This book is written for all those interested in arguments and arguing—and especially
for students enrolled in courses designed to improve their critical thinking abilities. My
goal in this work is to present enough theory to explain why certain kinds of argument
are good or bad and enough illustrations and examples to show how that theory can
The book includes lively illustrations from contemporary debates and issues and
ample student exercises. Responses to some exercises are provided within the book,
while the remainder are answered in a manual available to instructors.
This paper demonstrates that generating arguments in natural language requires planning at an abstract level, and that the appropriate abstraction cannot be captured by approaches based solely upon coherence relations. An abstraction based planning system is presented which employs operators motivated by empirical study and rhetorical maxims. These operators include a subset of traditional deductive rules of inference, argumentation theoretic rules of refutation, and inductive reasoning patterns. ...
We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The ﬁrst model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more reﬁned hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not necessarily identical.
THERE is now but one great question dividing the American people, and that, to the great danger of the
stability of our government, the concord and harmony of our citizens, and the perpetuation of our liberties,
divides us by a geographical line.
The core-adjunct argument distinction is a basic one in the theory of argument structure. The task of distinguishing between the two has strong relations to various basic NLP tasks such as syntactic parsing, semantic role labeling and subcategorization acquisition. This paper presents a novel unsupervised algorithm for the task that uses no supervised models, utilizing instead state-of-the-art syntactic induction algorithms. This is the ﬁrst work to tackle this task in a fully unsupervised scenario. ...
In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.
This volume brings together a collection of essays on the history and philosophy of probability and statistics by one of the eminent scholars in these subjects. Written over the last ﬁfteen years, they fall into three broad categories. The ﬁrst deals with the use of symmetry arguments in inductive probability, in particular, their use in deriving rules of succession (Carnap’s “continuum of inductive methods”).
How can you quickly and proficiently construct both personal-opinion and fact-based arguments that demonstrate coherence? By starting with a clear method of organization. There are two ways to organize an argument: deduction and induction. Let's start with the personal-opinion argument and deduction.
This paper describes the application of so-called topic models to selectional preference induction. Three models related to Latent Dirichlet Allocation, a proven method for modelling document-word cooccurrences, are presented and evaluated on datasets of human plausibility judgements. Compared to previously proposed techniques, these models perform very competitively, especially for infrequent predicate-argument combinations where they exceed the quality of Web-scale predictions while using relatively little data. ...
Current Semantic Role Labeling technologies are based on inductive algorithms trained over large scale repositories of annotated examples. Frame-based systems currently make use of the FrameNet database but fail to show suitable generalization capabilities in out-of-domain scenarios. In this paper, a state-of-art system for frame-based SRL is extended through the encapsulation of a distributional model of semantic similarity. The resulting argument classiﬁcation model promotes a simpler feature space that limits the potential overﬁtting effects....
Hand-coded scripts were used in the 1970-80s as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. We propose unsupervised induction of similar schemata called narrative event chains from raw newswire text. A narrative event chain is a partially ordered set of events related by a common protagonist. We describe a three step process to learning narrative event chains. The ﬁrst uses unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments.