The Winograd Schema Challenge is an alternative to the Turing Test that may provide a more meaningful measure of machine intelligence. It poses a set of coreference resolution problems that cannot be solved without human-like reasoning. In this paper, we take the view that the solution to such problems lies in establishing discourse coherence. Specifically, we examine two types of rhetorical re...

We present our recent work on query-focused summarization, focusing on our efforts in building and applying models of rhetorical-semantic relations (RSRs) such as contrast and causality. We overview ongoing work in extracting and evaluating RSR models. We describe our system for query-focused summarization, focusing on an enhanced, feature-based framework. We present results of experiments to m...

We introduce a simple semi-supervised approach to improve implicit discourse relation identification. This approach harnesses large amounts of automatically extracted discourse connectives along with their arguments to construct new distributional word representations. Specifically, we represent words in the space of discourse connectives as a way to directly encode their rhetorical function. E...

In this paper, a new model of representing semantics called the concept relational tree model is proposed. The model adapts the architecture of expression tree in providing a hierarchical organization to semantics. It is motivated by an approach known as the discourse structure tree that organizes semantics based on preposition and relies on rhetorical relations to define the connection between...

HA, EUN YOUNG. Modeling Discourse Structure and Temporal Event Relations for Automated Document Summarization with Markov Logic Networks. (Under the direction of James C. Lester.) Recent years have seen significant progress in natural language processing. A key challenge posed by many natural language applications ranging from text summarization to question answering and machine translation is ...

Segmented Discourse Representation Theory (SDRT) [2, 7] provides a dynamic semantics for discourse that exploits a rich notion of discourse structure. According to SDRT, a text is segmented into constituents related to each other by means of rhetorical relations; the resulting structure, known as a segmented discourse representation structure or SDRS has various semantic effects. This theory ha...

The paper deals with the cohesion part of a model of global discourse interpretation, usually known as Veins Theory (VT). By taking the notion of nuclearity (though ignoring relations), from the Rhetorical Structure Theory, VT computes strings of discourse units, called veins, from which domains of accessibility can be determined for each discourse unit. VT’s constructs best fit with an increme...

This paper focuses on the interpretation of metaphor in discourse. We build on previous work [1] in which we provide a formalization in a computationally-oriented formal semantic framework of a set of mappings that we claim are required for the interpretation of map-transcending metaphor. Such mappings are domain-independent and are identified as invariant adjuncts to any conceptual metaphor. I...

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 dedu...

Previous work introduced transition-based algorithms to form a unified architecture of parsing rhetorical structures (including span, nuclearity and relation), but did not achieve satisfactory performance. In this paper, we propose that transition-based model is more appropriate for parsing the naked discourse tree (i.e., identifying span and nuclearity) due to data sparsity. At the same time, ...