We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear.

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 such measures reflect the fact that summaries conveying different content can be equally good and informative? In this paper 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.

In this paper we present a novel feature enriched approach that learns to detect the conversation focus of threaded discussions by combining NLP analysis and IR techniques. Using the graph-based algorithm HITS, we integrate different features such as lexical similarity, poster trustworthiness, and speech act analysis of human conversations with feature oriented link generation functions. It is the first quantitative study to analyze human conversation focus in the context of online discussions that takes into account heterogeneous sources of evidence. Experimental results using a threaded discussion corpus from an undergraduate class show that it achieves significant performance improvements compared with the baseline system. 1

Being able to identify which rhetorical relations (e.g., contrast or explanation) hold between spans of text is important for many natural language processing applications. Using machine learning to obtain a classifier which can distinguish between different relations typically depends on the availability of manually labelled training data, which is very time-consuming to create. However, rhetorical relations are sometimes lexically marked, i.e., signalled by discourse markers (e.g., because, but, consequently etc.), and it has been suggested (Marcu and Echihabi, 2002) that the presence of these cues in some examples can be exploited to label them automatically with the corresponding relation. The discourse markers are then removed and the automatically labelled data are used to train a classifier to determine relations even when no discourse marker is present (based on other linguistic cues such as word co-occurrences). In this paper, we investigate empirically how feasible this approach is. In particular, we test whether automatically labelled, lexically marked examples are really suitable training material for classifiers that are then applied to unmarked examples. Our results suggest that training on this type of data may not be such a good strategy, as models trained in this way do not seem to generalise very well to unmarked data. Furthermore, we found some evidence that this behaviour is largely independent of the classifiers used and seems to lie in the data itself (e.g., marked and unmarked examples may be too dissimilar linguistically and removing unambiguous markers in the automatic labelling process may lead to a meaning shift in the examples). 1

Abstract not found

We describe a data-driven approach to building interpretable discourse structures for appointment scheduling dialogues. We represent discourse structures as headed trees and model them with probabilistic head-driven parsing techniques. We show that dialogue-based features regarding turn-taking and domain specific goals have a large positive impact on performance.

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like after, which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects. 1.

In this paper we consider the problem of identifying and classifying discourse coherence relations. We report initial results over the recently released Discourse GraphBank (Wolf and Gibson, 2005). Our approach considers, and determines the contributions of, a variety of syntactic and lexico-semantic features. We achieve 81% accuracy on the task of discourse relation type classification and 70 % accuracy on relation identification. 1

In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and small amounts of discourse annotations. We also demonstrate how discourse chunking can be successfully applied to a sentence compression task. 1

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”. We work with a corpus of implicit relations present in newspaper text and report results on a test set that is representative of the naturally occurring distribution of senses. We use several linguistically informed features, including polarity tags, Levin verb classes, length of verb phrases, modality, context, and lexical features. In addition, we revisit past approaches using lexical pairs from unannotated text as features, explain some of their shortcomings and propose modifications. Our best combination of features outperforms the baseline from data intensive approaches by 4% for comparison and 16 % for contingency. 1