Tootfinder

Opt-in global Mastodon full text search. Join the index!

@netzschleuder@social.skewed.de
2025-08-21 00:00:05

bag_of_words: Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. .
This network has 13919 nodes and 746316 edges.
Tags: Informational, Text, Bipartite, Weighted, Metadata

bag_of_words: Bag of words (2008). 13919 nodes, 746316 edges. https://networks.skewed.de/net/bag_of_words#nips

bag_of_words — Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. After tokenization and removal of stopwords, the vocabulary of unique words was truncated by only keeping words that occurred more than ten times. Individual document names (i.e. a identifier for each docID) are not provided for copyright reasons.

@netzschleuder@social.skewed.de
2025-07-16 20:00:06

bag_of_words: Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. .
This network has 67963 nodes and 3710420 edges.
Tags: Informational, Text, Bipartite, Weighted, Metadata
…

bag_of_words: Bag of words (2008). 67963 nodes, 3710420 edges. https://networks.skewed.de/net/bag_of_words#enron

bag_of_words — Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. After tokenization and removal of stopwords, the vocabulary of unique words was truncated by only keeping words that occurred more than ten times. Individual document names (i.e. a identifier for each docID) are not provided for copyright reasons.

@arXiv_csSE_bot@mastoxiv.page
2025-08-26 09:04:56

TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings
Md Afif Al Mamun, Gias Uddin, Lan Xia, Longyu Zhang
arxiv.org/abs/2508.16860

TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings
Pretrained Language Models or PLMs are transformer-based architectures that can be used in bug triaging tasks. PLMs can better capture token semantics than traditional Machine Learning (ML) models that rely on statistical features (e.g., TF-IDF, bag of words). However, PLMs may still attend to less relevant tokens in a bug report, which can impact their effectiveness. In addition, the model can be sub-optimal with its recommendations when the interaction history of developers around similar bug…

@netzschleuder@social.skewed.de
2025-08-08 06:00:14

bag_of_words: Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. .
This network has 402660 nodes and 69679427 edges.
Tags: Informational, Text, Bipartite, Weighted, Metadata

bag_of_words: Bag of words (2008). 402660 nodes, 69679427 edges. https://networks.skewed.de/net/bag_of_words#nytimes

bag_of_words — Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. After tokenization and removal of stopwords, the vocabulary of unique words was truncated by only keeping words that occurred more than ten times. Individual document names (i.e. a identifier for each docID) are not provided for copyright reasons.

@netzschleuder@social.skewed.de
2025-06-05 01:00:04

bag_of_words: Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. .
This network has 10336 nodes and 353160 edges.
Tags: Informational, Text, Bipartite, Weighted, Metadata

bag_of_words: Bag of words (2008). 10336 nodes, 353160 edges. https://networks.skewed.de/net/bag_of_words#kos

bag_of_words — Bag of words (2008)
Five text collections in the form of bags-of-words, i.e. a bipartite document–word network. Left nodes are documents and right nodes are words. Edge weights are multiplicities. After tokenization and removal of stopwords, the vocabulary of unique words was truncated by only keeping words that occurred more than ten times. Individual document names (i.e. a identifier for each docID) are not provided for copyright reasons.

@arXiv_csCV_bot@mastoxiv.page
2025-07-11 10:20:01

CLIP Won't Learn Object-Attribute Binding from Natural Data and Here is Why
Bijay Gurung, David T. Hoffmann, Thomas Brox
arxiv.org/abs/2507.07985

CLIP Won't Learn Object-Attribute Binding from Natural Data and Here is Why
Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite their popularity, their representations show major limitations. For instance, CLIP models learn bag-of-words representations and, as a consequence, fail to distinguish whether an image is of "a yellow submarine and a blue bus" or "a blue submarine and a yellow bus". Previous attempts to fix this issue added hard negative…