CAREA: Cotraining Attribute and Relation Embeddings for Cross-Lingual Entity Alignment in Knowledge Graphs

<div><svg height="10.5908pt" id="M200" style="vertical-align:-1.30247pt" version="1.1" viewbox="-0.0498162 -9.28833 42.7351 10.5908" width="42.7351pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M729 650H468V622C546 615 554 610 554 527V365H213V527C213 610 221 616 297 622V650H38V622C120 616 128 611 128 527V123C128 39 120 34 40 28V0H303V28C221 34 213 40 213 123V322H554V123C554 39 546 34 460 28V0H728V28C647 34 639 39 639 123V527C639 610 647 615 729 622V650Z"></path></g><g transform="matrix(.013,0,0,-0.013,9.749,0)"><path d="M135 536C164 536 186 560 186 587C186 617 164 639 136 639C109 639 85 617 85 587C85 560 109 536 135 536ZM252 0V26C188 32 181 38 181 106V451C138 433 90 420 39 412V388C99 379 102 374 102 312V106C102 38 95 32 32 26V0H252Z"></path></g><g transform="matrix(.013,0,0,-0.013,13.077,0)"><path d="M298 36L289 62C276 55 253 45 228 45C202 45 169 60 169 141V397H276C289 405 292 426 282 437H169V574L155 576L90 509V437H45L17 408L21 397H90V107C90 28 125 -12 188 -12C198 -12 213 -8 230 1L298 36Z"></path></g><g transform="matrix(.013,0,0,-0.013,17.042,0)"><path d="M319 325C317 349 306 409 297 431C277 440 250 449 209 449C117 449 57 389 57 319C57 243 122 209 182 182C232 159 261 135 261 91C261 48 227 21 190 21C130 21 85 79 68 145L41 140C41 104 51 36 58 22C75 7 121 -12 172 -12C252 -12 337 35 337 126C337 195 286 231 210 262C166 281 126 304 126 348C126 388 152 417 191 417C240 417 274 378 294 318L319 325Z"></path></g><g transform="matrix(.013,0,0,-0.013,24.071,0)"><path d="M545 -14C518 -29 444 -52 385 -52C186 -52 116 86 116 218C116 404 241 540 428 540C565 540 665 460 665 322C665 187 587 118 519 116C494 115 490 128 500 181C515 263 532 343 548 408C538 408 528 409 514 412C501 415 479 420 464 420C402 419 348 388 303 346C245 290 223 213 223 158C223 100 247 74 271 74C317 74 408 155 441 204L443 203L432 145C424 104 424 74 477 74C611 74 713 186 713 322C713 459 612 579 433 579C241 579 53 442 52 208C52 5 195 -97 352 -97C421 -97 486 -83 556 -42L545 -14ZM422 380C442 380 464 375 477 369C472 339 462 291 452 258C392 175 338 138 320 138C308 138 299 147 299 183C299 247 328 318 357 350C374 368 396 380 422 380Z"></path></g><g transform="matrix(.013,0,0,-0.013,36.036,0)"><path d="M480 416C480 431 465 448 438 448C388 448 312 383 252 330C217 299 188 273 155 237H153L257 680C262 700 263 712 253 712C240 712 183 684 97 674L92 648L126 647C166 646 172 645 163 606L23 -6L29 -12C51 -5 77 2 107 8C115 62 130 128 142 180C153 193 179 220 204 241C231 170 259 106 288 54C317 0 336 -12 358 -12C381 -12 423 2 477 80L460 100C434 74 408 54 398 54C385 54 374 65 351 107C326 154 282 241 263 299C296 332 351 377 403 377C424 377 436 372 445 368C449 366 456 368 462 375C472 386 480 402 480 416Z"></path></g></svg> on entity alignment with respect to the proportion of training data. (a) DBP<sub>ZH-EN</sub>. (b) DBP<sub>JA-EN</sub>. (c) DBP<sub>FR-EN</sub>.</div>

Discrete Dynamics in Nature and Society

fig4

Figure 4

Figure 4: CAREA: Cotraining Attribute and Relation Embeddings for Cross-Lingual Entity Alignment in Knowledge Graphs 