Lexical Chains meet Word Embeddings in Document-level Statistical Machine Translation

Abstract

The phrase-based Statistical Machine Translation (SMT) approach deals with sentences in isolation, making it difficult to consider discourse context in translation. This poses a challenge for ambiguous words that need discourse knowledge to be correctly translated. We propose a method that benefits from the semantic similarity in lexical chains to improve SMT output by integrating it in a document-level decoder. We focus on word embeddings to deal with the lexical chains, contrary to the traditional approach that uses lexical resources. Experimental results on German→English show that our method produces correct translations in up to 88% of the changes, improving the translation in 36%-48% of them over the baseline.

Document-Level Neural Machine Translation with Hierarchical Attention Networks

“…Statistical Machine Translation (SMT) Initial studies were based on cache memories (Tiede- mann, 2010; Gong et al, 2011). However, most of the work explicitly models discourse phenomena (Sim Smith, 2017) such as lexical cohesion (Meyer and Popescu-Belis, 2012;Xiong et al, 2013;Loáiciga and Grisot, 2016;Pu et al, 2017;Mascarell, 2017), coherence (Born et al, 2017), and coreference (Rios Gonzales and Tuggener, 2017;Miculicich Werlen and Popescu-Belis, 2017a). Hardmeier et al (2013) introduced the document-level SMT paradigm.…”

Selective Attention for Context-aware Neural Machine Translation

“…Conventional Document-level MT These can further be classified into two main categories. The first, which use cache-based memories (Tiedemann, 2010;Gong et al, 2011) and the second, which focus on specific discourse phenomema like anaphora (Hardmeier and Federico, 2010), lexical cohesion (Xiong et al, 2013;Gong et al, 2015;Mascarell, 2017) and coreference (Miculicich Werlen and Popescu-Belis, 2017) to name a few. Most of these approaches are, however, restrictive as they mostly involve using handcrafted features similar to the conventional MT approaches.…”

Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs

“…These words are related sequentially in the text, defining the topic of the text segment that they cover and establishing associations between sentences. Following this observation, some researchers have obtained success in many NLP tasks such as word sense induction (Tao et al, 2014) , machine translation (Mascarell, 2017) and text (Stokes et al, 2004) segmentation. In the BB-rel dataset, the sentences where inter-sentence relations occur usually express the same topic or have semantic associations each other.…”