Necip Fazil Ayan

Improving Alignments for Better Confusion Networks for Combining Machine Translation Systems

The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confusion networks. One of the crucial steps in confusion network decoding is the alignment of different hypotheses to each other when building a network. In this paper, we present new methods to improve alignment of hypotheses using word synonyms and a two-pass alignment strategy. We demonstrate that combination with the new alignment technique yields up to 2.9 BLEU point improvement over the best input system and up to 1.3 BLEU point improvement over a state-of-the-art combination method on two different language pairs.

Efficient data selection for machine translation

Performance of statistical machine translation (SMT) systems relies on the availability of a large parallel corpus which is used to estimate translation probabilities. However, the generation of such corpus is a long and expensive process. In this paper, we introduce two methods for efficient selection of training data to be translated by humans. Our methods are motivated by active learning and aim to choose new data that adds maximal information to the currently available data pool. The first method uses a measure of disagreement between multiple SMT systems, whereas the second uses a perplexity criterion. We performed experiments on Chinese-English data in multiple domains and test sets. Our results show that we can select only one-fifth of the additional training data and achieve similar or better translation performance, compared to that of using all available data.

“Can you give me another word for hyperbaric?”: Improving speech translation using targeted clarification questions

We present a novel approach for improving communication success between users of speech-to-speech translation systems by automatically detecting errors in the output of automatic speech recognition (ASR) and statistical machine translation (SMT) systems. Our approach initiates system-driven targeted clarification about errorful regions in user input and repairs them given user responses. Our system has been evaluated by unbiased subjects in live mode, and results show improved success of communication between users of the system.

Automatic disfluency removal for improving spoken language translation

Statistical machine translation (SMT) systems for spoken languages suffer from conversational speech phenomena, in particular, the presence of speech disfluencies. We examine the impact of disfluencies from broadcast conversation data on our hierarchical phrasebased SMT system and implement automatic disfluency removal approaches for cleansing the MT input. We evaluate the efficacy of proposed approaches and investigate the impact of disfluency removal on SMT performance across different disfluency types. We show that for translating Mandarin broadcast conversational transcripts into English, our automatic disfluency removal approaches could produce significant improvement in BLEU and TER.

Implementing SRI's Pashto speech-to-speech translation system on a smart phone

We describe our recent effort implementing SRIs UMPC-based Pashto speech-to-speech (S2S) translation system on a smart phone running the Android operating system. In order to maintain very low latencies of system response on computationally limited smart phone platforms, we developed efficient algorithms and data structures and optimized model sizes for various system components. Our current Android-based S2S system requires less than one-fourth the system memory and significantly lower processor speed with a sacrifice of 15% relative loss of system accuracy, compared to a laptop-based platform.