arXiv Comp. Linguistics๐Ÿ“š · @arxiv_cl
222 followers · 3980 posts · Server creative.ai

๐Ÿ“ Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens ๐Ÿ“š๐Ÿง 

"Proposes Multi2SPE -- it encourages each of multiple CLS tokens to learn diverse ways of aggregating token embeddings, then sums them up together to create a single vector representation." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2309.04333v1

#cl #DL #lg #arxiv

Last updated 1 year ago

arXiv Sound & Audio๐Ÿ”Š · @arxiv_sd
39 followers · 621 posts · Server creative.ai

๐Ÿ“ Large-Scale Automatic Audiobook Creation ๐Ÿ”Š๐Ÿ‘พ๐Ÿง 

"Leverages recent advances in neural text-to-speech and text summarization and allows users to customize an audiobook's speaking style and speed using a small amount of speech samples." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2309.03926v1

#sd #ai #dc #DL #lg #arxiv

Last updated 1 year ago

๐Ÿ“ OldVisOnline: Curating a Dataset of Historical Visualizations ๐Ÿ‘‹

"Proposes a workflow to scrape and process heterogeneous metadata for historical visualization images from seven online libraries and propose a semi-automatic labeling approach to distinguish visualizations from other artifacts." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/oldvis
๐Ÿ”— arxiv.org/abs/2308.16053v1

#hc #DL #arxiv

Last updated 1 year ago

arXiv Graphics๐Ÿ–ผ๏ธ · @arxiv_gr
63 followers · 1346 posts · Server creative.ai

๐Ÿ“ Saving Temporary Exhibitions in Virtual Environments: The Digital Renaissance of Ulisse Aldrovandi ๐Ÿ–ผ๏ธ

"To make the digital twin of the temporary exhibition "The Other Renaissance: Ulisse Aldrovandi and the Wonders of the World" accessible online." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2308.15920v1

#gr #DL #arxiv

Last updated 1 year ago

Harald Sack · @lysander07
741 followers · 454 posts · Server sigmoid.social

Interesting new lecture by Christopher Potts & his team, Stanford: Natural Language Understanding (CS224U, Spring 2023):
- Domain adaptation for supervised sentiment
- Retrieval augmented in-context learning
- Advanced behavioral evaluation and analysis methods
methods
Resources:
Video lectures: youtube.com/playlist?list=PLoR
Course website: web.stanford.edu/class/cs224u/
Code: github.com/cgpotts/cs224u/

#nlp #ai #llm #deeplearning #DL #Transformers #lecture

Last updated 1 year ago

Raffaele Fitto · @RaffaeleFitto
1 followers · 1120 posts · Server respublicae.eu

Re Al momento dell'insediamento il aveva un numero di infrazioni pendenti con l' di 84, rispetto ad una media europea di 65.
Con il approvato oggi si interviene sull'avvio a soluzione e chiusura di 13 procedure e si previene l'apertura di nuove procedure.

๐Ÿฆ๐Ÿ”—: n.respublicae.eu/RaffaeleFitto

#GovernoMeloni #UE #DL

Last updated 1 year ago

arXiv Comp. Linguistics๐Ÿ“š · @arxiv_cl
190 followers · 3443 posts · Server creative.ai

๐Ÿ“ UnScientify: Detecting Scientific Uncertainty in Scholarly Full Text ๐Ÿ“š๐Ÿ‘พ

"UnScientify automatically labels and annotates scientific uncertainty in scholarly papers by using a combination of pattern matching, complex sentence checking, and authorial reference checking approaches." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2307.14236v1

#cl #ai #DL #arxiv

Last updated 1 year ago

arXiv Comp. Linguistics๐Ÿ“š · @arxiv_cl
190 followers · 3438 posts · Server creative.ai

๐Ÿ“ Unsupervised Extraction of Local and Global Keywords From a Single Text ๐Ÿ“š

"Based on the spatial distribution of words and the change of this distribution due to a random permutation of words, in the text of a literary work (e." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2307.14005v1

#cl #DL #arxiv

Last updated 1 year ago

Leonardo Grando · @lgrando123
100 followers · 287 posts · Server sciencemastodon.com

๐Ÿ“ OpenGDA: Graph Domain Adaptation Benchmark for Cross-Network Learning ๐Ÿ‘พ

"To provide a benchmark for evaluating Graph Domain Adaptation models, OpenGDA provides unified preprocessed datasets for different types of tasks (i) node classification, (ii) link prediction or (iii) graph classification." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/Skyorca/OpenGDA
๐Ÿ”— arxiv.org/abs/2307.11341v1

#ai #DL #si #arxiv

Last updated 1 year ago

๐Ÿ“ Classification of Visualization Types and Perspectives in Patents ๐Ÿ”ญ๐Ÿ‘พ๐Ÿ’ฟ๐Ÿง 

"Adopts state-of-the-art deep learning methods including transformers for the classification of visualization types and perspectives in patent images with a new patent dataset that contains a larger variety of visualization types and perspectives." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/TIBHannover/PatentI
๐Ÿ”— arxiv.org/abs/2307.10471v1

#cv #ai #DL #ir #lg #arxiv

Last updated 1 year ago

๐Ÿ“ Testing for Reviewer Anchoring in Peer Review: A Randomized Controlled Trial ๐Ÿ‘‹

"Investigates whether reviewers anchor to their original scores when updating their reviews, which serves as a potential explanation for the lack of updates in reviewer scores (Figure 1)." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/theryanl/
๐Ÿ”— arxiv.org/abs/2307.05443v1

#hc #DL #arxiv

Last updated 1 year ago

๐Ÿ“ Can We Mathematically Spot Possible Manipulation of Results in Research Manuscripts Using Benford's Law? ๐Ÿ’ฟ

"An automatic tool that detects manipulated results using a statistical phenomenon (Benford's law) on commonly employed analyses in academic manuscripts, thus reducing the need for the raw data itself." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2307.01742v1

#ir #DL #arxiv

Last updated 1 year ago

๐Ÿ“ Predictive Patentomics: Forecasting Innovation Success and Valuation with ChatGPT ๐Ÿง ๐Ÿ‘พ๐Ÿ“š

"ChatGPT uses state-of-the-art deep learning techniques to process the unstructured text of 34,000,000 patents and their associated metadata and produce embeddings that are rich representations of the quality, potential impact, and other nuances of inventions." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2307.01202v1

#lg #ai #cl #DL #arxiv

Last updated 1 year ago

๐Ÿ“ Multimodal Search on Iconclass Using Vision-Language Pre-Trained Models ๐Ÿ’ฟ๐Ÿ‘พ

"The search engine is developed using a pre-trained CLIP vision-language model that is used to encode concepts in Iconclass as well as images and short textual descriptions associated with them." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/ISE-FIZKarlsruhe/ic
๐Ÿ”— arxiv.org/abs/2306.16529v1

#ir #ai #DL #arxiv

Last updated 1 year ago

arXiv Comp. Linguistics๐Ÿ“š · @arxiv_cl
155 followers · 3004 posts · Server creative.ai

๐Ÿ“ Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers ๐Ÿ“š

"A network-aware contrastive fine-tuning module and a hierarchy-aware aggregation module are designed to leverage the cross-paper network structure and the in-paper hierarchy structure of each paper, respectively." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2306.14003v1

#cl #DL #arxiv

Last updated 1 year ago

arXiv Machine Learning๐Ÿง  · @arxiv_lg
118 followers · 1992 posts · Server creative.ai

๐Ÿ“ Has the Machine Learning Review Process Become More Arbitrary as the Field Has Grown? The NeurIPS 2021 Consistency Experiment ๐Ÿง 

"We randomly selected a subset of NeurIPS (2021) submissions to be assigned to a second committee for review, and then measured the consistency between the two committees." [gal30b+] ๐Ÿค–

๐Ÿ”— arxiv.org/abs/2306.03262v1

#lg #DL #arxiv

Last updated 1 year ago

๐Ÿ“ DeepScribe: Localization and Classification of Elamite Cuneiform Signs via Deep Learning ๐Ÿ”ญ๐Ÿ’ฟ

"Develops DeepScribe, a modular computer vision pipeline that can analyze photos of cuneiform tablets from the Achaemenid period and provide useful transliteration suggestions to researchers." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/edwardclem/deepscri
๐Ÿ”— arxiv.org/abs/2306.01268v1

#cv #DL #ir #arxiv

Last updated 1 year ago

florian kofler · @neuronflow
3 followers · 10 posts · Server sigmoid.social

Ever wondered what the brain of a tumor patient looked like before they developed the disease? This question keeps doctors awake at night. Help them by joining the BraTS Inpainting Challenge!
synapse.org/#!Synapse:syn51156

#ai #machinelearning #deeplearning #computervision #glioma #ml #DL

Last updated 1 year ago

arXiv Comp. Linguistics๐Ÿ“š · @arxiv_cl
131 followers · 2570 posts · Server creative.ai

๐Ÿ“ Forgotten Knowledge: Examining the Citational Amnesia in NLP ๐Ÿ“š

"Studies NLP papers published between 1990 and June 2019 and find that 82% of papers cite at least one paper that was published within 5 years before the target paper." [gal30b+] ๐Ÿค–

โš™๏ธ github.com/iamjanvijay/
๐Ÿ”— arxiv.org/abs/2305.18554v1

#cl #DL #arxiv

Last updated 1 year ago