Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts. (arXiv:2205.12701v2 [cs.CL] UPDATED)
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models. (arXiv:2205.11169v2 [cs.CV] UPDATED)
Improving Intrinsic Exploration with Language Abstractions. (arXiv:2202.08938v2 [cs.LG] UPDATED)
Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes. (arXiv:2109.05250v2 [cs.CL] UPDATED)
Fast Nearest Neighbor Machine Translation. (arXiv:2105.14528v3 [cs.CL] UPDATED)
A Unified MRC Framework for Named Entity Recognition. (arXiv:1910.11476v7 [cs.CL] UPDATED)
HyperTuning: Toward Adapting Large Language Models without Back-propagation. (arXiv:2211.12485v1 [cs.CL])
On Narrative Information and the Distillation of Stories. (arXiv:2211.12423v1 [cs.CL])
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks. (arXiv:2211.12402v1 [cs.CV])
An Emotion-Aware Multi-Task Approach to Fake News and Rumour Detection using Transfer Learning. (arXiv:2211.12374v1 [cs.CL])
Method for Determining the Similarity of Text Documents for the Kazakh language, Taking Into Account Synonyms: Extension to TF-IDF. (arXiv:2211.12364v1 [cs.IR])
GDPR Compliant Collection of Therapist-Patient-Dialogues. (arXiv:2211.12360v1 [cs.CL])
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions. (arXiv:2211.12316v1 [cs.LG])
Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction. (arXiv:2211.12266v1 [cs.LG])
A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding. (arXiv:2211.12220v1 [cs.CL])
PromptTTS: Controllable Text-to-Speech with Text Descriptions. (arXiv:2211.12171v1 [eess.AS])
OLGA : An Ontology and LSTM-based approach for generating Arithmetic Word Problems (AWPs) of transfer type. (arXiv:2211.12164v1 [cs.CL])
PESE: Event Structure Extraction using Pointer Network based Encoder-Decoder Architecture. (arXiv:2211.12157v1 [cs.CL])
Event Causality Identification with Causal News Corpus -- Shared Task 3, CASE 2022. (arXiv:2211.12154v1 [cs.CL])
Coreference Resolution through a seq2seq Transition-Based System. (arXiv:2211.12142v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl