Guy Lev
YOU?
Author Swipe
View article: Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization
Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization Open
Many organizations require their customer-care agents to manually summarize their conversations with customers. These summaries are vital for decision making purposes of the organizations. The perspective of the summary that is required to…
View article: HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles Open
We present HowSumm, a novel large-scale dataset for the task of query-focused multi-document summarization (qMDS), which targets the use-case of generating actionable instructions from a set of sources. This use-case is different from the …
View article: Detector-Free Weakly Supervised Grounding by Separation
Detector-Free Weakly Supervised Grounding by Separation Open
Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with the task of using this data to learn to localize (or to groun…
View article: orgFAQ: A New Dataset and Analysis on Organizational FAQs and User Questions
orgFAQ: A New Dataset and Analysis on Organizational FAQs and User Questions Open
Frequently Asked Questions (FAQ) webpages are created by organizations for their users. FAQs are used in several scenarios, e.g., to answer user questions. On the other hand, the content of FAQs is affected by user questions by definition.…
View article: A Summarization System for Scientific Documents
A Summarization System for Scientific Documents Open
We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on the…
View article: TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks
TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks Open
Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at sci…
View article: Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks Open
The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting. Most natural language processing applications expect segmented and well-formatted texts as input, which is not a…