activity
20162022
most citedHopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions

5 citations · 5 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CL2022

Pre-training Language Models with Deterministic Factual Knowledge

Shaobo Li, Xiaoguang Li, Lifeng Shang +5

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitiv…

cs.CL2022

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

Shaobo Li, Xiaoguang Li, Lifeng Shang +6

Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs' ability to fill in the missing factu…

cs.CL2021

Integrating Regular Expressions with Neural Networks via DFA

Shaobo Li, Qun Liu, Xin Jiang +5

Human-designed rules are widely used to build industry applications. However, it is infeasible to maintain thousands of such hand-crafted rules. So it is very important to integrat…

cs.CL20205 cited

HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions

Shaobo Li, Xiaoguang Li, Lifeng Shang +5

Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA,…

cs.CL2016

Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

Yang Liu, Chengjie Sun, Lei Lin +1

In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooli…