Corpus ID: 202540412

Incidental Supervision from Question-Answering Signals

@article{He2019IncidentalSF,
  title={Incidental Supervision from Question-Answering Signals},
  author={Hangfeng He and Qiang Ning and D. Roth},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.00333}
}
Human annotations are costly for many natural language processing (NLP) tasks, especially for those requiring NLP expertise. [...] Key Result We also find that the representation retrieved from question-answer meaning representation (QAMR) data can almost universally improve on a wide range of tasks, suggesting that such kind of natural language annotations indeed provide unique information on top of modern language models.Expand
Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text
TLDR
A new model, JEANS, is proposed, which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental supervision signals from text. Expand

References

SHOWING 1-10 OF 45 REFERENCES
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
TLDR
The results show that non-expert annotators can produce high quality QA-SRL data, and also establish baseline performance levels for future work on this task, and introduce simple classifierbased models for predicting which questions to ask and what their answers should be. Expand
Crowdsourcing Question-Answer Meaning Representations
TLDR
A crowdsourcing scheme is developed to show that QAMRs can be labeled with very little training, and a qualitative analysis demonstrates that the crowd-generated question-answer pairs cover the vast majority of predicate-argument relationships in existing datasets. Expand
Zero-Shot Relation Extraction via Reading Comprehension
TLDR
It is shown that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels. Expand
Question Answering as Global Reasoning Over Semantic Abstractions
TLDR
This work presents the first system that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Expand
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
TLDR
The experimental results on the SemEval-2010 relation classification task show that the AttBLSTM method outperforms most of the existing methods, with only word vectors. Expand
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TLDR
A strong logistic regression model is built, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). Expand
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
TLDR
The Multi-Genre Natural Language Inference corpus is introduced, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding and shows that it represents a substantially more difficult task than does the Stanford NLI corpus. Expand
Partial Or Complete, That’s The Question
TLDR
This paper provides an information theoretic formulation for this perspective and uses it, in the context of three diverse structured learning tasks, to show that learning from partial structures can sometimes outperform learning from complete ones. Expand
Supervised Open Information Extraction
TLDR
A novel formulation of Open IE as a sequence tagging problem, addressing challenges such as encoding multiple extractions for a predicate, and a supervised model that outperforms the existing state-of-the-art Open IE systems on benchmark datasets. Expand
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
TLDR
A benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models, which favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. Expand
...
1
2
3
4
5
...