Minh Le

I ran into an error with this tree from CoNLL-2012 dataset: ``` In [1]: import StanfordDependencies In [2]: sd = StanfordDependencies.get_instance() In [3]: sd.convert_trees(['(TOP (S (CC But) (PRN (S (NP...

Existing resource on some NLP tasks

1

See https://natural-language-understanding.wikia.com/wiki/Category:State_of_the_art List of pages: Entity coreference resolution (state-of-the-art) Event coreference resolution (state of the art) Event factuality (state-of-the-art) Implicit semantic role labelling (State-of-the-art) Knowledge base completion (state-of-the-art) Named entity...

Can't serialize document

15

I can save a Spacy document to disk but not one produced by neuralcoref. For example, the following snippet returns error `TypeError: can't serialize My sister: [My sister, She]`. ```python...

I find this behaviour counter-intuitive: if you read a corpus (using `Corpus.from_file`) and write it out right away (using `write_to_file`), all set IDs are lost, i.e. the last column contains...

AvgPool2d (kernel_size=1)

5

In `vgg.py` I found this line: `layers += [nn.AvgPool2d(kernel_size=1, stride=1)]` . Do I understand correctly that AvgPool2d layers with kernel_size=1 just return the input as it is? Why do we...

String matching features?

3

I'm reading Clark and Manning (2016) and the list of features include "String Matching Features: Head match, exact string match, and partial string match." I look at [datasets.py](https://github.com/clarkkev/deep-coref/blob/master/datasets.py) but can't...

Segmentation fault with the program "score"

1

It doesn't say anything else. ``` $ OxLM-2017-10-09/bin/score -m output/lb-ec-chain.bin.ea34c9f24e06de6e957ea32f53ca9d72fe3a2e9e -t 3 -d output/ec_fn_chain_as_sentences.dev.unk.txt Loading model from output/lb-ec-chain.bin.ea34c9f24e06de6e957ea32f53ca9d72fe3a2e9e... Reading model took 40.19 seconds... Reading test corpus... Done reading test corpus......

Tests fail

3

I downloaded and built OxLM today and two tests failed. What should I do now? ``` [ FAILED ] MaxentSGDTest.TestTrainMaxentNCEExtractedNGrams (2410 ms) [----------] 4 tests from MaxentSGDTest (8846 ms total)...

Loading a big graph is slow

2

I tried running the [random walk example](https://github.com/snap-stanford/snap/blob/master/examples/randwalk/randwalk.cpp) on a graph of 1.1B edges and it took 37 min just to load the graph into memory. How can we improve this...