Maryam Siahbani

Improving Statistical Machine Translation with a Multilingual Paraphrase Database

The multilingual Paraphrase Database (PPDB) is a freely available automatically created resource of paraphrases in multiple languages. In statistical machine translation, paraphrases can be used to provide translation for out-of-vocabulary (OOV) phrases. In this paper, we show that a graph propagation approach that uses PPDB paraphrases can be used to improve overall translation quality. We provide an extensive comparison with previous work and show that our PPDB-based method improves the BLEU score by up to 1.79 percent points. We show that our approach improves on the state of the art in three different settings: when faced with limited amount of parallel training data; a domain shift between training and test data; and handling a morphologically complex source language. Our PPDB-based method outperforms the use of distributional profiles from monolingual source data.

Two Improvements to Left-to-Right Decoding for Hierarchical Phrase-based Machine Translation

Left-to-right (LR) decoding (Watanabe et al., 2006) is promising decoding algorithm for hierarchical phrase-based translation (Hiero) that visits input spans in arbitrary order producing the output translation in left to right order. This leads to far fewer language model calls, but while LR decoding is more efficient than CKY decoding, it is unable to capture some hierarchical phrase alignments reachable using CKY decoding and suffers from lower translation quality as a result. This paper introduces two improvements to LR decoding that make it comparable in translation quality to CKY-based Hiero.

LensingWikipedia: Parsing text for the interactive visualization of human history

Extracting information from text is challenging. Most current practices treat text as a bag of words or word clusters, ignoring valuable linguistic information. Leveraging this linguistic information, we propose a novel approach to visualize textual information. The novelty lies in using state-of-the-art Natural Language Processing (NLP) tools to automatically annotate text which provides a basis for new and powerful interactive visualizations. Using NLP tools, we built a web-based interactive visual browser for human history articles from Wikipedia.

Incremental translation using hierarchichal phrase-based translation system

Hierarchical phrase-based machine translation [1] (Hiero) is a prominent approach for Statistical Machine Translation usually comparable to or better than conventional phrase-based systems. But Hiero typically uses the CKY decoding algorithm which requires the entire input sentence before decoding begins, as it produces the translation in a bottom-up fashion. Left-to-right (LR) decoding [2] is a promising decoding algorithm for Hiero that produces the output translation in left to right order. In this paper we focus on simultaneous translation using the Hiero translation framework. In simultaneous translation, translations are generated incrementally as source language speech input is processed. We propose a novel approach for incremental translation by integrating segmentation and decoding in LR-Hiero. We compare two incremental decoding algorithms for LR-Hiero and present translation quality scores (BLEU) and the latency of generating translations for both decoders on audio lectures from the TED collection.