http://index.cslt.org/mediawiki/index.php?action=history&feed=atom&title=Dongxu_Zhang_2016-03-07Dongxu Zhang 2016-03-07 - 版本历史2026-04-09T06:19:38Z本wiki的该页面的版本历史MediaWiki 1.23.3http://index.cslt.org/mediawiki/index.php?title=Dongxu_Zhang_2016-03-07&diff=19267&oldid=prev2016年3月7日 (一) 01:25 Zhangdx2016-03-07T01:25:23Z<p></p>
<table class='diff diff-contentalign-left'>
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr style='vertical-align: top;'>
<td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td>
<td colspan='2' style="background-color: white; color:black; text-align: center;">2016年3月7日 (一) 01:25的版本</td>
</tr><tr><td colspan="2" class="diff-lineno">第3行：</td>
<td colspan="2" class="diff-lineno">第3行：</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>* Similar pair with sampling method to create more training data.</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>* Similar pair with sampling method to create more training data.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>* compare different strategies.(attention input)</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>* compare different strategies.(attention input)</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>   1. use source sentence pairs to create more data. and then sample co-occurred words with similar pair map. Other words in the core lexicon including zhuci, tanci, jieci map to themselves and words out of lexicon map to <unk>. (create a lot of <unk> when decoding)</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>   1. use source sentence pairs to create more data. and then sample co-occurred words with similar pair map.  </div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>   2. sample co-occurred words with similar pairs. Other words in the core lexicon including zhuci, tanci, jieci map to themselves and words out of lexicon map to <unk>. (can alignment in some extent.)</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">    </ins>Other words in the core lexicon including zhuci, tanci, jieci map to themselves and words out of lexicon  </div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">    </ins>map to <unk>. (create a lot of <unk> when decoding)</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>   2. sample co-occurred words with similar pairs. Other words in the core lexicon including zhuci, tanci, jieci  </div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">    </ins>map to themselves and words out of lexicon map to <unk>. (can alignment in some extent.)</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   3. sample all the words except zhuci, tanci, jieci. （worse than 2. in alignment performance）</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   3. sample all the words except zhuci, tanci, jieci. （worse than 2. in alignment performance）</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   4. sample words out of lexicon, and map words in the lexicon to themselves.(competitive to 2.)</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   4. sample words out of lexicon, and map words in the lexicon to themselves.(competitive to 2.)</div></td></tr>
</table>Zhangdxhttp://index.cslt.org/mediawiki/index.php?title=Dongxu_Zhang_2016-03-07&diff=19254&oldid=prevZhangdx：以“Last Week ---- * Similar pair with sampling method to create more training data. * compare different strategies.(attention input) 1. use source sentence pairs to c...”为内容创建页面2016-03-07T00:57:45Z<p>以“Last Week ---- * Similar pair with sampling method to create more training data. * compare different strategies.(attention input) 1. use source sentence pairs to c...”为内容创建页面</p>
<p><b>新页面</b></p><div>Last Week<br />
----<br />
* Similar pair with sampling method to create more training data.<br />
* compare different strategies.(attention input)<br />
1. use source sentence pairs to create more data. and then sample co-occurred words with similar pair map. Other words in the core lexicon including zhuci, tanci, jieci map to themselves and words out of lexicon map to <unk>. (create a lot of <unk> when decoding)<br />
2. sample co-occurred words with similar pairs. Other words in the core lexicon including zhuci, tanci, jieci map to themselves and words out of lexicon map to <unk>. (can alignment in some extent.)<br />
3. sample all the words except zhuci, tanci, jieci. （worse than 2. in alignment performance）<br />
4. sample words out of lexicon, and map words in the lexicon to themselves.(competitive to 2.)<br />
* Ask Bingdong for POS corpus.<br />
<br />
This Week<br />
----<br />
* split fujitsu data into training and testing data. And evaluate with hit@1<br />
* evaluate 2. 3. 4. model.<br />
* evaluate model that only mapping nouns if Bingdong provide the POS corpus.<br />
* attention both input and hidden layer. And try to initialize word embedding matrix with word vector.</div>Zhangdx