Instilling Type Knowledge in Language Models via Multi-Task QA
Comments Findings of NAACL 2022; dataset link: https://github.com/amazon-research/wikiwiki-dataset
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation
Comments NAACL 2022
QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization
Comments NAACL 2022
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks
Comments Accepted at NAACL 2022 (Main Conference)
AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarization
Comments NAACL 2022; arXiv admin note: substantial text overlap with arXiv:2104.08536
What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research
Comments NAACL 2022
Post-Training Dialogue Summarization using Pseudo-Paraphrasing
Comments Findings of NAACL 2022
EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification
Comments 13 pages, 7 figures, 7 tables. Accepted in NAACL 2022 (Findings)
Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion
Comments Accepted in NAACL 2022
An End-to-End Dialogue Summarization System for Sales Calls
Comments To be published in NAACL 2022
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
Comments Camera-ready for NAACL 2022
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
Comments Accepted by Findings of NAACL 2022
Consistency Training with Virtual Adversarial Discrete Perturbation
Comments NAACL 2022 (short)
Query2Particles: Knowledge Graph Reasoning with Particle Embeddings
Comments Findings of NAACL-2022
SkillSpan: Hard and Soft Skill Extraction from English Job Postings
Comments Accepted to NAACL 2022 Main conference
On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations
Comments Findings of NAACL 2022
Document-Level Relation Extraction with Sentences Importance Estimation and Focusing
Comments Accepted to NAACL 2022
Exploring Neural Models for Query-Focused Summarization
Comments Findings of NAACL 2022
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
Comments Accepted to appear at the main conference of NAACL 2022
EmpHi: Generating Empathetic Responses with Human-like Intents
Comments Accepted to NAACL 2022
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Comments NAACL 2022 findings
Locally Aggregated Feature Attribution on Natural Language Model Understanding
Comments NAACL 2022
LaMemo: Language Modeling with Look-Ahead Memory
Comments Accepted by NAACL 2022
Few-Shot Self-Rationalization with Natural Language Prompts
Comments v2: NAACL Findings 2022 accepted paper camera-ready version. First two authors contributed equally. 9 pages main, 3 pages appendix
Knowledge Inheritance for Pre-trained Language Models
Comments NAACL 2022
Aspect-based Analysis of Advertising Appeals for Search Engine Advertising
Comments Accepted by NAACL-HLT2022 Industry track
MCSE: Multimodal Contrastive Learning of Sentence Embeddings
Comments Accepted by NAACL 2022 main conference (short paper), 11 pages
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
Comments Accepted at NAACL 2022
Star-Transformer
Comments Accepted by NAACL 2019
Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
Comments Accepted by NAACL 2022
