View as presentation
Slide 1 :public:bg19.jpg

Joint Approaches for Sentence Alignment on Multiparallel Texts

Johannes Graën
2016-11-29

↓ Slide 2

Overview

→ Slide 3

Sentence Alignment on Multiparallel Texts

↓ Slide 4

Example

de Es geht nicht um die Großzügigkeit des Präsidenten, es geht um die Zeit, die Sie sich selbst genehmigen; [1+3] ich habe Ihnen angezeigt, wann die Minute abgelaufen war. [2+3]
en Mr Izquierdo Collado, it is not a question of the President’s generosity. [3] It is a question of the time you allow yourself, because I informed you when your minute was up. [3]
fr Monsieur Izquierdo, il ne s’agit pas de la générosité du président, il s’agit du temps que vous vous attribuez. [1+3] Je vous ai fait signe quand vous avez atteint la minute. [2+3]
→ Slide 5

Agreement of Bilingual Alignments

↓ Slide 6

Approach

  1. Perform pairwise alignments with hunalign.
  2. Join all these alignments in a graph.
  3. Calculate “connectedness” by counting supporting languages for each edge.
    • How many languages align with both sentences of a particular language pair?
  4. Continue deleting the least supported edge until small consistent clusters emerge.
  5. An alignment hierarchy can be obtained by reversing the deletion process.
↓ Slide 7

Two Languages

↓ Slide 8

Three Languages

↓ Slide 9

Four Languages

↓ Slide 10

Five Languages

↓ Slide 11

Hierarchical Alignments

↓ Slide 12

Problems/Limitations

→ Slide 13

Sampling in Discrete Vector Space

↓ Slide 14

Visual Representation

↓ Slide 15

Approach

  1. Set initial aligment to a sequence of vectors approximating a diagonal line.
  2. Calculate local (pairwise) and global alignment scores (and keep results in memory).
  3. Find and evaluate all applicable sampling operations.
  4. Sample by selecting one of those operations – according to their respective evaluation scores.
  5. Lower temperature, i.e. probability of picking an operation that leads to a worse sample.
  6. Repeat from (3) until temperature reaches zero-point.
↓ Slide 16

Sampling Operations

  1. Changing two consecutive vectors $\vec{x}$ and $\vec{y}$ such that $\vec{x}^\prime + \vec{y}^\prime = \vec{x} + \vec{y}$.
  2. Replace two consecutive vectors $\vec{x}$ and $\vec{y}$ by vector $\vec{z}$ such that $\vec{z} = \vec{x} + \vec{y}$.
  3. Split a vector $\vec{z}$ into vectors $\vec{x}$ and $\vec{y}$ such that $\vec{x} + \vec{y} = \vec{z}$.
↓ Slide 17

Problems/Limitations

→ Slide 18

Agglomerative Hierarchical Clustering

↓ Slide 19

Approach

  1. Calculate scores for each a) language pair, b) source and c) sentence pair.
  2. Map the (normal) distribution of each source's scores to one with $\mu = 1$ and $\sigma = 1$ and
  3. multiply the values with a source-specific weight between 0 and 1.
  4. Sum up these score-specific values to set the link weight between each two sentences.
  5. Calculate the supported link weight based on the weight of a particular link and the link weights of all “triangles” with other languages.
  6. Use those weights for clustering.
↓ Slide 20

Approach (Clustering)

  1. Perform first agglomerative clustering such that
    1. a cluster cannot take more than one sentence of each language.
    2. crossing clusters are prohibited.
  2. Let all remaining sentences be the only member of their own cluster.
  3. Perform secondary agglomerative clustering for incomplete clusters such that
    1. crossing clusters are prohibited.
↓ Slide 21

Sources for Pairwise Scores

↓ Slide 22

Demo

→ Slide 23

Evaluation Metrics

→ Slide 24

Hierarchical Clustering for Word Alignment

Slide 25 :public:bg23.jpg

EOP