公开(公告)号：US09514098B1

公开(公告)日：2016-12-06

申请号：US14141182

申请日：2013-12-26

Applicant: Google Inc.

Inventor： Amarnag Subramanya ,  Jingyi Liu ,  Fernando Carlos das Neves Pereira ,  Kai Chen ,  Jay Ponte ,  Rami Al-Rfou′

IPC: G06F17/21

CPC classification number: G06F17/21 ,  G06F17/277 ,  G06F17/278

Abstract: Methods and apparatus related to determining coreference resolution using distributed word representations. Distributed word representations, indicative of syntactic and semantic features, may be identified for one or more noun phrases. For each of the one or more noun phrases, a referring feature representation and an antecedent feature representation may be determined, where the referring feature representation includes the distributed word representation, and the antecedent feature representation includes the distributed word representation augmented by one or more antecedent features. In some implementations the referring feature representation may be augmented by one or more referring features. Coreference embeddings of the referring and antecedent feature representations of the one or more noun phrases may be learned. Distance measures between two noun phrases may be determined based on the coreference embeddings.

Abstract translation: 与使用分布式字表示法确定协同解析相关的方法和设备。 可以为一个或多个名词短语识别表示句法和语义特征的分布式词表示。 对于一个或多个名词短语中的每个，可以确定引用特征表示和先行特征表示，其中引用特征表示包括分布式词表示，并且先行特征表示包括由一个或多个前缀增强的分布式词表示 特征。 在一些实现中，引用特征表示可以由一个或多个引用特征来增强。 可以学习一个或多个名词短语的引用和先行特征表示的核心嵌入。 两个名词短语之间的距离度量可以基于核心嵌入来确定。

公开(公告)号：US09697475B1

公开(公告)日：2017-07-04

申请号：US14138606

申请日：2013-12-23

Applicant: GOOGLE INC.

Inventor： Amarnag Subramanya ,  Michael Ringgaard ,  Fernando Carlos das Neves Pereira

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06N7/005

Abstract: Systems and methods are disclosed for using an additive context model for entity disambiguation. An example method may include receiving a span of text from a document and a phrase vector for the span. The phrase vector may have a quantity of features and represent a context for the span. The method also includes determining a quantity of candidate entities from a knowledge base that have been referred to by the span. For each of the quantity of candidate entities, the method may include determining a support score for the candidate entity for each feature in the phrase vector, combining the support scores additively, and computing a probability that the span resolves to the candidate entity given the context. The method may also include resolving the span to a candidate entity with a highest probability.