We’ve had this conversation before: A Novel Approach to Measuring Dialog Similarity

This paper adapts edit distance to measure the similarity of dialog. Specifically, for the following Minimum Edit Distance algorithm:

\begin{equation} d_{i,j} = min \begin{cases} d_{i-1, j} \hspace{10pt} + \hspace{15pt} w_{del}(a_{i}) \\ d_{i, j-1} \hspace{10pt} + \hspace{15pt} w_{ins}(b_{j}) \\ d_{i-1, j-1} + w_{sub}(a_{i}, b_{j}) \\ \end{cases} \end{equation}

they propose to define the substitution cost as:

\begin{equation} \label{eq:sub-cosine} w_{sub}(u_1^i, u_2^j) = \alpha{\times}(1-\cos(e_1^i, e_2^j)) \end{equation}

where the embeddings are from the Universal Sentence Encoder.


  • 3-min reading paper.
  • 5: Transformative: This paper is likely to change our field. It should be considered for a best paper award.
  • 4.5: Exciting: It changed my thinking on this topic. I would fight for it to be accepted.
  • 4: Strong: I learned a lot from it. I would like to see it accepted.
  • 3.5: Leaning positive: It can be accepted more or less in its current form. However, the work it describes is not particularly exciting and/or inspiring, so it will not be a big loss if people don’t see it in this conference.
  • 3: Ambivalent: It has merits (e.g., it reports state-of-the-art results, the idea is nice), but there are key weaknesses (e.g., I didn’t learn much from it, evaluation is not convincing, it describes incremental work). I believe it can significantly benefit from another round of revision, but I won’t object to accepting it if my co-reviewers are willing to champion it.
  • 2.5: Leaning negative: I am leaning towards rejection, but I can be persuaded if my co-reviewers think otherwise.
  • 2: Mediocre: I would rather not see it in the conference.
  • 1.5: Weak: I am pretty confident that it should be rejected.
  • 1: Poor: I would fight to have it rejected.

0 投票者