We present a quantitative and qualitative comparison of the discourse trees defined by the Rhetorical Structure Theory and Questions under Discussion models. Based on an empirical analysis of parallel annotations for 28 texts (blog posts and podcast transcripts), we conclude that both discourse frameworks capture similar structural information. The qualitative analysis shows that while complex discourse units often match between analyses, QUD structures do not indicate the centrality of segments.

This paper describes the approach of team Kit Kittredge to SemEval-2019 Task 4: Hyperpartisan News Detection. The goal was binary classification of news articles into the categories of “biased” or “unbiased”. We had two software submissions: one a simple bag-of-words model, and the second an LSTM (Long Short Term Memory) neural network, which was trained on a subset of the original dataset selected by a voting system of other LSTMs. This method did not prove much more successful than the baseline, however, due to the models’ tendency to learn publisher-specific traits instead of general bias.

Questions are an integral part of discourse. They provide structure and support the exchange of information. One linguistic theory, the Questions Under Discussion model, takes question structures as integral to the functioning of a coherent discourse. This theory has not been tested on the count of its validity for predicting observations in real dialogue data, however. In this submission, a system for ranking explicit and implicit questions by their appropriateness in a dialogue is presented. This system implements constraints and principles put forward in the linguistic literature.

We introduce our pilot study applying PDTB-style annotation to Twitter conversations. Lexically grounded coherence annotation for Twitter threads will enable detailed investigations of the discourse structure of conversations on social media. Here, we present our corpus of 185 threads and annotation, including an inter-annotator agreement study. We discuss our observations as to how Twitter discourses differ from written news text wrt. discourse connectives and relations. We confirm our hypothesis that discourse relations in written social media conversations are expressed differently than in (news) text. We find that in Twitter, connective arguments frequently are not full syntactic clauses, and that a few general connectives expressing EXPANSION and CONTINGENCY make up the majority of the explicit relations in our data.

Learned dynamic weighting of the conditioning signal (attention) has been shown to improve neural language generation in a variety of settings. The weights applied when generating a particular output sequence have also been viewed as providing a potentially explanatory insight in the internal workings of the generator. In this paper, we reverse the direction of this connection and ask whether through the control of the attention of the model we can control its output. Specifically, we take a standard neural image captioning model that uses attention, and fix the attention to predetermined areas in the image. We evaluate whether the resulting output is more likely to mention the class of the object in that area than the normally generated caption. We introduce three effective methods to control the attention and find that these are producing expected results in up to 27.43% of the cases.

We present a corpus study of pronominal anaphora on Twitter conversations. After outlining the specific features of this genre, with respect to reference resolution, we explain the construction of our corpus and the annotation steps. From this we derive a list of phenomena that need to be considered when performing anaphora resolution on this type of data. Finally, we test the performance of an off-the-shelf resolution system, and provide some qualitative error analysis.

We present a new lexicon of English discourse connectives called DiMLex-Eng, built by merging information from two annotated corpora and an additional list of relation signals from the literature. The format follows the German connective lexicon DiMLex, which provides a cross-linguistically applicable XML schema. DiMLex-Eng contains 149 English connectives, and gives information on syntactic categories, discourse semantics and non-connective uses (if any). We report on the development steps and discuss design decisions encountered in the lexicon expansion phase. The resource is freely available for use in studies of discourse structure and computational applications.

DiMLex is a lexicon of German connectives that can be used for various language understanding purposes. We enhanced the coverage to 275 connectives, which we regard as covering all known German discourse connectives in current use. In this paper, we consider the task of adding the semantic relations that can be expressed by each connective. After discussing different approaches to retrieving semantic information, we settle on annotating each connective with senses from the new PDTB 3.0 sense hierarchy. We describe our new implementation in the extended DiMLex, which will be available for research purposes.

We present a new corpus of German tweets. Due to the relatively small number of German messages on Twitter, it is possible to collect a virtually complete snapshot of German twitter messages over a period of time. In this paper, we present our collection method which produced a 24 million tweet corpus, representing a large majority of all German tweets sent in April, 2013. Further, we analyze this representative data set and characterize the German twitterverse. While German Twitter data is similar to other Twitter data in terms of its temporal distribution, German Twitter users are much more reluctant to share geolocation information with their tweets. Finally, the corpus collection method allows for a study of discourse phenomena in the Twitter data, structured into discussion threads.