This paper describes a corpus of situated multiparty chats developed for the STAC project (Strategic Conversation, ERC grant n. 269427). and annotated for discourse structure in the style of Segmented Discourse Representation Theory (SDRT; Asher & Lascarides,2003).  The STAC corpus is not only a rich source of data on strategic conversation, but also the first corpus that we are aware of that provides discourse structures for multiparty dialogues situated within a virtual environment.  The corpus was annotated in two stages: we initially annotated the chat moves only, but later decided to annotate interactions between the chat moves and non-linguistic events from the virtual environment. This two-step procedure  has allowed us quantify various ways in which adding information from the nonlinguistic context affects dialogue structure.  In this paper, we  look at how annotations based only on linguistic information were preserved once the nonlinguistic context was factored in.  We explain that while the preservation of relation instances is relatively high when we move from one corpus to the other, there is little preservation of higher order structures that capture "the main point" of a dialogue and distinguish it from peripheral information.

This paper investigates the advantages and limits of data programming for the task of learning discourse structure. The data programming paradigm implemented in the Snorkel framework allows a user to label training data using expert-composed heuristics, which are then transformed via the "generative step" into probability distributions of the class labels given the training candidates. These results are later generalized using a discriminative model. Snorkel's attractive promise to create a large amount of annotated data from a smaller set of training data by unifying the output of a set of heuristics has yet to be used for computationally difficult tasks, such as that of discourse attachment, in which one must decide where a given discourse unit attaches to other units in a text in order to form a coherent discourse structure. Although approaching this problem using Snorkel requires significant modifications to the structure of the heuristics, we show that weak supervision methods can be more than competitive with classical supervised learning approaches to the attachment problem.

This paper provides a detailed comparison of a data programming approach with (i) off-the-shelf, state-of-the-art deep learning architectures that optimize their representations (BERT) and (ii) handcrafted-feature approaches previously used in the discourse analysis literature. We compare these approaches on the task of learning discourse structure for multi-party dialogue. The data programming paradigm offered by the Snorkel framework allows a user to label training data using expert-composed heuristics, which are then transformed via the "generative step" into probability distributions of the class labels given the data. We show that on our task the generative model outperforms both deep learning architectures as well as more traditional ML approaches when learning discourse structure-it even outperforms the combination of deep learning methods and handcrafted features. We also implement several strategies for "decoding" our generative model output in order to improve our results. We conclude that weak supervision methods hold great promise as a means for creating and improving data sets for discourse structure.

No abstract

No abstract