1 code implementation • INLG (ACL) 2020 • Deen Mohammad Abdullah, Yllias Chali
Then, we fine-tuned the BERTSUM model for generating the abstractive summaries.
no code implementations • 10 Mar 2023 • Deen Abdullah, Shamanth Nayak, Gandharv Suri, Yllias Chali
Finally, we used the MMR approach again to select the query relevant sentences from the generated summaries of individual pre-trained models and constructed the final summary.
no code implementations • 19 Nov 2022 • David Adams, Gandharv Suri, Yllias Chali
In Natural Language Processing, multi-document summarization (MDS) poses many challenges to researchers above those posed by single-document summarization (SDS).
no code implementations • WS 2019 • Elozino Egonmwan, Yllias Chali
For better quality of generated paraphrases, we propose a framework that combines the effectiveness of two models {--} transformer and sequence-to-sequence (seq2seq).
no code implementations • WS 2019 • Elozino Egonmwan, Yllias Chali
We propose a system that improves performance on single document summarization task using the CNN/DailyMail and Newsroom datasets.
1 code implementation • WS 2018 • Yllias Chali, Tina Baghaee
We study the problem of opinion question generation from sentences with the help of community-based question answering systems.
no code implementations • COLING 2018 • Mir Tafseer Nayeem, Tanvir Ahmed Fuad, Yllias Chali
Furthermore, we apply our sentence level model to implement an abstractive multi-document summarization system where documents usually contain a related set of sentences.
no code implementations • IJCNLP 2017 • Yllias Chali, Moin Tanvee, Mir Tafseer Nayeem
We propose a submodular function-based summarization system which integrates three important measures namely importance, coverage, and non-redundancy to detect the important sentences for the summary.
no code implementations • WS 2017 • Mir Tafseer Nayeem, Yllias Chali
In this work, we aim at developing an extractive summarizer in the multi-document setting.
no code implementations • 15 Jan 2014 • Yllias Chali, Shafiq Rayhan Joty, Sadid A. Hasan
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topic-oriented, informative multi-document summarization where the goal is to produce a single text as a compressed version of a set of documents with a minimum loss of relevant information.