• Publications
  • Influence
Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
The method (Relevance Sensitive Attention for QFS) is compared to extractive baselines and with various ways to combine abstractive models on the DUC QFS datasets and with solid improvements on ROUGE performance. Expand
Question Answering as an Automatic Evaluation Metric for News Article Summarization
An end-to-end neural abstractive model is presented that maximizes APES, while increasing ROUGE scores to competitive results, and analyzing the strength of this metric by comparing it to known manual evaluation metrics. Expand
Diffeomorphic Temporal Alignment Nets
The Diffeomorphic Temporal alignment Net is proposed, a learning-based method for time-series joint alignment that not only outperforms existing joint-alignment methods in aligning training data but also generalizes well to test data. Expand
Interactive Extractive Search over Biomedical Corpora
A light-weight query language is introduced that does not require the user to know the details of the underlying linguistic representations, and instead to query the corpus by providing an example sentence coupled with simple markup, allowing for rapid exploration, development and refinement of user queries. Expand
Bootstrapping Relation Extractors using Syntactic Search by Examples
This work proposes a process for bootstrapping training datasets which can be performed quickly by non-NLP-experts and takes advantage of search engines over syntactic-graphs to obtain positive examples by searching for sentences that are syntactically similar to user input examples. Expand
Large Scale Substitution-based Word Sense Induction
A word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora, and which allows to induce corpora-specific senses, which may not appear in standard sense inventories, is presented. Expand
Question Answering as an Automatic Summarization Evaluation Metric
Recent work in the field of automatic summarization and headline generation focuses on maximizing ROUGE scores for various news datasets. We present an alternative, extrinsic, evaluation metric forExpand