Share This Author
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links and supports construction of a scientific knowledge graph, which is used to analyze information in scientific literature.
Entity, Relation, and Event Extraction with Contextualized Span Representations
This work examines the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction (called DyGIE++) and achieves state-of-the-art results across all tasks.
Text Generation from Knowledge Graphs with Graph Transformers
- Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh Hajishirzi
- Computer ScienceNAACL
- 1 April 2019
This work addresses the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph by introducing a novel graph transforming encoder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints.
A general framework for information extraction using dynamic span graphs
- Yi Luan, David Wadden, Luheng He, A. Shah, Mari Ostendorf, Hannaneh Hajishirzi
- Computer ScienceNAACL
- 5 April 2019
This framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains and is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset.
Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
Experiments show that this multi-task learning approach to training neural conversation models that leverages both conversation data across speakers and other types of data pertaining to the speaker and speaker roles to be modeled leads to significant improvements over baseline model quality.
The UWNLP system at SemEval-2018 Task 7: Neural Relation Extraction Model with Selectively Incorporated Concept Embeddings
This model is based on the end-to-end relation extraction model of (Miwa and Bansal, 2016) with several enhancements such as character-level encoding attention mechanism on selecting pretrained concept candidate embeddings.
Recognition of stance strength and polarity in spontaneous speech
- Gina-Anne Levow, V. Freeman, Trang Tran
- Computer ScienceIEEE Spoken Language Technology Workshop (SLT)
- 1 December 2014
A new annotated corpus of spontaneous, conversational speech designed to elicit high densities of stance-taking at different strengths is presented and classifiers for automatic recognition of stances-taking behavior in speech are developed.
Scientific Information Extraction with Semi-supervised Neural Tagging
This paper addresses the problem of extracting keyphrases from scientific articles and categorizing them as corresponding to a task, process, or material and introduces semi-supervised methods to a neural tagging model, which builds on recent advances in named entity recognition.
LSTM based Conversation Models
A conversational model that incorporates both context and participant role for two-party conversations that outperforms a traditional LSTM model as measured by language model perplexity and response ranking is presented.