167 citations · 534 across the 24 of their papers we have counts for
5 papers · 1 filter
Knowledge-Enhanced Evidence Retrieval for Counterargument Generation
Yohan Jo, Haneul Yoo, JinYeong Bak +3
Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse…
Learning Bill Similarity with Annotated and Augmented Corpora of Bills
Jiseon Kim, Elden Griggs, In Song Kim +1
Bill writing is a critical element of representative democracy. However, it is often overlooked that most legislative bills are derived, or even directly copied, from other bills.…
Mitigating Language-Dependent Ethnic Bias in BERT
Jaimeen Ahn, Alice Oh
BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, an…
Weakly Supervised Pre-Training for Multi-Hop Retriever
Yeon Seonwoo, Sang-Woo Lee, Ji-Hoon Kim +2
In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question de…
KLUE: Korean Language Understanding Evaluation
Sungjoon Park, Jihyung Moon, Sungdong Kim +28
We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification,…