Fusing Logical Relationship Information of Text in Neural Network for Text Classification

<div>FLRIOTINN. <i>d</i>: length of Dic; <i>c</i>: total number of categories; <span class="nowrap"><svg height="5.76278pt" id="M31" style="vertical-align:-0.1150403pt" version="1.1" viewbox="-0.0498162 -5.64774 9.2207 5.76278" width="9.2207pt" 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="M699 442H515V410C577 401 582 389 573 351C563 308 532 208 517 161H515C476 254 437 345 401 437H362C326 342 293 250 258 163H256C237 225 217 294 197 358C186 392 192 401 250 410V442H3V410C45 405 55 395 71 347C108 235 151 112 191 -11H229C267 84 302 175 340 268C377 177 418 83 457 -11H495C545 129 587 249 623 342C644 394 651 402 699 410V442Z"></path></g></svg>:</span> weight; <b>b</b>: bias; <b>F</b>: activation function.</div>

Mathematical Problems in Engineering

fig4

Figure 4

Figure 4: Fusing Logical Relationship Information of Text in Neural Network for Text Classification 