Update link to Hoffman paper (online VB LDA)

The previous link was Matthew Hoffman's Google Scholar profile or not the official one.
Use full author names in the first occurrence and first author only afterward.

Author: jonaschn

gensim/models/ldamodel.py

@@ -13,9 +13,10 @@
 for online training.
 
 The core estimation code is based on the `onlineldavb.py script
-<https://github.com/blei-lab/onlineldavb/blob/master/onlineldavb.py>`_, by `Hoffman, Blei, Bach:
+<https://github.com/blei-lab/onlineldavb/blob/master/onlineldavb.py>`_, by
+`Matthew D. Hoffman, David M. Blei, Francis Bach:
 Online Learning for Latent Dirichlet Allocation, NIPS 2010
-<https://scholar.google.com/citations?hl=en&user=IeHKeGYAAAAJ&view_op=list_works>`_.
+<https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
 
 The algorithm:
 
@@ -199,7 +200,7 @@ def blend(self, rhot, other, targetsize=None):
         The number of documents is stretched in both state objects, so that they are of comparable magnitude.
         This procedure corresponds to the stochastic gradient update from
         `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-        <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_, see equations (5) and (9).
+        <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_, see equations (5) and (9).
 
         Parameters
         ----------
@@ -311,8 +312,9 @@ def load(cls, fname, *args, **kwargs):
 
 
 class LdaModel(interfaces.TransformationABC, basemodel.BaseTopicModel):
-    """Train and use Online Latent Dirichlet Allocation (OLDA) models as presented in
-    `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+    """Train and use Online Latent Dirichlet Allocation models as presented in
+    `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+    <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
 
     Examples
     -------
@@ -395,12 +397,12 @@ def __init__(self, corpus=None, num_topics=100, id2word=None,
         decay : float, optional
             A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
             when each new document is examined. Corresponds to Kappa from
-            `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
         offset : float, optional
             Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
-            Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            Corresponds to Tau_0 from `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
         eval_every : int, optional
             Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x.
         iterations : int, optional
@@ -643,7 +645,7 @@ def inference(self, chunk, collect_sstats=False):
         """Given a chunk of sparse document vectors, estimate gamma (parameters controlling the topic weights)
         for each document in the chunk.
 
-        This function does not modify the model The whole input chunk of document is assumed to fit in RAM;
+        This function does not modify the model. The whole input chunk of document is assumed to fit in RAM;
         chunking of a large corpus must be done earlier in the pipeline. Avoids computing the `phi` variational
         parameter directly using the optimization presented in
         `Lee, Seung: Algorithms for non-negative matrix factorization"
@@ -863,8 +865,8 @@ def update(self, corpus, chunksize=None, decay=None, offset=None,
         This update also supports updating an already trained model with new documents; the two models are then merged
         in proportion to the number of old vs. new documents. This feature is still experimental for non-stationary
         input streams. For stationary input (no topic drift in new documents), on the other hand, this equals the
-        online update of `Matthew D. Hoffman, David M. Blei, Francis Bach:
-        "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+        online update of `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+        <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_
         and is guaranteed to converge for any `decay` in (0.5, 1.0). Additionally, for smaller corpus sizes, an
         increasing `offset` may be beneficial (see Table 1 in the same paper).
 
@@ -878,12 +880,12 @@ def update(self, corpus, chunksize=None, decay=None, offset=None,
         decay : float, optional
             A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
             when each new document is examined. Corresponds to Kappa from
-            `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
         offset : float, optional
             Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
-            Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            Corresponds to Tau_0 from `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
+            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
         passes : int, optional
             Number of passes through the corpus during training.
         update_every : int, optional