In future work, we would like to investigate the use of other distance functions, in particular the use of approximate tree edit distance functions such as the pq-gram algorithm (Augsten et al., 2005).

For large data sets such as the PCEDT set used in this work, computing 04 with tree edit distance as the distance measure can take a very long time.8 This is due to the fact that 04 requires 0(n2) comparisons to be made, each of which is 0(n2) using our current approach.

In this article we propose a family of chance-corrected measures of agreement, applicable to both dependency- and constituency-based syntactic annotation, based on Krippendorff’s 04 and tree edit distance .

The idea of using edit distance as the basis for an inter-annotator agreement metric has previously been explored by Fournier (2013).

However that work used a boundary edit distance as the basis of a metric for the task of text segmentation.

Instead, we propose to use an agreement measure based on Krippendorff’s a (Krippendorff, 1970; Krippendorff, 2004) and tree edit distance .

Instead, we base our work on tree edit distance .

The tree edit distance (TED) problem is defined analogously to the more familiar problem of string edit distance : what is the minimum number of edit operations required to transform one tree into the other?

0 We compute the normalized edit distance between the system’s output and a human-generated Chinglish reference.

We measure the normalized edit distance against an English reference.

the test portion of our phrasebook, using edit distance .

The average edit distance of phoneme-phrase model and that of hybrid training/decoding model are close, indicating that long phoneme-phrase pairs can emulate word-pinyin mappings.

MOdeI Edit Distance Reference English 0.477 Phoneme based 0.696 Hybrid training and decoding 0.496

If the user prefix cannot be found in the search graph, approximate string matching is used by finding a path with minimal string edit distance , i.e., a path in the graph with the minimal number of insertions, deletions and substitutions to match the user prefix.

Cost is measured primarily in terms of string edit distance (number of deletions, insertions and substitutions), and secondary in terms of translation model score for the matched path in the graph.

ms 5 1015 20 25 30 35 40pX Figure 1: Average response time of baseline method based on length of the prefix and number of edits: The main bottleneck is the string edit distance between prefix and path.

the length of the user prefix and the string edit distance between the user prefix and the search graph.

We attempt to find the last word in the predicted path either before or after the optimal matching position according to string edit distance .

tion output is a better fallback than computing optimal string edit distance .

Dissimilarity is measured as letter edit distance

We employ several orthographic metrics widely used in this research area: the edit distance (Levenshtein, 1965), the longest common subsequence ratio (Melamed, 1995) and the XDice metric (Brew and McKelvie, l996)4.

In addition, we use SpSim (Gomes and Lopes, 2011), which outperformed the longest common subsequence ratio and a similarity measure based on the edit distance in previous experiments.

For the edit distance , we subtract the normalized value from 1 in order to obtain similarity.

Therefore, because the edit distance was widely used in this research area and produced good results, we are encouraged to employ orthographic alignment for identifying pairs of cognates, not only to compute similarity scores, as was previously done, but to use aligned subsequences as features for machine learning algorithms.

(2013) proposed a method for cognate production relying on statistical character-based machine translation, learning orthographic production patterns, and Mulloni (2007) introduced an algorithm for cognate production based on edit distance alignment and the identification of orthographic cues when words enter a new language.

We calculate the edit distance between the two transcripts at the character and word level, as well as the two most similar phonetic rewrites.

Of the similarity features, the ones that contributed significantly in the final model were character edit distance (normalized) and phoneme edit distance (raw and normalized); as expected, retries are associated with more similar query pairs.

T-tests between the two categories showed that all edit distance features—character, word, reduced, and phonetic; raw and normalized—are significantly more similar between retry query pairs.1 Similarly, the number of unigrams the two queries have in common is significantly higher for retries.

Most notably, all edit distance features are significantly greater for rephrases.

Number of Edits Table 4 indicates the edit distance of the output sentences w.r.t.

In sum, the automatic metrics indicate that our system produces simplification that are consistently closest to the reference in terms of edit distance , number of splits and BLEU score.

The governing criteria for the construction of the training graph is that, at each step, it tries to minimize the Leven-shtein edit distance between the complex and the simple sentences.