Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Embedding Uncertain Knowledge Graphs
This paper proposes a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space and introduces probabilistic soft logic to infer confidence scores for unseen relation facts during training.
Examining Gender Bias in Languages with Grammatical Gender
Experiments on modified Word Embedding Association Test, word similarity, word translation, and word pair translation tasks show that the proposed approaches can effectively reduce the gender bias while preserving the utility of the original embeddings.
Cross-lingual Entity Alignment with Incidental Supervision
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.
On Tractable Representations of Binary Neural Networks
A more efficient approach for compiling neural networks is considered, based on a pseudo-polynomial time algorithm for compiling a neuron, and it is shown that it is feasible to obtain compact representations of neural networks as SDDs.
Compiling Neural Networks into Tractable Boolean Circuits
This work shows how to reduce a neural network over binary inputs and step activation functions into a Boolean circuit, then compile this Boolean circuit into a tractable one (a core problem in the domain of knowledge compilation).
Retrofitting Contextualized Word Embeddings with Paraphrases
This work proposes a post-processing approach to retrofit the contextualized word embedding with paraphrases, which seeks to minimize the variance of word representations on paraphrased contexts and significantly improves ELMo on various sentence classification and inference tasks.
Design Challenges in Low-resource Cross-lingual Entity Linking
It is claimed that, under the low-resource language setting, outside-Wikipedia cross-lingual resources are essential and a simple but effective zero-shot framework is proposed, CogCompXEL, that complements current methods by utilizing query log mapping files from online search engines.
DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions
Compared to other multi-document summarization tasks, this task is entity-centric, more abstractive, and covers a wide range of domains, and there exists a large gap between state-of-art models and human performance.
Learning Bilingual Word Embeddings Using Lexical Definitions
- Weijia Shi, Muhao Chen, Yingtao Tian, Kai-Wei Chang
- Computer Science, LinguisticsRepL4NLP@ACL
- 21 June 2019
Without the need of predefined seed lexicons, BiLex comprises a novel word pairing strategy to automatically identify and propagate the precise fine-grain word alignment from lexical definitions for bilingual word embedding learning.
Computational Analysis of French Reborrowing Process for English Loanwords
- Zhubo Deng, Weijia Shi, Pei Zhou, Muhao Chen, Kai-Wei Chang
- LinguisticsInternational Conference on Data Mining Workshops…
- 1 November 2019
A new computational method for detecting and tracking the semantic change of loanword between two languages, specifically for the reborrowing process of loanwords, is presented and it is shown that the model can detect reborrows loanwords that have been discovered in literature.