DIRECTOR: Generator-Classifiers For Supervised Language Modeling. (arXiv:2206.07694v2 [cs.CL] UPDATED)
Unbiased and Efficient Sampling of Dependency Trees. (arXiv:2205.12621v2 [cs.CL] UPDATED)
Improving Passage Retrieval with Zero-Shot Question Generation. (arXiv:2204.07496v3 [cs.CL] UPDATED)
CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis. (arXiv:2204.00791v3 [cs.CL] UPDATED)
Hierachical Delta-Attention Method for Multimodal Fusion. (arXiv:2011.10916v2 [cs.CV] UPDATED)
Forecasting financial markets with semantic network analysis in the COVID-19 crisis. (arXiv:2009.04975v3 [q-fin.GN] UPDATED)
Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation. (arXiv:2004.08694v5 [cs.CL] UPDATED)
Financial Event Extraction Using Wikipedia-Based Weak Supervision. (arXiv:1911.10783v2 [cs.CL] UPDATED)
Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models. (arXiv:2211.14777v1 [cs.CV])
Navigation as the Attacker Wishes? Towards Building Byzantine-Robust Embodied Agents under Federated Learning. (arXiv:2211.14769v1 [cs.AI])
MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding. (arXiv:2211.14739v1 [cs.CV])
X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications. (arXiv:2211.14734v1 [cs.CL])
BadPrompt: Backdoor Attacks on Continuous Prompts. (arXiv:2211.14719v1 [cs.CL])
A novel multimodal dynamic fusion network for disfluency detection in spoken utterances. (arXiv:2211.14700v1 [cs.CL])
Gender Biases Unexpectedly Fluctuate in the Pre-training Stage of Masked Language Models. (arXiv:2211.14639v1 [cs.CL])
Searching for Discriminative Words in Multidimensional Continuous Feature Space. (arXiv:2211.14631v1 [cs.CL])
The distribution of syntactic dependency distances. (arXiv:2211.14620v1 [cs.CL])
A Survey of Text Representation Methods and Their Genealogy. (arXiv:2211.14591v1 [cs.CL])
Who are you referring to? Weakly supervised coreference resolution with multimodal grounding. (arXiv:2211.14563v1 [cs.CV])
Contextual Expressive Text-to-Speech. (arXiv:2211.14548v1 [eess.AS])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl