activity
20182022
most citedSelective Annotation Makes Language Models Better Few-Shot Learners

64 citations · 66 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CL20222 cited

RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering

Victor Zhong, Weijia Shi, Wen-tau Yih +1

We introduce RoMQA, the first benchmark for robust, multi-evidence, multi-answer question answering (QA). RoMQA contains clusters of questions that are derived from related constra…

cs.CL202264 cited

Selective Annotation Makes Language Models Better Few-Shot Learners

Hongjin Su, Jungo Kasai, Chen Henry Wu +8

Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they l…

cs.CL2021

DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions

Weijia Shi, Mandar Joshi, Luke Zettlemoyer

Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking a…

cs.CL2020

Cross-lingual Entity Alignment with Incidental Supervision

Muhao Chen, Weijia Shi, Ben Zhou +1

Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagesp…

cs.LG2020

On Tractable Representations of Binary Neural Networks

Weijia Shi, Andy Shih, Adnan Darwiche +1

We consider the compilation of a binary neural network's decision function into tractable representations such as Ordered Binary Decision Diagrams (OBDDs) and Sentential Decision D…

cs.CL2019

Retrofitting Contextualized Word Embeddings with Paraphrases

Weijia Shi, Muhao Chen, Pei Zhou +1

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstrea…