Collection of papers and resources for data augmentation for NLP.

Fetch Academic Research Papers from different sources

[ACL-IJCNLP 2021] Automated Concatenation of Embeddings for Structured Prediction

TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)

[NAACL'21 & ACL'21] SapBERT: Self-alignment pretraining for BERT & XL-BEL: Cross-Lingual Biomedical Entity Linking.

The released codes for ACL 2021 paper 'BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data'

CogIE: An Information Extraction Toolkit for Bridging Text and CogNet. ACL 2021

Towards Quantifiable Dialogue Coherence Evaluation (ACL 2021)

Codebase, data and models for the Keep it Simple paper at ACL2021

Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation (ACL 2021 Findings).

[ACL-IJCNLP 2021] Self-Supervised Multimodal Opinion Summarization

code for the paper "UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction"

Code for the NLP4Prog workshop paper "Reading StackOverflow Encourages Cheating: Adding Question TextImproves Extractive Code Generation"

Source Code For ACL 2021 Paper "Mention Flags (MF): Constraining Transformer-based Text Generators"

Official repository to release the code and datasets in the paper, "Article Reranking by Memory-enhanced Key Sentence Matching for Detecting Previously Fact-checked Claims", ACL-IJCNLP 2021.

The official repository for "Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP" published in ACL-IJNLP 2021.

Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization (ACL 2021)

Code for paper Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach by Zhe Lin, Xiaojun Wan. This paper is accepted by Findings of ACL'21.

[ACL'21] Data for "An In-depth Study on Internal Structure of Chinese Words".

Code for Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution (ACL2021)