IIITBH-IITP@CL-SciSumm20, CL-LaySumm20, LongSumm20

Abstract

In this paper, we present the IIIT Bhagalpur and IIT Patna team's effort to solve the three shared tasks namely, CL-SciSumm 2020, CL-LaySumm 2020, LongSumm 2020 at SDP 2020. The themes of these tasks are to generate medium-scale, lay and long summaries, respectively, for scientific articles. For the first two tasks, unsupervised systems are developed, while for the third one, we have developed a supervised system. The performances of all the systems are evaluated on the associated datasets with the shared tasks in term of well-known ROUGE metric.

Proceedings of the 4th New Frontiers in Summarization Workshop

“…For analyzing our proposed model's performances on CL-SciSumm-2020 Corpus, we have used R-2 and R-SU4 F-1 scores (as the other comparable models are reported with these metrics) We have experimented to generate abstract and human summaries. As benchmarks, we have selected the research works submitted to CL-SciSumm-2019/2020: (1) Jaccard-focused GCN (Umapathy et al, 2020): an extractive summarizer utilizing cross-sentence graph and graph attention networks, (2) Clustering (Mishra et al, 2020): based on different clustering algorithms followed by sentencescoring functions, (3) MMR2 (Reddy et al, 2020): based on the maximal marginal relevance technique, and (4) LSTM+BabelNet (Chiruzzo et al, 2019): BabelNet vectors were used to train the LSTM. The CL-SciSumm task provides a performance metric evaluation script which is used to calculate the R-2 and R-SU4 values for the modelgenerated summaries against the test set.…”

IBERIFIER Reports: Is the ‘AI toolbox for disinformation’ ready?

“…The majority of recent work in disinformation analysis has been conducted with Computational Linguistic methods (Ruffo, Semeraro, Giachanou, & Rosso, 2023). Some recent (and straightforward) approaches put together an NLP pipeline (preprocessing, feature extraction, model building) to exploit traditional text analysis techniques (Asaad & Erascu, 2018;Koloski, Pollak, & Škrlj, 2020) or to train neural networks (Reddy, Suman, Saha, & Bhattacharyya, 2020;Umer et al, 2020;Eldesoky & Moussa, 2021;Qazi, Khan, & Ali, 2020;Tida, Hsu, & Hei, 2022;Dun, Tu, Chen, Hou, & Yuan, 2021) for fake news classification.…”

CNLP-NITS @ LongSumm 2021: TextRank Variant for Generating Long Summaries

“…They also suggested an abstractive summarizer based on the BART transformer that runs after the extractive summarizer. Other methods were Convolutional Neural Network (CNN) in (Reddy et al, 2020), Graph Convolutional Network (GCN) and Graph Attention Network (GAN) in (Li et al, 2020), and unsupervised clustering in (Mishra et al, 2020) and (Ju et al, 2020).…”