Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special discourse tokens. The obtained results demonstrate that incorporating discourse tokens into training sequences is sufficient to significantly improve dialogue consistency and overall generation quality. The suggested approach performs well, including for automatically annotated data. Apart from that, it is observed that increasing the weight of the discourse planning task in the loss function accelerates learning convergence.

The rate of scientific publications is increasing exponentially, necessitating a significant investment of time in order to read and comprehend the most important articles. While ancillary services exist to facilitate this process, they are typically closed-model and paid services or have limited capabilities. In this paper, we present PaperPersiChat, an open chatbot-system designed for the discussion of scientific papers. This system supports summarization and question-answering modes within a single end-to-end chatbot pipeline, which is guided by discourse analysis. To expedite the development of similar systems, we also release the gathered dataset, which has no publicly available analogues.

Recent transformer-based approaches to NLG like GPT-2 can generate syntactically coherent original texts. However, these generated texts have serious flaws: global discourse incoherence and meaninglessness of sentences in terms of entity values. We address both of these flaws: they are independent but can be combined to generate original texts that will be both consistent and truthful. This paper presents an approach to estimate the quality of discourse structure. Empirical results confirm that the discourse structure of currently generated texts is inaccurate. We propose the research directions to correct it using discourse features during the fine-tuning procedure. The suggested approach is universal and can be applied to different languages. Apart from that, we suggest a method to correct wrong entity values based on Web Mining and text alignment.

In this paper, the utility and advantages of the discourse analysis for text pairs categorization and ranking are investigated. We consider two tasks in which discourse structure seems useful and important: automatic verification of political statements, and ranking in question answering systems. We propose a neural network based approach to learn the match between pairs of discourse tree structures. To this end, the neural TreeLSTM model is modified to effectively encode discourse trees and DSNDM model based on it is suggested to analyze pairs of texts. In addition, the integration of the attention mechanism in the model is proposed. Moreover, different ranking approaches are investigated for the second task. In the paper, the comparison with state-of-the-art methods is given. Experiments illustrate that combination of neural networks and discourse structure in DSNDM is effective since it reaches top results in the assigned tasks. The evaluation also demonstrates that discourse analysis improves quality for the processing of longer texts.