Applications that store a large number of documents often have summarization and retrieval functionalities to help users digest large amounts of information efficiently. Currently, such systems need to run two task-specific models, for summarization and retrieval, redundantly on the same set of documents. An efficient approach to amend this redundancy would be to reuse hidden representations produced during the summary generation for retrieval. However, our experiment shows that existing models, including recent large language models, do not produce retrieval-friendly embeddings during summarization due to a lack of a contrastive objective during their training. To this end, we introduce a simple, cost-effective training strategy which integrates a contrastive objective into standard summarization training without requiring additional annotations. We empirically show that our model can perform on par or even outperform in some cases compared to the combination of two task-specific models while improving throughput and FLOPs by up to 17% and 20%, respectively.

We present GenGO, a system for exploring papers published in ACL conferences. Paper data stored in our database is enriched with multi-aspect summaries, extracted named entities, a field of study label, and text embeddings by our data processing pipeline. These metadata are used in our web-based user interface to enable researchers to quickly find papers relevant to their interests, and grasp an overview of papers without reading full-text of papers. To make GenGO to be available online as long as possible, we design GenGO to be simple and efficient to reduce maintenance and financial costs. In addition, the modularity of our data processing pipeline lets developers easily extend it to add new features. We make our code available to foster open development and transparency: https://gengo.sotaro.io.

Extensive efforts in the past have been directed toward the development of summarization datasets. However, a predominant number of these resources have been (semi)-automatically generated, typically through web data crawling. This resulted in subpar resources for training and evaluating summarization systems, a quality compromise that is arguably due to the substantial costs associated with generating ground-truth summaries, particularly for diverse languages and specialized domains. To address this issue, we present ACLSum, a novel summarization dataset carefully crafted and evaluated by domain experts. In contrast to previous datasets, ACLSum facilitates multi-aspect summarization of scientific papers, covering challenges, approaches, and outcomes in depth. Through extensive experiments, we evaluate the quality of our resource and the performance of models based on pretrained language models (PLMs) and state-of-the-art large language models (LLMs). Additionally, we explore the effectiveness of extract-then-abstract versus abstractive end-to-end summarization within the scholarly domain on the basis of automatically discovered aspects. While the former performs comparably well to the end-to-end approach with pretrained language models regardless of the potential error propagation issue, the prompting-based approach with LLMs shows a limitation in extracting sentences from source documents.

Keywords, that is, content-relevant words in summaries play an important role in efficient information conveyance, making it critical to assess if system-generated summaries contain such informative words during evaluation. However, existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. To address this issue, we present a keyword-oriented evaluation metric, dubbed ROUGE-K, which provides a quantitative answer to the question of – How well do summaries include keywords? Through the lens of this keyword-aware metric, we surprisingly find that a current strong baseline model often misses essential information in their summaries. Our analysis reveals that human annotators indeed find the summaries with more keywords to be more relevant to the source documents. This is an important yet previously overlooked aspect in evaluating summarization systems. Finally, to enhance keyword inclusion, we propose four approaches for incorporating word importance into a transformer-based model and experimentally show that it enables guiding models to include more keywords while keeping the overall quality.

In this paper, we provide an overview of the SV-Ident shared task as part of the 3rd Workshop on Scholarly Document Processing (SDP) at COLING 2022. In the shared task, participants were provided with a sentence and a vocabulary of variables, and asked to identify which variables, if any, are mentioned in individual sentences from scholarly documents in full text. Two teams made a total of 9 submissions to the shared task leaderboard. While none of the teams improve on the baseline systems, we still draw insights from their submissions. Furthermore, we provide a detailed evaluation. Data and baselines for our shared task are freely available at https://github.com/vadis-project/sv-ident.