-06-25 · Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon, Oliver Kosut 외

Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a large number of compositions. As a cons…

Quantization

Composing Distributed Representations of Relational Patterns

2017-07-23 · ACL 2016 8 · Sho Takase, Naoaki Okazaki, Kentaro Inui

Learning distributed representations for relation instances is a central technique in downstream NLP applications. In order to address semantic modeling of relational patterns, this paper constructs a new dataset that pr…

General ClassificationRelationRelation Classification

Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms

2021-07-27 · David M. Sommer, Lukas Abfalterer, Sheila Zingg, Esfandiar Mohammadi

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bound…

Sensitivity

Additive Compositionality of Word Vectors

2019-11-01 · WS 2019 11 · Yeon Seonwoo, Sungjoon Park, Dongkwan Kim, Alice Oh

Additive compositionality of word embedding models has been studied from empirical and theoretical perspectives. Existing research on justifying additive compositionality of existing word embedding models requires a rath…

SentenceSentence SimilarityWord Similarity

Smoothed Differential Privacy

2021-07-04 · Ao Liu, Yu-Xiang Wang, Lirong Xia

Differential privacy (DP) is a widely-accepted and widely-applied notion of privacy based on worst-case analysis. Often, DP classifies most mechanisms without additive noise as non-private (Dwork et al., 2014). Thus, add…