• Publications
  • Influence
Creating Causal Embeddings for Question Answering with Minimal Supervision
TLDR
This work argues that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings, and implements causality as a use case. Expand
Deep Affix Features Improve Neural Named Entity Recognizers
TLDR
A practical model for named entity recognition (NER) that combines word and character-level information with a specific learned representation of the prefixes and suffixes of the word is proposed and achieves state of the art results on the CoNLL 2002 Spanish and Dutch and coNLL 2003 German NER datasets. Expand
Framing QA as Building and Ranking Intersentence Answer Justifications
TLDR
A question answering approach for standardized science exams that both identifies correct answers and produces compelling human-readable justifications for why those answers are correct is proposed, and it is shown that information aggregation is key to addressing the information need in complex questions. Expand
The phonetic specificity of contrastive hyperarticulation in natural speech
Abstract Evidence suggests that speakers hyperarticulate phonetic cues to word identity in a way that increases phonetic distance to similar competitors. However, the degree and type of phoneticExpand
Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering
TLDR
An unsupervised, simple, and fast alignment and informa- tion retrieval baseline that incorporates two novel contributions: a one-to-many alignment between query and document terms and negative alignment as a proxy for discriminative information. Expand
Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering
TLDR
It is shown that these alignment models trained directly from discourse structures imposed on free text improve performance considerably over an information retrieval baseline and a neural network language model trained on the same data. Expand
On the Importance of Delexicalization for Fact Verification
TLDR
This work focuses on the recognizing textual entailment (RTE) task and its application to fact verification, and investigates the attention weights a state of the art RTE method assigns to input tokens in the RTE component of fact verification systems. Expand
Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models
TLDR
This paper introduces an approach that builds executable probabilistic models from raw, free text from Eidos, INDRA, and Delphi, an open-domain machine reading system designed to extract causal relations from natural language. Expand
Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification
TLDR
A neural network architecture for QA that reranks answer justifications as an intermediate (and human-interpretable) step in answer selection and shows that with this end-to-end approach it is able to significantly improve upon a strong IR baseline in both justification ranking and answer selection. Expand
Intravenous ferric carboxymaltose accelerates erythropoietic recovery from experimental malarial anemia.
TLDR
The findings challenge the restrictive use of iron therapy in malaria and show the need for trials of intravenous ferric carboxymaltose as an adjunctive treatment for severe malarial anemia. Expand
...
1
2
3
...