LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification
Comments Accepted to ACL 2021
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children's mindreading ability
Comments The paper will be presented at ACL-IJCNLP 2021
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
Comments The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP): Findings
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
Comments Accepted to ACL 2021 Findings
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
Comments Accepted in Findings of ACL-IJCNLP 2021
A Systematic Investigation of KB-Text Embedding Alignment at Scale
Comments Accepted to ACL-IJCNLP 2021. 11 pages, 2 figures
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text
Comments Findings of ACL 2021
The Limitations of Limited Context for Constituency Parsing
Comments To be published in ACL 2021 (https://2021.aclweb.org/) as a long paper
Discriminative Reasoning for Document-level Relation Extraction
Comments 11 pages, 4 figures, 5 tables. Findings of ACL 2021
Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?
Comments Accepted By ACL-IJCNLP 2021
CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
Comments ACL-IJCNLP 2021 camera-ready (long paper in main conference)
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
Comments 13 pages, 3 figures, accepted by findings of ACL 2021
MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding
Comments Accepted by ACL 2021
Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution
Comments ACL 2021; 16 pages
Knowing More About Questions Can Help: Improving Calibration in Question Answering
Comments ACL 2021 (finding)
Evaluating the Efficacy of Summarization Evaluation across Languages
Comments Findings of ACL 2021
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
Comments 9 pages, Findings of ACL-IJCNLP 2021
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks
Comments Findings of ACL 2021
Figurative Language in Recognizing Textual Entailment
Comments ACL 2021 (Findings)
OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres
Comments ACL 2021
Controllable Abstractive Dialogue Summarization with Sketch Supervision
Comments ACL-Findings 2021. Code is released at https://github.com/salesforce/ConvSumm
Automatic Construction of Sememe Knowledge Bases via Dictionaries
Comments Accepted by Findings of ACL at ACL-IJCNLP 2021. Camera-ready version
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
Comments Accepted by ACL-IJCNLP 2021 as a long paper. Camera-ready version
BERT Busters: Outlier Dimensions that Disrupt Transformers
Comments Accepted as long paper at Findings of ACL 2021
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
Comments ACL 2021 camera-ready
Modeling Fine-Grained Entity Types with Box Embeddings
Comments ACL 2021
UnitedQA: A Hybrid Approach for Open Domain Question Answering
Comments ACL 2021 camera-ready
Shortformer: Better Language Modeling using Shorter Inputs
Comments To appear at ACL 2021
Detecting Hallucinated Content in Conditional Neural Sequence Generation
Comments Accepted by ACL-Finding 2021
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings
Comments Accepted to ACL-IJCNLP 2021 SRW
