Eleni Miltsakaki

D-LTAG System: Discourse Parsing with a Lexicalized Tree-Adjoining Grammar

We present an implementation of a discourse parsing system for alexicalized Tree-Adjoining Grammar for discourse, specifying the integrationof sentence and discourse level processing. Our system is based on theassumption that the compositional aspects of semantics at thediscourse level parallel those at the sentence level. This coupling isachieved by factoring away inferential semantics and anaphoric features ofdiscourse connectives. Computationally, this parallelism is achievedbecause both the sentence and discourse grammar are LTAG-based and the sameparser works at both levels. The approach to an LTAG for discourse has beendeveloped by Webber and colleagues in some recent papers. Our system takes a discourseas input, parses the sentences individually, extracts the basic discourseconstituent units from the sentence derivations, and reparses the discoursewith reference to the discourse grammar while using the same parser usedat the sentence level.

Attribution and the (Non-)Alignment of Syntactic and Discourse Arguments of Connectives

The annotations of the Penn Discourse Treebank (PDTB) include (1) discourse connectives and their arguments, and (2) attribution of each argument of each connective and of the relation it denotes. Because the PDTB covers the same text as the Penn TreeBank WSJ corpus, syntactic and discourse annotation can be compared. This has revealed significant differences between syntactic structure and discourse structure, in terms of the arguments of connectives, due in large part to attribution. We describe these differences, an algorithm for detecting them, and finally some experimental results. These results have implications for automating discourse annotation based on syntactic annotation.

Sense annotation in the Penn discourse treebank

An important aspect of discourse understanding and generation involves the recognition and processing of discourse relations. These are conveyed by discourse connectives, i.e., lexical items like because and as a result or implicit connectives expressing an inferred discourse relation. The Penn Discourse TreeBank (PDTB) provides annotations of the argument structure, attribution and semantics of discourse connectives. In this paper, we provide the rationale of the tagset, detailed descriptions of the senses with corpus examples, simple semantic definitions of each type of sense tags as well as informal descriptions of the inferences allowed at each level.

Annotation and data mining of the Penn Discourse TreeBank

The Penn Discourse TreeBank (PDTB) is a new resource built on top of the Penn Wall Street Journal corpus, in which discourse connectives are annotated along with their arguments. Its use of standoff annotation allows integration with a stand-off version of the Penn TreeBank (syntactic structure) and PropBank (verbs and their arguments), which adds value for both linguistic discovery and discourse modeling. Here we describe the PDTB and some experiments in linguistic discovery based on the PDTB alone, as well as on the linked PTB and PDTB corpora.

Toward an aposynthesis of topic continuity and intrasentential anaphora

The problem of proposing referents for anaphoric expressions has been extensively researched in the literature and significant insights have been gained through the various approaches. However, no single model is capable of handling all the cases. We argue that this is due to a failure of the models to identify two distinct processes. Drawing on current insights and empirical data from various languages we propose an aposynthetic1 model of discourse in which topic continuity, computed across units, and focusing preferences internal to these units are subject to different mechanisms. The observed focusing preferences across the units (i.e., intersententially) are best modeled structurally, along the lines suggested in centering theory. The focusing mechanism within the unit is subject to preferences projected by the semantics of the verbs and the connectives in the unit as suggested in semantic/pragmatic focusing accounts. We show that this distinction not only overcomes important problems in anaphora resolution but also reconciles seemingly contradictory experimental results reported in the literature. We specify a model of anaphora resolution that interleaves the two mechanisms. We test the central hypotheses of the proposed model with an experimental study in English and a corpus-based study in Greek. Aposynthesis is a Greek word that means decomposition, that is, pulling apart the components that constitute what appears to be a uniform entity.

Real Time Web Text Classification and Analysis of Reading Difficulty

The automatic analysis and categorization of web text has witnessed a booming interest due to the increased text availability of different formats, content, genre and authorship. We present a new tool that searches the web and performs in real-time a) html-free text extraction, b) classification for thematic content and c) evaluation of expected reading difficulty. This tool will be useful to adolescent and adult low-level reading students who face, among other challenges, a troubling lack of reading material for their age, interests and reading level.

The role of centering theory's rough-shift in the teaching and evaluation of writing skills

Existing software systems for automated essay scoring can provide NLP researchers with opportunities to test certain theoretical hypotheses, including some derived from Centering Theory. In this study we employ ETSs e-rater essay scoring system to examine whether local discourse coherence, as defined by a measure of Rough-Shift transitions, might be a significant contributor to the evaluation of essays. Our positive results indicate that Rough-Shifts do indeed capture a source of incoherence, one that has not been closely examined in the Centering literature. These results not only justify Rough-Shifts as a valid transition type, but they also support the original formulation of Centering as a measure of discourse continuity even in pronominal-free text.

Matching Readers' Preferences and Reading Skills with Appropriate Web Texts

This paper describes Read-X, a system designed to identify text that is appropriate for the reader given his thematic choices and the reading ability associated with his educational background. To our knowledge, Read-X is the first web-based system that performs real-time searches and returns results classified thematically and by reading level within seconds. To facilitate educators or students searching for reading material at specific reading levels, Read-X extracts the text from the html, pdf, doc, or xml format and makes available a text editor for viewing and editing the extracted text.

Refining the Meaning of Sense Labels in PDTB: ``Concession''

The most recent release of PDTB 2.0 contains annotations of senses of connectives. The PDTB 2.0 manual describes the hierarchical set of senses used in the annotation and offers rough semantic descriptions of each label. In this paper, we refine the semantics of concession substantially and offer a formal description of concessive relations and the associated inferences drawn by the reader, utilizing basic notions from Hobbss logic, including the distinction between causes and causal complexes (Hobbs, 2005). This work is part of a larger project on the semantics of connectives which aims at developing formal descriptions of discourse relations, useful for processing real data.

Information Structure, Discourse Structure and Discourse and Discourse Semantics Workshop Proceedings

We present an implementation of a discourse parsing system for alexicalized Tree-Adjoining Grammar for discourse, specifying the integrationof sentence and discourse level processing. Our system is based on theassumption that the compositional aspects of semantics at thediscourse level parallel those at the sentence level. This coupling isachieved by factoring away inferential semantics and anaphoric features ofdiscourse connectives. Computationally, this parallelism is achievedbecause both the sentence and discourse grammar are LTAG-based and the sameparser works at both levels. The approach to an LTAG for discourse has beendeveloped by Webber and colleagues in some recent papers. Our system takes a discourseas input, parses the sentences individually, extracts the basic discourseconstituent units from the sentence derivations, and reparses the discoursewith reference to the discourse grammar while using the same parser usedat the sentence level.