Nenkova, Ani
Loading...
Email Address
ORCID
Disciplines
Research Projects
Organizational Units
Position
Faculty Member
Introduction
Research Interests
Search Results
Now showing 1 - 10 of 23
Publication Predicting the Fluency of Text with Shallow Structural Features: Case Studies of Machine Tanslation and Human-Written Text(2009-03-01) Chae, Jieun; Nenkova, AniSentence fluency is an important component of overall text readability but few studies in natural language processing have sought to understand the factors that define it. We report the results of an initial study into the predictive power of surface syntactic statistics for the task; we use fluency assessments done for the purpose of evaluating machine translation. We find that these features are weakly but significantly correlated with fluency. Machine and human translations can be distinguished with accuracy over 80%. The performance of pairwise comparison of fluency is also very high—over 90% for a multi-layer perceptron classifier. We also test the hypothesis that the learned models capture general fluency properties applicable to human-written text. The results do not support this hypothesis: prediction accuracy on the new data is only 57%. This finding suggests that developing a dedicated, task-independent corpus of fluency judgments will be beneficial for further investigations of the problem.Publication Automatically Evaluating Content Selection in Summarization Without Human Models(2009-08-01) Louis, Annie; Nenkova, AniWe present a fully automatic method for content selection evaluation in summarization that does not require the creation of human model summaries. Our work capitalizes on the assumption that the distribution of words in the input and an informative summary of that input should be similar to each other. Results on a large scale evaluation from the Text Analysis Conference show that input-summary comparisons are very effective for the evaluation of content selection. Our automatic methods rank participating systems similarly to manual model-based pyramid evaluation and to manual human judgments of responsiveness. The best feature, Jensen- Shannon divergence, leads to a correlation as high as 0.88 with manual pyramid and 0.73 with responsiveness evaluations.Publication The Pyramid Method: Incorporating Human Content Selection Variation in Summarization Evaluation(2007-04-19) Nenkova, Ani; Passonneau, Rebecca; McKeown, KathleenHuman 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 such measures reflect the fact that summaries conveying different content can be equally good and informative? In this article, we address these very questions by proposing a method for analysis of multiple human abstracts into semantic content units. Such analysis allows us not only to quantify human variation in content selection, but also to assign empirical importance weight to different content units. It serves as the basis for an evaluation method, the Pyramid Method, that incorporates the observed variation and is predictive of different equally informative summaries. We discuss the reliability of content unit annotation, the properties of Pyramid scores, and their correlation with other evaluation methods.Publication Measuring Importance and Query Relevance in Toopic-Focused Multi-Document Summarization(2007-06-01) Gupta, Surabhi; Nenkova, Ani; Jurafsky, DanThe 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 commonly used schemes for assigning importance to words in the context of query focused multi-document summarization: raw frequency (word probability) and log-likelihood ratio. We demonstrate that the advantages of log-likelihood ratio come from its known distributional properties which allow for the identification of a set of words that in its entirety defines the aboutness of the input. We also find that LLR is more suitable for query-focused summarization since, unlike raw frequency, it is more sensitive to the integration of the information need defined by the user.Publication High Frequency Word Entertainment in Spoken Dialogue(2008-06-01) Nenkova, Ani; Gravano, Agustin; Hirschberg, JuliaCognitive 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 comprehension in dialogue. In this paper we examine novel types of entrainment in two corpora—Switchboard and the Columbia Games corpus. We examine entrainment in use of high-frequency words (the most common words in the corpus), and its association with dialogue naturalness and flow, as well as with task success. Our results show that such entrainment is predictive of the perceived naturalness of dialogues and is significantly correlated with task success; in overall interaction flow, higher degrees of entrainment are associated with more overlaps and fewer interruptions.Publication Automatic Evaluation of Linguistic Quality in Multi-Document Summarization(2010-07-01) Pitler, Emily; Louis, Annie; Nenkova, AniTo date, few attempts have been made to develop and validate methods for automatic evaluation of linguistic quality in text summarization. We present the first systematic assessment of several diverse classes of metrics designed to capture various aspects of well-written text. We train and test linguistic quality models on consecutive years of NIST evaluation data in order to show the generality of results. For grammaticality, the best results come from a set of syntactic features. Focus, coherence and referential clarity are best evaluated by a class of features measuring local coherence on the basis of cosine similarity between sentences, coreference information, and summarization specific features. Our best results are 90% accuracy for pairwise comparisons of competing systems over a test set of several inputs and 70% for ranking summaries of a specific input.Publication Entity-Driven Rewrite for Multi-Document Summarization(2008-01-01) Nenkova, AniIn 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 the summary in comparison to an extractive summary produced using the same underlying approach, showing the promise the technique has to offer. In addition, summaries produced using entity-driven rewrite have higher linguistic quality than a comparison non-extractive system. Some improvement is also seen in content selection over extractive summarization as measured by pyramid method evaluation.Publication Discourse Indicators for Content Selection in Summaization(2010-09-01) Joshi, Aravind K; Louis, Annie; Nenkova, AniWe present analyses aimed at eliciting which specific aspects of discourse provide the strongest indication for text importance. In the context of content selection for single document summarization of news, we examine the benefits of both the graph structure of text provided by discourse relations and the semantic sense of these relations. We find that structure information is the most robust indicator of importance. Semantic sense only provides constraints on content selection but is not indicative of important content by itself. However, sense features complement structure information and lead to improved performance. Further, both types of discourse information prove complementary to non-discourse features. While our results establish the usefulness of discourse features, we also find that lexical overlap provides a simple and cheap alternative to discourse for computing text structure with comparable performance for the task of content selection.Publication Automatic Summarization(2011-06-01) Nenkova, Ani; McKeown, KathleenIt has now been 50 years since the publication of Luhn’s seminal paper on automatic summarization. During these years the practical need for automatic summarization has become increasingly urgent and numerous papers have been published on the topic. As a result, it has become harder to find a single reference that gives an overview of past efforts or a complete view of summarization tasks and necessary system components. This article attempts to fill this void by providing a comprehensive overview of research in summarization, including the more traditional efforts in sentence extraction as well as the most novel recent approaches for determining important content, for domain and genre specific summarization and for evaluation of summarization. We also discuss the challenges that remain open, in particular the need for language generation and deeper semantic understanding of language that would be necessary for future advances in the field.Publication Structural Features for Predicting the Linguistic Quality of Text: Applications to Machine Translation, Automatic Summarization and Human-Authored Text(2010-01-01) Nenkova, Ani; Chae, Jieun; Louis, Annie; Pitler, EmilySentence structure is considered to be an important component of the overall linguistic quality of text. Yet few empirical studies have sought to characterize how and to what extent structural features determine fluency and linguistic quality. We report the results of experiments on the predictive power of syntactic phrasing statistics and other structural features for these aspects of text. Manual assessments of sentence fluency for machine translation evaluation and text quality for summarization evaluation are used as gold-standard. We find that many structural features related to phrase length are weakly but significantly correlated with fluency and classifiers based on the entire suite of structural features can achieve high accuracy in pairwise comparison of sentence fluency and in distinguishing machine translations from human translations. We also test the hypothesis that the learned models capture general fluency properties applicable to human-authored text. The results from our experiments do not support the hypothesis. At the same time structural features and models based on them prove to be robust for automatic evaluation of the linguistic quality of multi-document summaries.