The Universal Dependencies (UD) project has created an invaluable collection of treebanks with contributions in over 140 languages. However, the UD annotations do not tell the full story. Grammatical constructions that convey meaning through a particular combination of several morphosyntactic elements -- for example, interrogative sentences with special markers and/or word orders -- are not labeled holistically. We argue for (i) augmenting UD annotations with a 'UCxn' annotation layer for such meaning-bearing grammatical constructions, and (ii) approaching this in a typologically informed way so that morphosyntactic strategies can be compared across languages. As a case study, we consider five construction families in ten languages, identifying instances of each construction in UD treebanks through the use of morphosyntactic patterns. In addition to findings regarding these particular constructions, our study yields important insights on methodology for describing and identifying constructions in language-general and language-particular ways, and lays the foundation for future constructional enrichment of UD treebanks.
Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention spans in the OntoNotes benchmark. This paper addresses this limitation by combining predicted mentions from existing nested NER systems and features derived from OntoNotes syntax trees. With this approach, we create a near approximation of the OntoNotes dataset with all singleton mentions, achieving ~94% recall on a sample of gold singletons. We then propose a two-step neural mention and coreference resolution system, named SPLICE, and compare its performance to the end-to-end approach in two scenarios: the OntoNotes test set and the out-of-domain (OOD) OntoGUM corpus. Results indicate that reconstructed singleton training yields results comparable to end-to-end systems for OntoNotes, while improving OOD stability (+1.1 avg. F1). We conduct error analysis for mention detection and delve into its impact on coreference clustering, revealing that precision improvements deliver more substantial benefits than increases in recall for resolving coreference chains.
In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Structure Theory (RST). The framework encompasses discourse relation graphs with tree-breaking, nonprojective and concurrent relations, as well as implicit and explicit signals which give explainable rationales to our analyses. We survey shortcomings of RST and other existing frameworks, such as Segmented Discourse Representation Theory (SDRT), the Penn Discourse Treebank (PDTB) and Discourse Dependencies, and address these using constructs in the proposed theory. We provide annotation, search and visualization tools for data, and present and evaluate a freely available corpus of English annotated according to our framework, encompassing 12 spoken and written genres with over 200K tokens. Finally, we discuss automatic parsing, evaluation metrics and applications for data in our framework.
As NLP models become increasingly capable of understanding documents in terms of coherent entities rather than strings, obtaining the most salient entities for each document is not only an important end task in itself but also vital for Information Retrieval (IR) and other downstream applications such as controllable summarization. In this paper, we present and evaluate GUMsley, the first entity salience dataset covering all named and non-named salient entities for 12 genres of English text, aligned with entity types, Wikification links and full coreference resolution annotations. We promote a strict definition of salience using human summaries and demonstrate high inter-annotator agreement for salience based on whether a source entity is mentioned in the summary. Our evaluation shows poor performance by pre-trained SOTA summarization models and zero-shot LLM prompting in capturing salient entities in generated summaries. We also show that predicting or providing salient entities to several model architectures enhances performance and helps derive higher-quality summaries by alleviating the entity hallucination problem in existing abstractive summarization.
Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a coreference model that learns singletons as well as features such as entity type and information status via a multi-task learning-based approach. This approach achieves new state-of-the-art scores on the OntoGUM benchmark (+2.7 points) and increases robustness on multiple out-of-domain datasets (+2.3 points on average), likely due to greater generalizability for mention detection and utilization of more data from singletons when compared to only coreferent mention pair matching.
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited. In this paper, we examine and model some of the factors associated with parsing difficulties in previous work: the existence of implicit discourse relations, challenges in identifying long-distance relations, out-of-vocabulary items, and more. In order to assess the relative importance of these variables, we also release two annotated English test-sets with explicit correct and distracting discourse markers associated with gold standard RST relations. Our results show that as in shallow discourse parsing, the explicit/implicit distinction plays a role, but that long-distance dependencies are the main challenge, while lack of lexical overlap is less of a problem, at least for in-domain parsing. Our final model is able to predict where errors will occur with an accuracy of 76.3% for the bottom-up parser and 76.6% for the top-down parser.
Automatic summarization with pre-trained language models has led to impressively fluent results, but is prone to 'hallucinations', low performance on non-news genres, and outputs which are not exactly summaries. Targeting ACL 2023's 'Reality Check' theme, we present GUMSum, a small but carefully crafted dataset of English summaries in 12 written and spoken genres for evaluation of abstractive summarization. Summaries are highly constrained, focusing on substitutive potential, factuality, and faithfulness. We present guidelines and evaluate human agreement as well as subjective judgments on recent system outputs, comparing general-domain untuned approaches, a fine-tuned one, and a prompt-based approach, to human performance. Results show that while GPT3 achieves impressive scores, it still underperforms humans, with varying quality across genres. Human judgments reveal different types of errors in supervised, prompted, and human-generated summaries, shedding light on the challenges of producing a good summary.
We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of domain evaluation: dictionary entries, esports commentaries, legal documents, medical notes, poetry, mathematical proofs, syllabuses, and threat letters. GENTLE is manually annotated for a variety of popular NLP tasks, including syntactic dependency parsing, entity recognition, coreference resolution, and discourse parsing. We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE's utility as an evaluation dataset for NLP systems.
Recent advances in discourse parsing performance create the impression that, as in other NLP tasks, performance for high-resource languages such as English is finally becoming reliable. In this paper we demonstrate that this is not the case, and thoroughly investigate the impact of data diversity on RST parsing stability. We show that state-of-the-art architectures trained on the standard English newswire benchmark do not generalize well, even within the news domain. Using the two largest RST corpora of English with text from multiple genres, we quantify the impact of genre diversity in training data for achieving generalization to text types unseen during training. Our results show that a heterogeneous training regime is critical for stable and generalizable models, across parser architectures. We also provide error analyses of model outputs and out-of-domain performance. To our knowledge, this study is the first to fully evaluate cross-corpus RST parsing generalizability on complete trees, examine between-genre degradation within an RST corpus, and investigate the impact of genre diversity in training data composition.
Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies project raise the expectation that joint training and dataset comparison is increasingly possible for high-resource languages such as English, which have multiple corpora. Focusing on the two largest UD English treebanks, we examine progress in data consolidation and answer several questions: Are UD English treebanks becoming more internally consistent? Are they becoming more like each other and to what extent? Is joint training a good idea, and if so, since which UD version? Our results indicate that while consolidation has made progress, joint models may still suffer from inconsistencies, which hamper their ability to leverage a larger pool of training data.