Abstract e ev lu te sever l popul r models of lo l dis ourse oheren e for dom in nd t sk genE er
lity y pplying them to ht disent ngleE mentF sing experiments on syntheti multiE p rty onvers …

Research on coreference resolution and summarization has modeled the way entities are
realized as concrete phrases in discourse. In particular there exist models of the noun …

Summ-it: Um corpus anotado com informaç oes discursivas visando `a sumarizaç ao automática
Page 1 Summ-it: Um corpus anotado com informaç oes discursivas visando `a sumarizaç ao …

We propose an approach to summarization exploiting both lexical information and the output
of an automatic anaphoric resolver, and using Singular Value Decomposition (SVD) to …

Coreference resolution is one of the fundamental and challenging tasks in natural language
processing. Resolving coreference successfully can have a significant positive effect on …

Background Entity coreference is common in biomedical literature and it can affect text
understanding systems that rely on accurate identification of named entities, such as relation …

A discourse typically involves numerous entities, but few are mentioned more than once.
Distinguishing those that die out after just one mention (singleton) from those that lead …

This thesis investigates two main research questions: the more general question of whether
using a general anaphoric resolver in real end-goal applications brings in tangible benefits …

In this thesis, we investigate automated assessment (AA) systems of free text that
automatically analyse and score the quality of writing of learners of English as a second (or …

This thesis deals with the development of a new text summarization method that uses the
latent semantic analysis (lsa). The language-independent analysis is able to capture …