Surprisingly BLEU-2 performed better than any other n-grams for reasons that have yet to be examined.

Total n-grams 35,531 33,891 32,251 30,611

Table 1: n-grams confirmed by the reference and containing error flags.

The suspicious cases are n-grams confirmed by the reference but still containing a flag (false positives) and n-grams not confirmed despite containing no error flag (false negatives).

For the web baseline (reported as Google), we stemmed all words in the Google n-grams and counted every verb 2) and noun n that appear in Gigaword.

The dotted line uses Google n-grams as training.

We also avoided over-counting co-occurrences in lower order n-grams that appear again in 4 or 5 - grams.

We adopt a representation of concepts alternative to n-grams and propose two concept—scoring functions based on semantic overlap.

To represent sentences and answers we adopted an alternative approach to classical n-grams that could be defined bag-of-BEs.

Different from n-grams , they are variant in length and depend on parsing techniques, named entity detection, part-of-speech tagging and resolution of syntactic forms such as hyponyms, pronouns, per-tainyms, abbreviation and synonyms.

To provide information related to term usage to the classifier, we extracted trigram and 4-gram features from the Web lT Corpus (Brants and Franz, 2006), a large collection of n-grams and their counts created from approximately one trillion words of Web text.

Only n-grams containing lowercase words were used.

Only n-grams containing both terms (including plural forms) were extracted.

where gn(s) is the multi-set of all n-grams in a string s. In this definition, n-grams in e,~ and {rij} are weighted by Dt(i).

If the i-th training sample has a larger weight, the corresponding n-grams will have more contributions to the overall score WBLEU(E,R) .

In this method, a n-gram cache is used to store the most frequently and recently accessed n-grams .