In this paper, we study how humans perceive the use of images as an additional knowledge source to machine-translate usergenerated product listings in an e-commerce company. We conduct a human evaluation where we assess how a multi-modal neural machine translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attention-based NMT and a phrase-based statistical...

Example-based machine translation (EBMT) is based on a bilingual corpus. In EBMT, sentences similar to an input sentence are retrieved from a bilingual corpus and then output is generated from translations of similar sentences. Therefore, a similarity measure between the input sentence and each sentence in the bilingual corpus is important for EBMT. If some similar sentences are missed from ret...

This article shows how CGLF, CGIF, KIF, Formalized-English and Frame-CG can be used in a panorama of knowledge representation cases. It highlights various inadequacies of CGLF and CGIF, advantages provided by high-level expressive notations, and the KIF translations provide a logical interpretation. Knowledge providers may see this document as a guide for knowledge representation. Developers ma...

Multiple target translations are due to several meanings of source words, and various target word equivalents depending on the context of the source word. Thus, an automated approach is presented for resolving target-word selection, based on “word-to-sense” and “sense-to-word” source-translation relationships, using syntactic relationships (subject-verb, verb-object, adjectivenoun). Translation...

We report experiments on automatic learning of an English-Chinese translation lexicon, through statistical training on a large parallel corpus. The learned vocabulary size is nontrivial at 6,517 English words averaging 2.33 Chinese translations per entry, with a manuallyfiltered precision of 95.1% and a single-most-probable precision of 91.2%. We then introduce a significance filtering method t...

This paper introduces the logical basis for mod­ elling the phenomenon of reasoning in the pres­ ence of contradiction, by identifying this prob­ lem with the notion of change of context. We give here the basic definitions of a new seman­ tics, which works by interpreting one logic into a family of logics via translations, which we call semantics of translations. As a particular ap­ plication w...

We report experiments on automatic learning of an English-Chinese translation lexicon, through statistical training on a large parallel corpus. The learned vocabulary size is non-trivial at 6,517 English words averaging 2.33 Chinese translations per entry, with a manually-ltered precision of 95.1% and a single-most-probable precision of 91.2%. We then introduce a signiicance ltering method that...

We carried out a comparison of cross-language retrieval methods on the NTCIR-1 data based on dimension reduction (latent semantic indexing). These methods all use a collection parallel documents (translations or approximate translations) and very little, if any, linguistic knowledge. In NTCIR-1, we compared latent semantic indexing, local LSI, and approximate dimensional equalization (ADE). We ...

Multiple translations to the target language are due to several meanings of source words and various target word equivalents, depending on the context of the source word. Thus, an automated approach is presented for resolving target-word selection, based on “word-to-sense” and “sense-to-word” relationship between source words and their translations, using syntactic relationships (subject-verb, ...