The CL-SciSumm Shared Task 2018: Results and Key Insights

2017

The number of publications is rapidly growing and it is essential to enable fast access and analysis of relevant articles. In this paper, we describe a set of methods based on measuring semantic textual similarity, which we use to semantically analyze and summarize publications through other publications that cite them. We report the performance of our approach in the context of the third CL-SciSumm shared task and show that our system performs favorably to competing systems in terms of produced summaries.

2020

Related work sections or literature reviews are an essential part of every scientific article being crucial for paper reviewing and assessment. The automatic generation of related work sections can be considered an instance of the multi-document summarization problem. In order to allow the study of this specific problem, we have developed a manually annotated, machine readable data-set of related work sections, cited papers (e.g. references) and sentences, together with an additional layer of papers citing the references. We additionally present experiments on the identification of cited sentences, using as input citation contexts. The corpus alongside the gold standard are made available for use by the scientific community.

2017

This paper describes our approach on ”Recognizing Reference Spans,Classifying Their Discourse Facets and Summarizing from Reference Text” as an attempt in the shared task on relationship mining and scientific summarization of computational linguistics research papers at SIGIR 2017.

2014

The Computational Linguistics (CL) Summarization Pilot Task was created to encourage a community effort to address the research problem of summarizing research articles as “faceted summaries” in the domain of computational linguistics. In this pilot stage, a handannotated set of citing papers was provided for ten reference papers to help in automating the citation span and discourse facet identification problems. This paper details the corpus construction efforts by the organizers and the participating teams, who also participated in the task-based evaluation. The annotated development corpus used for this pilot task is publicly available at: https://github.com/WING-

2021

Most earlier work on text summarization is carried out on news article datasets. The summary in these datasets is naturally located at the beginning of the text. Hence, a model can spuriously utilize this correlation for summary generation instead of truly learning to summarize. To address this issue, we constructed a new dataset, SUMPUBMED, using scientific articles from the PubMed archive. We conducted a human analysis of summary coverage, redundancy, readability, coherence, and informativeness on SUMPUBMED. SUMPUBMED is challenging because (a) the summary is distributed throughout the text (not-localized on top), and (b) it contains rare domain-specific scientific terms. We observe that seq2seq models that adequately summarize news articles struggle to summarize SUMPUBMED. Thus, SUMPUBMED opens new avenues for the future improvement of models as well as the development of new evaluation metrics.

2013

Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.

International Journal on Digital Libraries, 2017

Your article is protected by copyright and all rights are held exclusively by Springer-Verlag GmbH Germany. This e-offprint is for personal use only and shall not be selfarchived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript version for posting on your own website. You may further deposit the accepted manuscript version in any repository, provided it is only made publicly available 12 months after official publication or later and provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at link.springer.com".

Proceedings of the First Workshop on Scholarly Document Processing

We present the results of three Shared Tasks held at the Scholarly Document Processing Workshop at EMNLP2020: CL-SciSumm, LaySumm and LongSumm. We report on each of the tasks, which received 18 submissions in total, with some submissions addressing two or three of the tasks. In summary, the quality and quantity of the submissions show that there is ample interest in scholarly document summarization, and the state of the art in this domain is at a midway point between being an impossible task and one that is fully resolved.

2020 IEEE International Conference on Big Data (Big Data), 2020

Recent advances in natural language processing have enabled automation of a wide range of tasks, including machine translation, named entity recognition, and sentiment analysis. Automated summarization of documents, or groups of documents, however, has remained elusive, with many efforts limited to extraction of keywords, key phrases, or key sentences. Accurate abstractive summarization has yet to be achieved due to the inherent difficulty of the problem, and limited availability of training data. In this paper, we propose a topic-centric unsupervised multi-document summarization framework to generate extractive and abstractive summaries for groups of scientific articles across 20 Fields of Study (FoS) in Microsoft Academic Graph (MAG) and news articles from DUC-2004 Task 2. The proposed algorithm generates an abstractive summary by developing salient language unit selection and text generation techniques. Our approach matches the state-of-the-art when evaluated on automated extract...

2011

We present a methodology combining surface NLP and Machine Learning techniques for ranking asbtracts and generating summaries based on annotated corpora. The corpora were annotated with meta-semantic tags indicating the category of information a sentence is bearing (objective, findings, newthing, hypothesis, conclusion, future work, related work). The annotated corpus is fed into an automatic summarizer for query-oriented abstract ranking and multiabstract summarization. To adapt the summarizer to these two tasks, two novel weighting functions were devised in order to take into account the distribution of the tags in the corpus. Results, although still preliminary, are encouraging us to pursue this line of work and find better ways of building IR systems that can take into account semantic annotations in a corpus.