• Publications
  • Influence
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
TLDR
We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Expand
  • 125
  • 25
  • PDF
CEDR: Contextualized Embeddings for Document Ranking
TLDR
We propose a joint approach that incorporates BERT's classification vector into existing neural models and show that it outperforms state-of-the-art ad-hoc ranking baselines. Expand
  • 100
  • 14
  • PDF
Depression and Self-Harm Risk Assessment in Online Forums
TLDR
We propose methods for identifying posts in support communities that may indicate a risk of self-harm, and demonstrate that our approach outperforms strong baselines on this general forum dataset. Expand
  • 78
  • 13
  • PDF
ADRTrace: Detecting Expected and Unexpected Adverse Drug Reactions from User Reviews on Social Media Sites
TLDR
We automatically extract adverse drug reactions from consumer reviews provided on various drug social media sites to identify adverse reactions not reported by the United States Food and Drug Administration (FDA) but touted by consumers. Expand
  • 88
  • 7
  • PDF
Scientific Article Summarization Using Citation-Context and Article's Discourse Structure
TLDR
We propose a summarization approach for scientific articles which takes advantage of citation-context and the document discourse model to overcome the problem of inconsistency between the citation summary and the article’s content. Expand
  • 55
  • 6
  • PDF
Ambiguity measure feature-selection algorithm
TLDR
We favorably show the effectiveness of our approach in outperforming eight existing featureselection methods, using five benchmark datasets with statistical significance of at least 95% confidence. Expand
  • 39
  • 6
  • PDF
Fusion of effective retrieval strategies in the same information retrieval system
TLDR
We hold constant systemic differences such as parsing, stemming, phrase processing, and relevance feedback, and fuse result sets generated from highly effective retrieval strategies in the same information retrieval system. Expand
  • 77
  • 5
  • PDF
Disproving the fusion hypothesis: an analysis of data fusion via effective information retrieval strategies
TLDR
We examine popular data fusion techniques designed to achieve improvements in effectiveness and clarify the conditions required for data fusion to show improvement. Expand
  • 44
  • 5
  • PDF
Triaging Mental Health Forum Posts
TLDR
Online mental health forums provide users with an anonymous support platform that is facilitated by moderators responsible for finding and addressing critical posts, especially those related to self-harm. Expand
  • 18
  • 5
  • PDF
Effective Structured Query Formulation for Session Search
TLDR
We use nuggets to formulate structured queries to feed into the Lemur search engine for session search. Expand
  • 16
  • 4
  • PDF