File:N16-1030 fig1.png
N16-1030_fig1.png (491 × 374 pixels, file size: 49 KB, MIME type: image/png)
Figure 1: Main architecture of the network. Word embeddings are given to a bidirectional LSTM. [math]\displaystyle{ l_i }[/math] represents the word i and its left context, [math]\displaystyle{ r_i }[/math] represents the word i and its right context. Concatenating these two vectors yields a representation of the word i in its context, [math]\displaystyle{ c_i }[/math].
In: Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. (2016). “Neural Architectures for Named Entity Recognition.” In: Proceedings of NAACL-HLT.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 22:44, 17 June 2018 | | 491 × 374 (49 KB) | Omoreira (talk | contribs) | Figure 1: Main architecture of the network. Word embeddings are given to a bidirectional LSTM. <math>l_i</math> represents the word <i>i</i> and its left context, <math>r_i</math> represents the word <i>i</i> and its right context. [[Concat... |
You cannot overwrite this file.
File usage
The following 2 pages use this file:
