research
∙
12/20/2022
ReCode: Robustness Evaluation of Code Generation Models
Code generation models have achieved impressive performance. However, th...
share
research
∙
10/19/2022
Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping
Fine-tuning over large pretrained language models (PLMs) has established...
research
∙
07/23/2022
The prediction of the quality of results in Logic Synthesis using Transformer and Graph Neural Networks
In the logic synthesis stage, structure transformations in the synthesis...
research
∙
12/31/2021
Transformer Embeddings of Irregularly Spaced Events and Their Participants
The neural Hawkes process (Mei Eisner, 2017) is a generative model o...
research
∙
06/07/2021
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
Recent advancements in open-domain question answering (ODQA), i.e., find...
research
∙
06/05/2021
Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains
Social media has become a valuable resource for the study of suicidal id...
research
∙
07/20/2020
Frustratingly Hard Evidence Retrieval for QA Over Books
A lot of progress has been made to improve question answering (QA) in re...
research
∙
07/10/2019
Modeling Semantic Compositionality with Sememe Knowledge
Semantic compositionality (SC) refers to the phenomenon that the meaning...
research
∙
06/01/2019
COS960: A Chinese Word Similarity Dataset of 960 Word Pairs
Word similarity computation is a widely recognized task in the field of ...
research
∙
01/28/2019
OpenHowNet: An Open Sememe-based Lexical Knowledge Base
In this paper, we present an open sememe-based lexical knowledge base Op...
research
∙
12/23/2018
Multi-modal Learning with Prior Visual Relation Reasoning
Visual relation reasoning is a central component in recent cross-modal a...
research
∙
10/31/2018
Semantic Modeling of Textual Relationships in Cross-Modal Retrieval
Feature modeling of different modalities is a basic problem in current r...
research
∙
10/31/2018