A Knowledge Based Strategy for Recognising Textual Entailment

Knowledge-Based Textual Inference via Parse-Tree Transformations

Journal of Artificial Intelligence Research ◽

10.1613/jair.4584 ◽

2015 ◽

Vol 54 ◽

pp. 1-57 ◽

Cited By ~ 2

Author(s):

Roy Bar-Haim ◽

Ido Dagan ◽

Jonathan Berant

Keyword(s):

Natural Language ◽

Relation Extraction ◽

Practical Applications ◽

Knowledge Based ◽

Tree Transformations ◽

Textual Entailment ◽

Automatic Methods ◽

Parse Trees ◽

Recognizing Textual Entailment ◽

Meaning Representation

Textual inference is an important component in many applications for understanding natural language. Classical approaches to textual inference rely on logical representations for meaning, which may be regarded as "external" to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe an inference formalism that operates directly on language-based structures, particularly syntactic parse trees. New trees are generated by applying inference rules, which provide a unified representation for varying types of inferences. We use manual and automatic methods to generate these rules, which cover generic linguistic structures as well as specific lexical-based inferences. We also present a novel packed data-structure and a corresponding inference algorithm that allows efficient implementation of this formalism. We proved the correctness of the new algorithm and established its efficiency analytically and empirically. The utility of our approach was illustrated on two tasks: unsupervised relation extraction from a large corpus, and the Recognizing Textual Entailment (RTE) benchmarks.

Download Full-text

A Knowledge-Based Textual Entailment Approach Applied to the AVE Task

Evaluation of Multilingual and Multi-modal Information Retrieval - Lecture Notes in Computer Science ◽

10.1007/978-3-540-74999-8_58 ◽

2007 ◽

pp. 490-493 ◽

Cited By ~ 1

Author(s):

Ó. Ferrández ◽

R. M. Terol ◽

R. Muñoz ◽

P. Martínez-Barco ◽

M. Palomar

Keyword(s):

Knowledge Based ◽

Textual Entailment

Download Full-text

Multiple Agent Based Entailment System(MABES) for RTE

10.29007/1gv1 ◽

2018 ◽

Author(s):

Byungtaek Jung ◽

Chiseung Soh ◽

Kihyun Hong ◽

Seungtak Lim ◽

Young-Yik Rhim

Keyword(s):

Artificial Intelligence ◽

Expert Knowledge ◽

Legal Reasoning ◽

Agent Based ◽

Knowledge Based ◽

Multiple Agent ◽

Textual Entailment ◽

Legal Knowledge Representation ◽

Recognizing Textual Entailment ◽

Legal Expertise

Despite growing needs of the legal artificial intelligence (AI), its development is slower than other AI domains because legal expertise is essentially required to develop legal AI systems. Legal knowledge representation on legal expertise needs to be considered to implement legal reasoning AI systems. In this paper, we present a legal reasoning methodology, which utilizes multiple expert knowledge based agents. These agents are designed to solve recognizing textual entailment (RTE) problems with syntactic and interpretative knowledge. The validity of the proposed method is provided through experiments with the COLIEE 2017 data.

Download Full-text

Is the Personal Always Political?

Journal of Individual Differences ◽

10.1027/1614-0001/a000230 ◽

2017 ◽

Vol 38 (3) ◽

pp. 133-143 ◽

Cited By ~ 4

Author(s):

Danny Osborne ◽

Yannick Dufresne ◽

Gregory Eady ◽

Jennifer Lees-Marshment ◽

Cliff van der Linden

Keyword(s):

Survey Data ◽

National Survey ◽

Negative Relationship ◽

Openness To Experience ◽

Political Sophistication ◽

Knowledge Based

Abstract. Research demonstrates that the negative relationship between Openness to Experience and conservatism is heightened among the informed. We extend this literature using national survey data (Study 1; N = 13,203) and data from students (Study 2; N = 311). As predicted, education – a correlate of political sophistication – strengthened the negative relationship between Openness and conservatism (Study 1). Study 2 employed a knowledge-based measure of political sophistication to show that the Openness × Political Sophistication interaction was restricted to the Openness aspect of Openness. These studies demonstrate that knowledge helps people align their ideology with their personality, but that the Openness × Political Sophistication interaction is specific to one aspect of Openness – nuances that are overlooked in the literature.

Download Full-text