• Publications
  • Influence
CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing
TLDR
We present the shared task for the Twentieth Conference on Computational Natural Language Learning (CoNLL-2016) on Multilingual Shallow Discourse Parsing. Expand
  • 90
  • 23
  • PDF
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
TLDR
We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task. Expand
  • 77
  • 13
  • PDF
TabFact: A Large-scale Dataset for Table-based Fact Verification
TLDR
The problem of verifying whether a textual hypothesis holds based on the given evidence, also known as fact verification, plays an important role in the study of natural language understanding and semantic representation. Expand
  • 29
  • 11
  • PDF
Universal Dependencies Parsing for Colloquial Singaporean English
TLDR
We investigate dependency parsing of Singlish by constructing a dependency treebank under the Universal Dependencies scheme, and then training a neural network model by integrating English syntactic knowledge into a state-of-the-art parser trained on the Singlish treebank. Expand
  • 15
  • 2
  • PDF
A Rank-Based Similarity Metric for Word Embeddings
TLDR
We propose a rank-based metric for word embeddings that performs comparably to vector cosine in similarity estimation and out-performs it in the recently-introduced and challenging task of outlier detection, thus suggesting that rank- based measures can improve clustering quality. Expand
  • 9
  • 1
  • PDF
A high-performance scheduling algorithm using greedy strategy toward quality of service in the cloud environments
TLDR
We present a novel algorithm named ITSA (Improved Task Schedule Algorithm), which is based on the gain value of task swap and performs “task pair” scheduling by utilizing the greedy strategy. Expand
  • 1
From Genesis to Creole Language
TLDR
We extend Wang et al. (2017) by enlarging the Singlish treebank to more than triple the size and with much more diversity in topics, as well as further exploring neural multi-task models for integrating English syntactic knowledge. Expand
A basic end-member model algorithm for grain-size data of marine sediments
TLDR
This paper introduces a new way to determine geologically feasible EMs, a new EM unmixing algorithm and a new method to determine the appropriate EM number. Expand
  • 1
2 Similarity , Relatedness and Dissimilarity : Current Issues in the Evaluation of DSMs
Word Embeddings (WE) have recently imposed themselves as a standard for representing word meaning in NLP. Semantic similarity between word pairs has become the most common evaluation benchmark forExpand
Building of the clinic for the Olympic Fencing Hall
Clinics in the Olympic venues make a critical component in the medical service system for Olympic venues. The clinic in the fencing hall is cited as an example in this paper, which introduced theExpand