The availability of a vast array of research papers in any area of study, necessitates the need of automated summarisation systems that can present the key research conducted and their corresponding findings. Scientific paper summarisation is a challenging task for various reasons including token length limits in modern transformer models and corresponding memory and compute requirements for long text. A significant amount of work has been conducted in this area, with approaches that modify the attention mechanisms of existing transformer models and others that utilise discourse information to capture long range dependencies in research papers. In this paper, we propose a hybrid methodology for research paper summarisation which incorporates an extractive and abstractive approach. We use the extractive approach to capture the key findings of research, and pair it with the introduction of the paper which captures the motivation for research. We use two models based on unsupervised learning for the extraction stage and two transformer language models, resulting in four combinations for our hybrid approach. The performances of the models are evaluated on three metrics and we present our findings in this paper. We find that using certain combinations of hyper parameters, it is possible for automated summarisation systems to exceed the abstractiveness of summaries written by humans. Finally, we state our future scope of research in extending this methodology to summarisation of generalised long documents.

Natural Language Inference (NLI) tasks involving temporal inference remain challenging for pre-trained language models (LMs). Although various datasets have been created for this task, they primarily focus on English and do not address the need for resources in other languages. It is unclear whether current LMs realize the generalization capacity for temporal inference across languages. In this paper, we present Jamp, a Japanese NLI benchmark focused on temporal inference. Our dataset includes a range of temporal inference patterns, which enables us to conduct fine-grained analysis. To begin the data annotation process, we create diverse inference templates based on the formal semantics test suites. We then automatically generate diverse NLI examples by using the Japanese case frame dictionary and well-designed templates while controlling the distribution of inference patterns and gold labels. We evaluate the generalization capacities of monolingual/multilingual LMs by splitting our dataset based on tense fragments (i.e., temporal inference patterns). Our findings demonstrate that LMs struggle with specific linguistic phenomena, such as habituality, indicating that there is potential for the development of more effective NLI models across languages.

In researc which lan uac; assumed knowled way it use of provide impreci recent h into a is to e. In that on re of th is used the cons s, to na se acous years, utomati (r,et a nost e need e lan u (pragma traints ke sens tic sit there has c speech u computer of this s to pro are (its s tics). It and expec e of the i nal that i been a nderstan to und recent a vide th yntax an will th tations nherentl s human rroat increase in dine, the purpose of erstand the spoken ctivity, it has been e computer with a d semantics) and the en be able to make which this knowledfre y vaf ue, sloppy and soeech. Syntactic constraints and expectations are based on the patterns formed by a Riven set of linguistic objects, e. .