This paper describes the techniques we explored to improve the translation of news text in the German-English and HungarianEnglish tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and...

This paper presents an evaluation method employing a latent variable model for paraphrases with their contexts. We assume that the context of a sentence is indicated by a latent variable of the model as a topic and that the likelihood of each variable can be inferred. A paraphrase is evaluated for whether its sentences are used in the same context. Experimental results showed that the proposed ...

for many years, there has been the concept of inner meaning of quran in addition to the outer one, so that, the tendency to paraphrase(tavil) and interpretation(tafsir) altogether, has been in the focal point of attention of this domain, s thinkers. in this field, fayz-e-kashani having an internal tendency to verses taken from philosophical- mystical stores from one hand and quranical-tradition...

An automatic essay paraphrasing system, written in JOVIAL, produces essay-like paraphrases of input texts written in a subset of English. The format and content of the essay paraphrase are controlled by an outline that is part of the input text. An individual sentence in the paraphrase may often reflect the content of several sentences in the input text. The system uses dependency rather than t...

This paper describes the techniques we explored to improve the translation of news text in the German-English and Hungarian-English tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, an...

Most state-of-the-art statistical machine translation systems use log-linear models, which are defined in terms of hypothesis features and weights for those features. It is standard to tune the feature weights in order to maximize a translation quality metric, using held-out test sentences and their corresponding reference translations. However, obtaining reference translations is expensive. In...

Lexical substitution is an annotation task in which annotators provide one-word paraphrases (lexical substitutes) for individual target words in a sentence context. Lexical substitution yields a fine-grained characterization of word meaning that can be done by non-expert annotators. We discuss results of a recent lexical substitution annotation effort, where we found strong contextual modulatio...

In this paper we propose an approach to corpus-based generation in a machine translation framework that is similar to shake & bake (Whitelock, 1992). A bag of words is mapped against an automatically induced TL template grammar and a sentence is generated by recursively applying rules that are extracted from the template grammar. A test version of the template grammar is enriched with further l...

The paper reports the approaches utilized and results achieved for our system in the shared task (in FIRE-2016) for paraphrase identification in Indian languages (DPIL). Since Indian languages have a complex inherent nature, paraphrase identification in these languages becomes a challenging task. In the DPIL task, the challenge is to detect and identify whether a given sentence pairs paraphrase...

This study aimed to investigate how Iranian EFL learners performed in producing sentences containing idioms and whether they had any problems in producing such sentences. This query, subsequently, raised the question of whether idioms influenced the participants’ grammaticality judgment on idiom-containing sentences. For this purpose, firstly, the writings of 24 learners were investigated for a...