This paper considers the problem of automatic assessment of local coherence. We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text. We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function. Our experiments demonstrate that the induced model achieves significantly higher accuracy than a state-of-the-art coherence model. 1

NOTE TO READERS: We have recently detected a software bug which affects the results of our standalone entity grid experiments. (The bug was in our syntactic analysis code, which incorrectly failed to label the second object of a conjoint VP; in the phrase “wash the dishes and clean the sink”, ‘dishes ’ would be correctly labeled as O but ‘sink ’ mislabeled as X.) This bug happened to have an unfortunate interaction with the ”This is preliminary information ” preamble mentioned in section 5. The results in table 2 above the line are incorrect; our relaxed entity grid does not outperform the naive grid on the discriminative test. This implies that our argument motivating the relaxed model at the end of section 2 is misguided. The design and performance of the joint model is unaffected. We present a model for discourse coherence which combines the local entitybased approach of (Barzilay and Lapata, 2005) and the HMM-based content model

This paper investigates whether the model of local rhetorical coherence suggested in Knott et al. (2001) can boost the performance of the Centering-based metrics of entity coherence employed by Karamanis et al. (2004) for the task of information ordering. Rhetorical coherence is integrated into the way Centering’s basic data structures are derived from the annotated features of the GNOME corpus. The results indicate that (a) the simplest metric continues to perform better than its competitors even when local rhetorical coherence is taken into account, and (b) this extra coherence constraint decreases its performance. Keywords: Information Ordering, Centering Theory, Rhetorical Coherence. 1.

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document topics. We propose a global model in which both topic selection and ordering are biased to be similar across a collection of related documents. We show that this space of orderings can be effectively represented using a distribution over permutations called the Generalized Mallows Model. We apply our method to three complementary discourse-level tasks: cross-document alignment, document segmentation, and information ordering. Our experiments show that incorporating our permutation-based model in these applications yields substantial improvements in performance over previously proposed methods. 1 1.

In this paper we discuss several metrics of coherence defined using Centering Theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional Centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems. 1.

Recent work on the problem of detecting synonymy through corpus analysis has used the Test of English as a Foreign Language (TOEFL) as a benchmark. However, this test involves as few as 80 questions, prompting questions regarding the statistical significance of reported results.

When reading a thesis, do you expect the first sentence to motivate the research or to involve a complex statistical process? When writing a news article, should the first sentence be an expert’s commentary on the situation or a general introduction to the event? Although intuitively the answer

Making global decisions in which several local interdependent decisions play a role. Informally: � Everything that has to do with constraints (and learning models) Issues to attend to: Formally: � While we formulate the problem as an ILP problem, Inference � We typically can be make done decisions multiple based ways on models such as: � Search; sampling; dynamic programming; SAT; ILP Argmax y w T φ(x,y) � CCMs (specifically, ILP formulations) make decisions based on models such as: Argmaxy wT � The focus is on joint global inference � Learning may or may not φ(x,y) be joint. + � c ∈ C ρc d(y, 1C) � We do �not Decomposing define the learning models method, is often beneficial but we’ll discuss it and make suggestions CCMs make predictions in the presence of /guided by constraints

This paper describes and analyzes how the FEMsum system deals with DUC 2007 tasks of providing summary-length answers to complex questions, both background and just-the-news summaries. We participated in producing background summaries for the main task with the FEMsum approach that obtained better results in our last year participation. The FEMsum semantic based approach was adapted to deal with the update pilot task with the aim of producing just-the-news summaries. 1

Identifying entailment relations between predicates is an important part of applied semantic inference. In this article we propose a global inference algorithm that learns such entailment rules. First, we define a graph structure over predicates that represents entailment relations as directed edges. Then, we use a global transitivity constraint on the graph to learn the optimal set of edges, formulating the optimization problem as an Integer Linear Program. The algorithm is applied in a setting where, given a target concept, the algorithm learns on the fly all entailment rules between predicates that co-occur with this concept. Results show that our global algorithm improves performance over baseline algorithms by more than 10%. 1.