Here you can find all my previous posts:
Now, how can this be applied to a natural language setting? Once we have word embeddings, we can consider that the vocabulary forms a metric space (we can compute a distance, for instance the euclidean or the cosine distance, between two word embeddings). The key is to define documents as distributions over words.
Given a vocabulary \(V \subset \mathbb{R}^n\) and a corpus \(D = (d^1, d^2, \ldots, d^{\lvert D \rvert})\), we represent a document as \(d^i \in \Delta^{l_i}\) where \(l_i\) is the number of unique words in \(d^i\), and \(d^i_j\) is the proportion of word \(v_j\) in the document \(d^i\). The word mover’s distance (WMD) is then defined simply as \[ \operatorname{WMD}(d^1, d^2) = W_1(d^1, d^2). \]
diff --git a/_site/contact.html b/_site/contact.html index 0a552a2..3078e9d 100644 --- a/_site/contact.html +++ b/_site/contact.html @@ -15,19 +15,9 @@ - - - - - - - - - - - - - + + +Now, how can this be applied to a natural language setting? Once we have word embeddings, we can consider that the vocabulary forms a metric space (we can compute a distance, for instance the euclidean or the cosine distance, between two word embeddings). The key is to define documents as distributions over words.
Given a vocabulary \(V \subset \mathbb{R}^n\) and a corpus \(D = (d^1, d^2, \ldots, d^{\lvert D \rvert})\), we represent a document as \(d^i \in \Delta^{l_i}\) where \(l_i\) is the number of unique words in \(d^i\), and \(d^i_j\) is the proportion of word \(v_j\) in the document \(d^i\). The word mover’s distance (WMD) is then defined simply as \[ \operatorname{WMD}(d^1, d^2) = W_1(d^1, d^2). \]
diff --git a/_site/posts/iclr-2020-notes.html b/_site/posts/iclr-2020-notes.html index 8d89179..d72c81e 100644 --- a/_site/posts/iclr-2020-notes.html +++ b/_site/posts/iclr-2020-notes.html @@ -15,19 +15,9 @@ - - - - - - - - - - - - - + + +Now, how can this be applied to a natural language setting? Once we have word embeddings, we can consider that the vocabulary forms a metric space (we can compute a distance, for instance the euclidean or the cosine distance, between two word embeddings). The key is to define documents as distributions over words.
Given a vocabulary \(V \subset \mathbb{R}^n\) and a corpus \(D = (d^1, d^2, \ldots, d^{\lvert D \rvert})\), we represent a document as \(d^i \in \Delta^{l_i}\) where \(l_i\) is the number of unique words in \(d^i\), and \(d^i_j\) is the proportion of word \(v_j\) in the document \(d^i\). The word mover’s distance (WMD) is then defined simply as \[ \operatorname{WMD}(d^1, d^2) = W_1(d^1, d^2). \]
diff --git a/_site/skills.html b/_site/skills.html index 45d5d32..9bdce8a 100644 --- a/_site/skills.html +++ b/_site/skills.html @@ -15,19 +15,9 @@ - - - - - - - - - - - - - + + +Here you can find all my previous posts:
$partial("templates/post-list.html")$