• Publications
  • Influence
Inferring Implicit Event Locations from Context with Distributional Similarities
tl;dr
We exploit distributional semantics, based on the hypothesis that if two events are described by similar expressions, it is likely that they occur in the same location. Expand
  • 2
  • Open Access
A novel method to analyze and design a NWL scheme DRAM
One of the most important issues for DRAM development is the control of data retention time. A negatively-biased off-state level of the word line (NWL) was introduced to the memory cell design toExpand
  • 2
A Corpus of Sentence-level Annotations of Local Acceptability with Reasons
News editorials are presented with arguments of different quality, which readers may or may not accept as presented. In this work, we present a corpus of news editorials with sentence-levelExpand
  • 1
  • Open Access
Unsupervised inference of implicit biomedical events using context triggers
tl;dr
We present an unsupervised method for inferring cross-sentence events by propagating intra-sentENCE information to adjacent sentences using context trigger expressions that strongly signal the implicit presence of entities of interest. Expand
Generating Sentential Arguments from Diverse Perspectives on Controversial Topic
Considering diverse aspects of an argumentative issue is an essential step for mitigating a biased opinion and making reasonable decisions. A related generation model can produce flexible resultsExpand
Extraction of Gene-Environment Interaction from the Biomedical Literature
tl;dr
We propose to overcome these challenges with neural network models and show that a modified sequence-to-sequence model with a static RNN decoder produces a good performance in GxE recognition. Expand
Assessing the Multi-level Knowledge Prominence Perceived by the Authors as Revealed on their Writings
Automatic identification of widely-known facts not only plays a crucial role in automatic curation of databases of common-sense knowledge, but also benefits many applications of natural languageExpand
Computer Assisted Annotation of Tension Development in TED Talks through Crowdsourcing
tl;dr
We propose a method of machine-assisted annotation for the identification of tension development, annotating whether the tension is increasing, decreasing, or staying unchanged. Expand
Nonsense!: Quality Control via Two-Step Reason Selection for Annotating Local Acceptability and Related Attributes in News Editorials
tl;dr
Annotation quality control is a critical aspect for building reliable corpora through linguistic annotation. Expand
  • 1
  • Open Access
Neural Theorem Prover with Word Embedding for Efficient Automatic Annotation
본 연구는 전문기관에서 생산되는 검증된 문서를 웹상의 수많은 검증되지 않은 문서에 자동 주석하여 신 뢰도 향상 및 심화 정보를 자동으로 추가하는 시스템을 설계하는 것을 목표로 한다. 이를 위해 활용 가능 한 시스템인 인공 신경 정리 증명계(neural theorem prover)가 대규모 말뭉치에 적용되지 않는다는 근본 적인 문제를 해결하기 위해 내부Expand