Attitude or speech reports in English with a non-parenthetical syntax sometimes give rise to interpretations in which the embedded clause, e.g., "John was out of town" in the report "Jill said that John was out of town", seems to convey the main point of the utterance while the attribution predicate, e.g., "Jillsaid that", merely plays an evidential or source-providing role (Urmson, 1952). Simons (2007) posits that parenthetical readings arise from the interaction between the report and the preceding discourse context, rather than from the syntax or semantics of the reports involved. However, no account of these discourse interactions has been developed in formal semantics. Research on parenthetical reports within frameworks of rhetorical structure has yielded hypotheses about the discourse interactions of parenthetical reports, but these hypotheses are not semantically sound. The goal of this paper is to unify and extend work in semantics and discourse structure to develop a formal, discourse-based account of parenthetical reports that does not suffer the pitfalls faced by current proposals in rhetorical frameworks.

Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses. Recent studies on constrained Markov Bayesian polynomial (CMBP) framework take the first step towards bridging the gap between rule-based and statistical approaches for DST. In this paper, the gap is further bridged by a novel framework – recurrent polynomial network (RPN). RPN’s unique structure enables the framework to have all the advantages of CMBP including efficiency, portability and interpretability. Additionally, RPN achieves more properties of statistical approaches than CMBP. RPN was evaluated on the data corpora of the second and the third Dialog State Tracking Challenge (DSTC-2/3). Experiments showed that RPN can significantly outperform both traditional rule-based approaches and statistical approaches with similar feature set. Compared with the state-of-the-art statistical DST approaches with a lot richer features, RPN is also competitive.

One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges.

The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural language understanding modules. The state tracking task is primarily meant to support a dialog policy. From a probabilistic perspective, this is achieved by maintaining a posterior distribution over hidden dialog states composed of a set of context dependent variables. Once a dialog policy is learned, it strives to select an optimal dialog act given the estimated dialog state and a defined reward function. This paper introduces a novel method of dialog state tracking based on a bilinear algebric decomposition model that provides an efficient inference schema through collective matrix factorization. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset and we show that the proposed tracker gives encouraging results compared to the state-of-the-art trackers that participated in this standard benchmark. Finally, we show that the prediction schema is computationally efficient in comparison to the previous approaches.

In a spoken dialog system, dialog state tracking refers to the task of correctly inferring the state of the conversation – such as the user’s goal – given all of the dialog history up to that turn. Dialog state tracking is crucial to the success of a dialog system, yet until recently there were no common resources, hampering progress. The Dialog State Tracking Challenge series of 3 tasks introduced the first shared testbed and evaluation metrics for dialog state tracking, and has underpinned three key advances in dialog state tracking: the move from generative to discriminative models; the adoption of discriminative sequential techniques; and the incorporation of the speech recognition results directly into the dialog state tracker. This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled.

This short article introduces the Special Issue on Dialogue State Tracking.

Over the last decennia, annotating discourse coherence relations has gained increasing interest of the linguistics research community. Because of the complexity of coherence relations, there is no agreement on an annotation standard. Current annotation methods often lack a systematic order of coherence relations. In this article, we investigate the usability of the cognitive approach to coherence relations, developed by Sanders et al. (1992, 1993), for discourse annotation. The theory proposes a taxonomy of coherence relations in terms of four cognitive primitives. In this paper, we first develop a systematic, step-wise annotation process. The reliability of this annotation scheme is then tested in an annotation experiment with non-trained, non-expert annotators. An implicit and explicit version of the annotation instruction was created to determine whether the type of instruction influences the annotator agreement. The results show that two of the four primitives, polarity and order of the segments, can be applied reliably by non-trained annotators. The other two primitives, basic operation and source of coherence, are more problematic. Participants using the explicit instruction show higher agreement on the primitives than participants used the implicit instruction. These results are comparable to agreement statistics of other discourse corpora annotated by trained, expert annotators. Given that non-trained, non-expert annotators show similar amounts of agreement, these results indicate that the cognitive approach to coherence relations is a promising method for annotating discourse.

This paper describes the CASOAR corpus, the first manually annotated corpus that explores the impact of discourse structure on sentiment analysis with a study of movie reviews in French and in English as well as letters to the editor in French. While annotating opinions at the expression, the sentence or the document level is a well-established task and relatively straightforward, discourse annotation remains difficult, especially for non-experts. Therefore, combining both annotations poses several methodological problems that we address here. We propose a multi-layered annotation scheme that includes: the complete discourse structure according to the Segmented Discourse Representation Theory, the opinion orientation of elementary discourse units and opinion expressions, and their associated features. We detail each layer, explore the interactions between them and discuss our results. In particular, we examine the correlation between discourse and semantic category of opinion expressions, the impact of discourse relations on both subjectivity and polarity analysis and the impact of discourse on the determination of the overall opinion of a document. Our results demonstrate that discourse is an important cue for sentiment analysis, at least for the corpus genres we have studied.