Spatio-temporal Storytelling? Leveraging Generative Models for Semantic Trajectory Analysis. (arXiv:2306.13905v1 [cs.CL])
Math Word Problem Solving by Generating Linguistic Variants of Problem Statements. (arXiv:2306.13899v1 [cs.CL])
Estimating the Causal Effect of Early ArXiving on Paper Acceptance. (arXiv:2306.13891v1 [cs.CL])
L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models. (arXiv:2306.13888v1 [cs.CL])
IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations. (arXiv:2306.13865v1 [cs.CL])
Is Pre-training Truly Better Than Meta-Learning?. (arXiv:2306.13841v1 [cs.LG])
Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data. (arXiv:2306.13840v1 [cs.CL])
The Double Helix inside the NLP Transformer. (arXiv:2306.13817v1 [cs.AI])
Cross-Language Speech Emotion Recognition Using Multimodal Dual Attention Transformers. (arXiv:2306.13804v1 [cs.CL])
An analysis of vaccine-related sentiments from development to deployment of COVID-19 vaccines. (arXiv:2306.13797v1 [cs.SI])
Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models. (arXiv:2306.13789v1 [cs.CL])
Resume Information Extraction via Post-OCR Text Processing. (arXiv:2306.13775v1 [cs.CL])
The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios. (arXiv:2306.13734v1 [eess.AS])
MarioGPT: Open-Ended Text2Level Generation through Large Language Models. (arXiv:2302.05981v2 [cs.AI] CROSS LISTED)
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning. (arXiv:2306.13089v2 [cs.LG] UPDATED)
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought. (arXiv:2306.12672v2 [cs.CL] UPDATED)
Human-in-the-Loop through Chain-of-Thought. (arXiv:2306.07932v2 [cs.CL] UPDATED)
Visually-Grounded Descriptions Improve Zero-Shot Image Classification. (arXiv:2306.06077v2 [cs.CV] UPDATED)
LEACE: Perfect linear concept erasure in closed form. (arXiv:2306.03819v2 [cs.LG] UPDATED)
Supplementary Features of BiLSTM for Enhanced Sequence Labeling. (arXiv:2305.19928v4 [cs.CL] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl