• Publications
  • Influence
Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
TLDR
This paper introduces Multi-News, the first large-scale MDS news dataset, and proposes an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets. Expand
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
TLDR
CoSQL is presented, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems that includes SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction and a set of strong baselines are evaluated. Expand
What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning
TLDR
LectureBank is introduced, a dataset containing 1,352 English lecture files collected from university courses which are each classified according to an existing taxonomy as well as 208 manually-labeled prerequisite relation topics, which is publicly available. Expand
TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation
TLDR
This work introduces TutorialBank, a new, publicly available dataset which aims to facilitate NLP education and research and is notably the largest manually-picked corpus of resources intended for N LP education which does not include only academic papers. Expand
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
TLDR
Experimental results on the MATERIAL dataset show that the proposed model outperforms the competitive translation-based baselines on English-Swahili, English-Tagalog, and English-Somali cross-lingual information retrieval tasks. Expand
Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess
TLDR
This paper introduces a neural pedagogical agent for real-time user modeling in the task of predicting user response correctness, a central task for mobile education applications, and outperforms existing approaches over several metrics. Expand
R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning
TLDR
This paper proposes a model called the Relational-Variational Graph AutoEncoder (R-VGAE) to predict concept relations within a graph consisting of concept and resource nodes that is notably the first graph-based model that attempts to make use of deep learning representations for the task of unsupervised prerequisite learning. Expand
Zero-shot Transfer Learning for Semantic Parsing
TLDR
This paper introduces a new method for learning the shared space between multiple domains based on the prediction of the domain label for each example and investigates the sensitivity of domain-label classification loss on each example. Expand
ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining
TLDR
Annotation protocols motivated by an issues–viewpoints–assertions framework are designed to crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads, and benchmark state-of-the-art models on these datasets and analyze characteristics associated with the data. Expand
Evaluation of Extractive Summarization Techniques on Powerpoint Presentations and HTML Pages from the AAN TutorialBank Corpus
This paper compares four different extractive summarization techniques on Powerpoint slides and HTML webpages. The algorithms are run on seven different topics related to Natural Language ProcessingExpand
...
1
2
...