Manifold-Constrained Sentence Embeddings via Triplet Loss: Projecting Semantics onto Spheres, Tori, and Möbius Strips

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Chavan, Vinit K.
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Testing Cross-Lingual Text Comprehension In LLMs Using Next Sentence Prediction
par: Chavan, Ritesh Sunil, et autres
Publié: (2025)

More Discriminative Sentence Embeddings via Semantic Graph Smoothing
par: Fettal, Chakib, et autres
Publié: (2024)

Sentence Representations via Gaussian Embedding
par: Yoda, Shohei, et autres
Publié: (2023)

Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing
par: Bedratyuk, Leonid
Publié: (2026)

Static Word Embeddings for Sentence Semantic Representation
par: Wada, Takashi, et autres
Publié: (2025)

Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform
par: Salama, Rana Aref, et autres
Publié: (2025)

Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity
par: Rep, Ivan, et autres
Publié: (2024)

CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
par: Zhang, Gaifan, et autres
Publié: (2025)

One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
par: Oda, Kohei, et autres
Publié: (2025)

Text Simplification with Sentence Embeddings
par: Shardlow, Matthew
Publié: (2025)

Space Decomposition for Sentence Embedding
par: Ponwitayarat, Wuttikorn, et autres
Publié: (2024)

Latent Reasoning via Sentence Embedding Prediction
par: Hwang, Hyeonbin, et autres
Publié: (2025)

Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Texts
par: Lamsal, Rabindra, et autres
Publié: (2024)

Set-Theoretic Compositionality of Sentence Embeddings
par: Bansal, Naman, et autres
Publié: (2025)

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment
par: Chen, Ziyang, et autres
Publié: (2026)

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
par: Opitz, Juri, et autres
Publié: (2022)

Vec2Summ: Text Summarization via Probabilistic Sentence Embeddings
par: Li, Mao, et autres
Publié: (2025)

Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation
par: Chen, Zihao, et autres
Publié: (2025)

Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
par: He, Liyang, et autres
Publié: (2025)

Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
par: Barančíková, Petra, et autres
Publié: (2025)

Edit-Constrained Decoding for Sentence Simplification
par: Zetsu, Tatsuya, et autres
Publié: (2024)

Sign Language Translation with Sentence Embedding Supervision
par: Hamidullah, Yasser, et autres
Publié: (2025)

TransAug: Translate as Augmentation for Sentence Embeddings
par: Wang, Jue
Publié: (2021)

Linear Cross-Lingual Mapping of Sentence Embeddings
par: Vasilyev, Oleg, et autres
Publié: (2023)

UNSEE: Unsupervised Non-contrastive Sentence Embeddings
par: Çağatan, Ömer Veysel
Publié: (2024)

2D Matryoshka Sentence Embeddings
par: Li, Xianming, et autres
Publié: (2024)

SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
par: Zhu, Yuxuan, et autres
Publié: (2025)

LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
par: Zhang, Yeqin, et autres
Publié: (2026)

Sentence Embeddings as an intermediate target in end-to-end summarisation
par: Zembrzuski, Maciej, et autres
Publié: (2025)

Sentence Smith: Controllable Edits for Evaluating Text Embeddings
par: Li, Hongji, et autres
Publié: (2025)

Adaptative Bilingual Aligning Using Multilingual Sentence Embedding
par: Kraif, Olivier
Publié: (2024)

Making Sentence Embeddings Robust to User-Generated Content
par: Nishimwe, Lydia, et autres
Publié: (2024)

SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval
par: Adams, Griffin, et autres
Publié: (2024)

T-VEC: A Telecom-Specific Vectorization Model with Enhanced Semantic Understanding via Deep Triplet Loss Fine-Tuning
par: Ethiraj, Vignesh, et autres
Publié: (2025)

Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss
par: He, Wei, et autres
Publié: (2024)

OrderSum: Semantic Sentence Ordering for Extractive Summarization
par: Kwon, Taewan, et autres
Publié: (2025)

Comateformer: Combined Attention Transformer for Semantic Sentence Matching
par: Li, Bo, et autres
Publié: (2024)

Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding
par: Salama, Rana, et autres
Publié: (2025)

EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning
par: Mao, Zhuoyuan, et autres
Publié: (2022)

Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization
par: Chellaf, Chaimae, et autres
Publié: (2026)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
VUFIND_SESSION	"32141a54f5b9e02f3725ec4d088c9d56"
language	"fr"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790902605.9674 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "32141a54f5b9e02f3725ec4d088c9d56" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"VUFIND_SESSION=32141a54f5b9e02f3725ec4d088c9d56; language=fr; ui=standard"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"33988"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_00014/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2505_00014/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790902605.9558
REQUEST_TIME	1790902605

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler