Collocation extraction using monolingual word alignment method

Abstract

Statistical bilingual word alignment has been well studied in the context of machine translation. This paper adapts the bilingual word alignment algorithm to monolingual scenario to extract collocations from monolingual corpus. The monolingual corpus is first replicated to generate a parallel corpus, where each sentence pair consists of two identical sentences in the same language. Then the monolingual word alignment algorithm is employed to align the potentially collocated words in the monolingual sentences. Finally the aligned word pairs are ranked according to refined alignment probabilities and those with higher scores are extracted as collocations. We conducted experiments using Chinese and English corpora individually. Compared with previous approaches, which use association measures to extract collocations from the co-occurring word pairs within a given window, our method achieves higher precision and recall. According to human evaluation in terms of precision, our method achieves absolute improvements of 27.9% on the Chinese corpus and 23.6% on the English corpus, respectively. Especially, we can extract collocations with longer spans, achieving a high precision of 69% on the long-span (>6) Chinese collocations.