• Publications
  • Influence
Evaluating Content Selection in Summarization: The Pyramid Method
It is argued that the method presented is reliable, predictive and diagnostic, thus improves considerably over the shortcomings of the human evaluation method currently used in the Document Understanding Conference. Expand
Automatic sense prediction for implicit discourse relations in text
We present a series of experiments on automatically identifying the sense of implicit discourse relations, i.e. relations that are not marked with a discourse connective such as "but" or "because".Expand
Revisiting Readability: A Unified Framework for Predicting Text Quality
This study combines lexical, syntactic, and discourse features to produce a highly predictive model of human readers' judgments of text readability and demonstrates that discourse relations are strongly associated with the perceived quality of text. Expand
The Impact of Frequency on Summarization
SumBasic is described, a summarization system that exploits frequency exclusively to create summaries and it is demonstrated how a frequency-based summarizer can incorporate context adjustment in a natural way and show that this adjustment contributes to the good performance of the summarizer and is sufficient means for duplication removal in multi-document summarization. Expand
Using Syntax to Disambiguate Explicit Discourse Connectives in Text
It is demonstrated that syntactic features improve performance in both disambiguation tasks and state-of-the-art results for identifying discourse vs. non-discourse usage and human-level performance on sense disambIGuation are reported. Expand
CREMA-D: Crowd-Sourced Emotional Multimodal Actors Dataset
An audio-visual dataset uniquely suited for the study of multi-modal emotion expression and perception, which consists of facial and vocal emotional expressions in sentences spoken in a range of basic emotional states, can be used to probe other questions concerning the audio- visual perception of emotion. Expand
The Pyramid Method: Incorporating human content selection variation in summarization evaluation
This article proposes a method for analysis of multiple human abstracts into semantic content units, which serves as the basis for an evaluation method that incorporates the observed variation and is predictive of different equally informative summaries. Expand
A Survey of Text Summarization Techniques
This chapter gives a broad overview of existing approaches based on how representation, sentence scoring or summary selection strategies alter the overall performance of the summarizer, and points out some of the peculiarities of the task of summarization. Expand
A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization
The research shows that a frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition. Expand