Ani Nenkova

Revisiting Readability: A Unified Framework for Predicting Text Quality (2009)

Emily Pitler, Ani Nenkova

We combine lexical, syntactic, and discourse features to produce a highly predictive model of human readers ’ judgments of text readability. This is the first study to take into account such a...

Can you summarize this? Identifying correlates of input difficulty for generic multi-document summarization (2009)

Ani Nenkova, Annie Louis

Different summarization requirements could make the writing of a good summary more difficult, or easier. Summary length and the characteristics of the input are such constraints influencing the...

AUTOMATIC DETECTION OF CONTRASTIVE ELEMENTS IN SPONTANEOUS SPEECH (2009)

Ani Nenkova, Dan Jurafsky

In natural speech people use different levels of prominence to signal which parts of an utterance are especially important. Contrastive elements are often produced with stronger than usual prominence...

Detecting prominence in conversational speech: pitch accent, givenness and focus (2009)

Vivek Kumar, Rangarajan Sridhar, Ani Nenkova, Shrikanth Narayanan, Dan Jurafsky

The variability and reduction that are characteristic of talking in natural interaction make it very difficult to detect prominence in conversational speech. In this paper, we present analytic...

Intonational overload: Uses of the Downstepped (H *!H * L- L%) contour in read and spontaneous speech (2008)

Julia Hirschberg, Agustín Gravano, Ani Nenkova, Elisa Sneed, Gregory Ward

Intonational contours are overloaded, conveying different meanings in different contexts. In this paper we examine two potential uses of the downstepped contours in Standard American English, in the...

Measuring Importance and Query Relevance in Topic-focused Multi-document Summarization (2008)

Surabhi Gupta, Ani Nenkova, Dan Jurafsky

The increasing complexity of summarization systems makes it difficult to analyze exactly which modules make a difference in performance. We carried out a principled comparison between the two most...

Abstract (2008)

Sasha Blair-goldensohn, David Evans, Vasileios Hatzivassiloglou, Kathleen Mckeown, Ani Nenkova, Rebecca Passonneau, ...

We describe our participation in tasks 2, 4 and 5 of the DUC 2004 evaluation. For each task, we present the system(s) used, focusing on novel and newly developed aspects. We also analyze the results...

Abstract (2008)

Sasha Blair-goldensohn, David Evans, Vasileios Hatzivassiloglou, Kathleen Mckeown, Ani Nenkova, Rebecca Passonneau, ...

We describe our participation in tasks 2, 4 and 5 of the DUC 2004 evaluation. For each task, we present the system(s) used, focusing on novel and newly developed aspects. We also analyze the results...

Easily Identifiable Discourse Relations (2008)

Pitler, Emily, Raghupathy, Mridhula, Mehta, Hena, Nenkova, Ani, Lee, Alan, Joshi, Aravind K

We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized contingency, comparison, temporal...

ABSTRACT Do Summaries Help? A Task-Based Evaluation of Multi-Document Summarization (2008)

Kathleen Mckeown, Ani Nenkova

We describe a task-based evaluation to determine whether multi-document summaries measurably improve user performance when using online news browsing systems for directed research. We evaluated the...

Improving the Coherence of Multi-document Summaries: a Corpus Study for Modeling the Syntactic Realization of Entities (2008)

Ani Nenkova

References included in multi-document summaries are often problematic. In this paper, we present a corpus study performed to derive statistical models for the syntactic realization of referential...

High frequency word entrainment in spoken dialogue (2008)

Ani Nenkova, Agustín Gravano, Julia Hirschberg

Cognitive theories of dialogue hold that entrainment, the automatic alignment between dialogue partners at many levels of linguistic representation, is key to facilitating both production and...

Entity-driven rewrite for multidocument summarization (2008)

Ani Nenkova

In this paper we explore the benefits from and shortcomings of entity-driven noun phrase rewriting for multi-document summarization of news. The approach leads to 20 % to 50 % different content in...

Easily identifiable discourse relations (2008)

Emily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee, Aravind Joshi

We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized relations. We show that while...

Automatic Detection of Contrastive Elements in Spontaneous Speech (2007)

Nenkova, Ani, Jurafsky, Dan

In natural speech people use different levels of prominence to signal which parts of an utterance are especially important. Contrastive elements are often produced with stronger than usual prominence...

General Terms (2007)

Kathleen R. Mckeown, Regina Barzilay, David Evans, Vasileios Hatzivassiloglou, Judith L. Klavans, Ani Nenkova, ...

Recently, there have been significant advances in several areas of language technology, including clustering, text categorization, and summarization. However, efforts to combine technology from these...

Modelling Prominence and Emphasis Improves Unit-Selection Synthesis (2007)

Strom, Volker, Nenkova, Ani, Clark, Robert, Vazquez-Alvarez, Yolanda, Brenier, Jason, King, Simon, ...

We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously...

Syntactic Simplification for Improving Content Selection in Multi-Document Summarization (2007)

Siddharthan, Advaith, Nenkova, Ani, McKeown, Kathleen

In this paper, we explore the use of automatic syntactic simplification for improving content selection in multi-document summarization. In particular, we show how simplifying parentheticals by...

Modelling prominence and emphasis improves unit-selection synthesis (2007)

Strom, Volker, Nenkova, Ani, Clark, Robert A J, Vazquez-Alvarez, Yolanda, Brenier, Jason, King, Simon, ...

We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously...

To memorize or to predict: Prominence labeling in conversational speech (2007)

Nenkova, Ani, Brenier, Jason, Kothari, Anubha, Calhoun, Sasha, Whitton, Laura, Beaver, David, ...

The immense prosodic variation of natural conversational speech makes it challenging to predict which words are prosodically prominent in this genre. In this paper, we examine a new feature, accent...

The pyramid method: incorporating human content selection variation in summarization evaluation (2007)

Ani Nenkova, Rebecca Passonneau, Kathleen Mckeown

Human variation in content selection in summarization has given rise to some fundamental research questions: How can one incorporate the observed variation in suitable evaluation measures? How can...

The pyramid method: incorporating human content selection variation in summarization evaluation (2007)

Ani Nenkova, Rebecca Passonneau, Kathleen Mckeown

Human variation in content selection in summarization has given rise to some fundamental research questions: How can one incorporate the observed variation in suitable evaluation measures? How can...

Modelling prominence and emphasis improves unit-selection synthesis (2007)

Volker Strom, Ani Nenkova, Robert Clark, A Vazquez-alvarez, Jason Brenier, Simon King, ...

We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously...

Understanding the process of multi-document summarization: Content selection, rewriting and evaluation (2006)

Nenkova, Ani

Recent years have seen unprecedented interest in news aggregation and browsing, with dedicated corporate and research websites becoming increasingly popular. Generic multidocument summarization can...

The (non)utility of linguistic features for predicting prominence in spontaneous speech (2006)

Jason M. Brenier, Ani Nenkova, Anubha Kothari, Laura Whitton, David Beaver, Dan Jurafsky

Conversational speech is characterized by prosodic variability which makes pitch accent prediction for this genre especially difficult. The linguistic literature points out that complex features such...

A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization (2006)

Ani Nenkova

The usual approach for automatic summarization is sentence extraction, where key sentences from the input documents are selected based on a suite of features. While word frequency often is used as a...

Do Summaries Help? A Task-Based Evaluation of Multi-Document Summarization (2005)

Kathleen Mckeown, Rebecca J. Passonneau, David K. Elson, Ani Nenkova, Julia Hirschberg

We describe a task-based evaluation to determine whether multi-document summaries measurably improve user performance when using online news browsing systems for directed research. We evaluated the...

Automation of Summary Evaluation by the Pyramid Method (2005)

Aaron Harnly Ani, Ani Nenkova, Rebecca Passonneau, Owen Rambow

The manual Pyramid method for summary evaluation, which focuses on the task of determining if a summary expresses the same content as a set of manual models, has shown sufficient promise that the...

Automatically Learning Cognitive Status for Multi-Document Summarization Of Newswire (2005)

Ani Nenkova, Advaith Siddharthan, Kathleen Mckeown

Machine summaries can be improved by using knowledge about the cognitive status of news article referents. In this paper, we present an approach to automatically acquiring distinctions in cognitive...

Automatically learning cognitive status for multi-document summarization of newswire (2005)

Ani Nenkova, Advaith Siddharthan, Kathleen Mckeown

Machine summaries can be improved by using knowledge about the cognitive status of news article referents. In this paper, we present an approach to automatically acquiring distinctions in cognitive...

Syntactic simplification for improving content selection in multi-document summarization (2004)

Advaith Siddharthan, Ani Nenkova, Kathleen Mckeown

In this paper, we explore the use of automatic syntactic simplification for improving content selection in multi-document summarization. In particular, we show how simplifying parentheticals by...

Columbia University at DUC 2004 (2004)

Sasha Blair-Goldensohn, David Evans, Vasileios Hatzivassiloglou, Kathleen Mckeown, Ani Nenkova, Rebecca Passonneau, ...

We describe our participation in tasks 2, 4 and 5 of the DUC 2004 evaluation. For each task, we present the system (s) used, focusing on novel and newly developed aspects. We also analyze the results...

Evaluating Content Selection in Human- or Machine-Generated Summaries: The Pyramid Scoring Method (2003)

Passonneau, Rebecca J., Nenkova, Ani

From the outset of automated generation of summaries, the difficulty of evaluation has been widely discussed. Despite many promising attempts, we believe it remains an unsolved problem. Here we...

Improving the Coherence of Multi-document Summaries: a Corpus Study for Modeling the Syntactic Realization of Entities (2003)

Nenkova, Ani, McKeown, Kathleen R.

References included in multi-document summaries are often problematic. In this paper, we present a corpus study performed to derive statistical models for the syntactic realization of referential...

Columbia at the document understanding conference 2003 (2003)

Ani Nenkova, Barry Schiffman, Andrew Schlaiker, Sasha Blair-goldensohn, Regina Barzilay, Sergey Sigelman, ...

based on the multi-document summarization system that we developed for DUC 2002 (McKeown et al., 2002). It uses different summarization strategies depending on the

Columbia’s newsblaster: New features and future directions (demo (2003)

Kathleen Mckeown, Regina Barzilay, John Chen, David Elson, David Evans, Judith Klavans, ...

Columbia’s Newsblaster tracking and summarization system is a robust system that clusters news into events, categorizes events into broad topics and summarizes multiple articles on each event. Here...

Columbia’s newsblaster: New features and future directions (demo (2003)

Kathleen Mckeown, Regina Barzilay, John Chen, David Elson, David Evans, Judith Klavans, ...

Columbia’s Newsblaster tracking and summarization system is a robust system that clusters news into events, categorizes events into broad topics and summarizes multiple articles on each event. Here...

Improving the Coherence of Multi-document Summaries: a Corpus Study (2003)

For Modeling The, Ani Nenkova, Kathleen Mckeown

References included in multi-document summaries are often problematic. In this paper, we present a corpus study performed to derive statistical models for the syntactic realization of referential...

Evaluating Content Selection in Human- or Machine-Generated Summaries: The Pyramid Scoring Method (2003)

Rebecca J. Passonneau, Ani Nenkova

Content Units Previous work suggests that it is possible for humans to reliably annotate semantic units in text. For example, Halteren and Teufel [3] claim that factoid identi cation is more...

The Columbia Multi-Document Summarizer for DUC 2002 (2002)

Kathleen Mckeown David, David Evans, Ani Nenkova, Regina Barzilay, Vasileios Hatzivassiloglou, Barry Schiffman, ...

this paper was supported by the Defense Advanced Research Projects Agency under TIDES grant NUU01-00-1-8919. Any opinions, findings, or recommendations are those of the authors and do not necessarily...

Measuring importance and query relevance in topic-focused multi-document summarization (1996)

Surabhi Gupta, Ani Nenkova, Dan Jurafsky

The increasing complexity of summarization systems makes it difficult to analyze exactly which modules make a difference in performance. We carried out a principled comparison between the two most...