activity
20192022
most citedX-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models

7 citations · 12 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL20221 cited

Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer

Zhengbao Jiang, Luyu Gao, Jun Araki +4

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and d…

cs.CL20224 cited

Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering

Zhengbao Jiang, Jun Araki, Haibo Ding +1

Generative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving rele…

cs.CL2020

How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering

Zhengbao Jiang, Jun Araki, Haibo Ding +1

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to pro…

cs.CL20207 cited

X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models

Zhengbao Jiang, Antonios Anastasopoulos, Jun Araki +2

Language models (LMs) have proven surprisingly successful at capturing factual knowledge by completing cloze-style fill-in-the-blank questions such as "Punta Cana is located in _."…

cs.CL2019

How Can We Know What Language Models Know?

Zhengbao Jiang, Frank F. Xu, Jun Araki +1

Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a _ by profe…

cs.CL2019

Generalizing Natural Language Analysis through Span-relation Representations

Zhengbao Jiang, Wei Xu, Jun Araki +1

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially design…