Ernie Chang, Yang Li, Patrick Huber, Vish Vogeti, David Kant, Yangyang Shi, Vikas Chandra. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Zekun Li, Zhiyu Zoey Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Luna Dong, Adithya Sagar, Xifeng Yan, Paul A. Crook. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Vered Shwartz, Arash Einolghozati. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

The already highly complex Urban Transit Routing Problem (UTRP) that serves to find efficient travelling routes for Public Transport (PT) systems is extended into the Heterogeneous Electric – Urban Transit Routing Problem (HE-UTRP). This extension focuses on step-by-step transformation of public bus transportation systems to electric mobility. The heterogeneity characteristics refers to the fleet and charging infrastructure. This article presents a framework that allows the generation, analysis and optimisation of PT Route Networks (RNs) for the HE-UTRP. In addition to the analysis of different charging technologies and Charging Locations (CLs), the approach enables a transformation process towards electrification of PT systems by presenting substitution scenarios as well as the resulting cost structure. The framework, based on a Sequence-based Selection Hyper-heuristic – with Great Deluge (SS-GD), is tested against varying objective functions and UTRP, HE-UTRP and Electric Transit Route Network Design Problem (E-TRNDP) instances.

With a growing number of BERTology works analyzing different components of pre-trained language models, we extend this line of research through an in-depth analysis of discourse information in pre-trained and finetuned language models.We move beyond prior work along three dimensions: First, we describe a novel approach to infer discourse structures from arbitrarily long documents.Second, we propose a new type of analysis to explore where and how accurately intrinsic discourse is captured in the BERT and BART models.Finally, we assess how similar the generated structures are to a variety of baselines as well as their distributions within and between models.

Patrick Huber, Wen Xiao, Giuseppe Carenini. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Previous work indicates that discourse information benefits summarization.In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summarizers.In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model.Experiments across models and datasets reveal that the summarizer learns both, dependency-and constituencystyle discourse information, which is typically encoded in a single head, covering long-and short-distance discourse dependencies.Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain 1 .

RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining.In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models.Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT.We further demonstrate that pretraining our parser on the recently available large-scale "silver-standard" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis.

Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures.To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis.More specifically, we are combining the largescale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model.Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data.We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.

The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RSTstyle discourse parsing.In this work, we present a novel scalable methodology to automatically generate discourse treebanks using distant supervision from sentiment-annotated datasets, creating and publishing MEGA-DT, a new large-scale discourse-annotated corpus.Our approach generates discourse trees incorporating structure and nuclearity for documents of arbitrary length by relying on an efficient heuristic beam-search strategy, extended with a stochastic component.Experiments on multiple datasets indicate that a discourse parser trained on our MEGA-DT treebank delivers promising inter-domain performance gains when compared to parsers trained on human-annotated discourse corpora.

Patrick Huber, Giuseppe Carenini. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.