[论文解读] Scalable graph-based individual named entity identification

Sammy Khalife, Michalis Vazirgiannis|arXiv (Cornell University)|Nov 26, 2018

Topic Modeling参考文献 26被引用 6

一句话总结

该论文提出了一种基于图的两阶段可扩展命名实体消歧（NEL）方法，首先使用信息检索技术过滤候选实体，然后通过图挖掘和图核方法对前K名结果进行重排序。该方法在NIST TAC-KBP数据集上实现了最先进（SOTA）的P@1精度，在CONLL/AIDA数据集上也表现出色，优于现有图-based方法，并且在更少超参数和更少标注数据的情况下，性能可与深度学习系统相媲美。

ABSTRACT

Named entity discovery (NED) is an important information retrieval problem that can be decomposed into two sub-problems. The first sub-problem, named entity recognition (NER), aims to tag pre-defined sets of words in a vocabulary (called "named entities": names, places, locations, ...) when they appear in natural language. The second subproblem, named entity linking/identification (NEL), considers these entity mentions as queries to be identified in a pre-existing database. In this paper, we consider the NEL problem, and assume a set of queries (or mentions) that have to be identified within a knowledge base. This knowledge base is represented by a text database paired with a semantic graph. We present state-of-the-art methods in NEL, and propose a 2-step method for individual identification of named entities. Our approach is well-motivated by the limitations brought by recent deep learning approaches that lack interpratability, and require lots of parameter tuning along with large volume of annotated data. First of all, we propose a filtering algorithm designed with information retrieval and text mining techniques, aiming to maximize precision at K (typically for 5 <= K <=20). Then, we introduce two graph-based methods for named entity identification to maximize precision at 1 by re-ranking the remaining top entity candidates. The first identification method is using parametrized graph mining, and the second similarity with graph kernels. Our approach capitalizes on a fine-grained classification of entities from annotated web data. We present our algorithms in details, and show experimentally on standard datasets (NIST TAC-KBP, CONLL/AIDA) their performance in terms of precision are better than any graph-based method reported, and competitive with state-of-the-art systems. Finally, we conclude on the advantages of our graph-based approach compared to recent deep learning methods.

研究动机与目标

• 为解决深度学习在NEL中可解释性差、数据/参数需求高的局限性。
• 通过利用结构化知识图谱提升个体命名实体识别的精度。
• 开发一种可扩展、高效且调参少的NEL方法，超越现有基于图的方法。
• 为现实世界NEL应用提供一种实用、可实现的系统，支持细粒度实体类型识别。

提出的方法

• 首先，采用基于信息检索和文本挖掘的过滤算法，将候选实体缩减至前K名（5 ≤ K ≤ 20），以最大化P@K。
• 其次，提出两种基于图的重排序方法：参数化图挖掘（SGM）和图核比较（GK），以最大化P@1。
• 这些方法依赖于以每个候选实体为中心的知识子图，利用语义关系和实体类型计算相似性特征。
• 从局部知识子图中提取特征，实现候选实体与真实实体之间的有效比较。
• 该方法假设可获得细粒度的实体类型（例如，PER: 演员，ORG: 足球俱乐部），以指导候选过滤与图结构构建。
• 计算复杂度与查询数和实体数呈线性关系，可在大规模知识库上实现良好可扩展性。

实验结果

研究问题

• RQ1 基于图的方法是否能在P@1指标上超越现有基于图的NEL方法？
• RQ2 K值（前K名过滤）的选择如何影响重排序阶段的最终P@1精度？
• RQ3 一种超参数更少、标注数据更少的方法是否能实现与最先进深度学习系统相当的NEL性能？
• RQ4 在NEL任务中，相较于端到端深度学习模型，使用基于图的特征在可解释性和效率方面能提升多少？

主要发现

• 所提方法在NIST TAC-KBP 2009和2010数据集上，是所有基于图的方法中报告的P@1最高者。
• 在CONLL/AIDA数据集上，该方法与最先进系统具有竞争力，展现出在不同基准上的强泛化能力。
• 在探索与过滤之间取得平衡的最优K值范围为5至10，低于或高于此范围性能均下降。
• 计算时间高效：在包含1,000个查询和280万实体的子实例上，过滤耗时约44分钟，SGM耗时约14分钟，GK耗时约16分钟。
• 该方法在分布式系统上具有良好可扩展性，20核CPU集群上的实验时间显著缩短。
• 仅需数千个训练样本即可达到高性能，表明其对数据的依赖性远低于深度学习模型。