The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Online, 5-10 July 2020

/pdf/a-large-scale-multi-document-summarization-dataset-from-the-46e1ummg1i.pdf

A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal

In this work, we aim at developing an unsupervised abstractive summarization system in the multi-document setting. We design a paraphrastic sentence fusion model which jointly performs sentence fusion and paraphrasing using skip-gram word embedding model at the sentence level. Our model improves the information coverage and at the same time abstractiveness of the generated sentences. We conduct our experiments on the human-generated multi-sentence compression datasets and evaluate our system on several newly proposed Machine Translation (MT) evaluation metrics. Furthermore, we apply our sentence level model to implement an abstractive multi-document summarization system where documents usually contain a related set of sentences. We also propose an optimal solution for the classical summary length limit problem which was not addressed in the past research. For the document level summary, we conduct experiments on the datasets of two different domains (e.g., news article and user reviews) which are well suited for multi-document abstractive summarization. Our experiments demonstrate that the methods bring significant improvements over the state-of-the-art methods.

Abstractive Unsupervised Multi-Document Summarization using Paraphrastic Sentence Fusion

Sentence fusion is the task of joining several independent sentences into a single coherent text. Current datasets for sentence fusion are small and insufficient for training modern neural models. In this paper, we propose a method for automatically-generating fusion examples from raw text and present DiscoFuse, a large scale dataset for discourse-based sentence fusion. We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences. We apply our approach on two document collections: Wikipedia and Sports articles, yielding 60 million fusion examples annotated with discourse information required to reconstruct the fused text. We develop a sequence-to-sequence model on DiscoFuse and thoroughly analyze its strengths and weaknesses with respect to the various discourse phenomena, using both automatic as well as human evaluation. Finally, we conduct transfer learning experiments with WebSplit, a recent dataset for text simplification. We show that pretraining on DiscoFuse substantially improves performance on WebSplit when viewed as a sentence fusion task.

DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion

Recent neural sequence-to-sequence models have shown significant progress on short text summarization However, for document summarization, they fail to capture the long-term structure of both documents and multi-sentence summaries, resulting in information loss and repetitions In this paper, we propose to leverage the structural information of both documents and multi-sentence summaries to improve the document summarization performance Specifically, we import both structural-compression and structural-coverage regularization into the summarization process in order to capture the information compression and information coverage properties, which are the two most important structural properties of document summarization Experimental results demonstrate that the structural regularization improves the document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperforms state-of-the-art neural abstractive methods

/pdf/improving-neural-abstractive-document-summarization-with-576jfo7i6d.pdf

Improving Neural Abstractive Document Summarization with Structural Regularization

In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to tackle summary coherence for increasing readability. We conduct experiments on the Document Understanding Conference (DUC) 2004 datasets using ROUGE toolkit. Our experiments demonstrate that the methods bring significant improvements over the state of the art methods in terms of informativity and coherence.

/pdf/extract-with-order-for-coherent-multi-document-summarization-1qwiod0nr9.pdf

Extract with Order for Coherent Multi-Document Summarization

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. We design monotone and submodular functions which allow us to apply an efficient and scalable greedy algorithm to obtain informative and well-covered summaries. In addition, we integrate two abstraction-based methods namely sentence compression and merging for generating an abstractive sentence set. We design our summarization models for both generic and query-focused summarization. Experimental results on DUC-2004 and DUC-2007 datasets show that our generic and query-focused summarizers have outperformed the state-of-the-art summarization systems in terms of ROUGE-1 and ROUGE-2 recall and F-measure.

Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging

Nowadays, due to enormous growth of web users many services in the internet including Email, search engine, social networking are provided with free of charge. With the expansion of Web services, denial of service (DoS) attacks by malicious automated programs (e.g., web bots) is becoming a serious problem of web service accounts. CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is a human authentication mechanism that generates and grades tests to determine whether the user is a human or a malicious computer program. These tests are easier for humans to solve and tough for automated bots. According to our study, the existing CAPTCHA techniques tried to maximize the difficulty for automated programs to pass tests by increasing distortion or noise. Consequently, it has also become difficult for humans too. In our proposed solution, we try to make use of human cognitive processing abilities into our CAPTCHA design. The suggested approach move and select is a 2-layer test, desired to improve security and reduce the solving time of human. In the result section we have studied both the usability and security issues of our design. The user studies indicate that this CAPTCHA can be solved with 99.04% average success rate in less than 10 seconds.

http://www.ijens.org/Vol_11_I_05/117005-8383-IJVIPNS-IJENS.pdf

Moin Mahmud Tanvee

Papers

Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging

Move & Select: 2-Layer CAPTCHA Based on Cognitive Psychology for Securing Web Services