• Publications
  • Influence
Examining Gender Bias in Languages with Grammatical Gender
TLDR
In this paper, we propose new metrics for evaluating gender bias in word embeddings of gendered languages and further demonstrate evidence ofgender bias in bilingual embeddINGS which align these languages with English. Expand
  • 28
  • 5
  • PDF
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
TLDR
In this paper, we present a constrained text generation task, CommonGen associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning. Expand
  • 21
  • 5
  • PDF
Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
TLDR
We present a procedure that allows for the systematized probing of both PTLMs' inference abilities and robustness. Expand
  • 5
  • 1
  • PDF
Multi-graph Affinity Embeddings for Multilingual Knowledge Graphs
TLDR
We propose an improved model by learning a generalized affine-map-based alignment model. Expand
  • 8
  • 1
  • PDF
Retrofitting Contextualized Word Embeddings with Paraphrases
TLDR
We propose a simple and effective paraphrase-aware retrofitting (PAR) method that is applicable to arbitrary pretrained contextualized embeddings. Expand
  • 9
  • 1
  • PDF
Quantification and Analysis of Scientific Language Variation Across Research Fields
TLDR
We propose a computational approach for analyzing linguistic variation among scientific research fields by capturing the semantic change of terms based on a neural language model. Expand
  • 2
  • PDF
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
TLDR
In this paper, we propose two methods to introduce KGs into pretrained language models for commonsense tasks. Expand
  • 2
  • PDF
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms.
TLDR
We introduce a new challenge, RICA, that evaluates the capabilities of making commonsense inferences and the robustness of these inferences to language variations. Expand
  • 2
Analyzing and Mitigating Gender Bias in Languages with Grammatical Gender and Bilingual Word Embeddings
TLDR
We propose new definitions of gender bias for languages with grammatical gender and apply bilingual word embeddings to analyze and mitigate the bias. Expand
Computational Analysis of French Reborrowing Process for English Loanwords
TLDR
Analyzing semantic change of loanwords over time between different languages has been a longstanding sociolinguistic problem. Expand
...
1
2
...