The complexity of phrase alignment problems

Abstract

Many phrase alignment models operate over the combinatorial space of bijective phrase alignments. We prove that finding an optimal alignment in this space is NP-hard, while computing alignment expectations is #P-hard. On the other hand, we show that the problem of finding an optimal alignment can be cast as an integer linear program, which provides a simple, declarative approach to Viterbi inference for phrase alignment models that is empirically quite efficient.

A phrase-based alignment model for natural language inference

“…Unfortunately, word alignment models assume that source words are individually trans-lated into target words, which stands at odds with the key assumption in phrase-based systems that many translations are non-compositional. More recently, several works (Marcu and Wong, 2002;DeNero et al, 2006;Birch et al, 2006;DeNero and Klein, 2008) have presented more unified phrasebased systems that jointly align and weight phrases, though these systems have not come close to the state of the art when evaluated in terms of MT performance.…”

Building Multiword Expressions Bilingual Lexicons for Domain Adaptation of an Example-Based Machine Translation System

“…The first strat-662 egy consists to acquire translations of phrases from parallel corpora in one step. Phrases are not necessary MWEs, they are contiguous sequences of a few words that encapsulate enough context to be translatable (DeNero and Klein, 2008;Marchand and Semmar, 2011). The second strategy firstly, identifies monolingual MWEs candidates and then applies alignment approaches to find bilingual correspondences (Daille et al, 1994;Blank, 2000;Barbu, 2004).…”

“…The identification and the alignment of MWEs from parallel texts is a complex task (Sag et al, 2002;Hurskainen, 2008;DeNero and Klein, 2008;Bouamor et al, 2012;Ramisch, 2014;Semmar and Laib, 2017). Statistical approaches for word alignment (Brown et al, 1993) are unable to handle many-to-many alignments and as a result they cannot take into account correctly MWEs present in parallel corpora.…”

Consistency-Aware Search for Word Alignment

“…Modeling structural constraints in alignment has received intensive attention in the community, either directly modeling phrase-to-phrase alignment (Marcu and Wong, 2002;DeNero and Klein, 2008;Cohn and Blunsom, 2009) or intersecting synchronous grammars with alignment (Wu, 1997;Zhang and Gildea, 2005;Haghighi et al, 2009). …”

“…Wordaligned bilingual corpora serve as a fundamental resource for translation rule extraction, not only for phrase-based models (Koehn et al, 2003;Och and Ney, 2004), but also for syntax-based models (Chiang, 2005;Galley et al, 2006). Dividing alignment and extraction into two separate steps significantly improves the efficiency and scalability of parameter estimation as compared with directly learning translation models from bilingual * Corresponding author: Yang Liu. corpora (Marcu and Wong, 2002;DeNero and Klein, 2008;Cohn and Blunsom, 2009). …”