Google offers several speech features on the Android mobile operating system: search by voice, voice input to any text field, and an API for application developers. As a result, our speech recognition service must support a wide range of usage scenarios and speaking styles: relatively short search queries, addresses, business names, dictated SMS and e-mail messages, and a long tail of spoken input to any of the applications users may install. We present a method of on-demand language model interpolation in which contextual information about each utterance determines interpolation weights among a number of n-gram language models. On-demand interpolation results in an 11.2 % relative reduction in WER compared to using a single language model to handle all traffic. Index Terms: language modeling, interpolation, mobile 1.

We use web-scale N-grams in a base NP parser that correctly analyzes 95.4 % of the base NPs in natural text. Web-scale data improves performance. That is, there is no data like more data. Performance scales log-linearly with the number of parameters in the model (the number of unique N-grams). The web-scale N-grams are particularly helpful in harder cases, such as NPs that contain conjunctions. 1

This paper presents methods to combine large language models trained from diverse text sources and applies them to a stateof-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking. 1

We describe an approach to improve Statistical Machine Translation (SMT) performance using multi-lingual, parallel, sentence-aligned corpora in several bridge languages. Our approach consists of a simple method for utilizing a bridge language to create a word alignment system and a procedure for combining word alignment systems from multiple bridge languages. The final translation is obtained by consensus decoding that combines hypotheses obtained using all bridge language word alignments. We present experiments showing that multilingual, parallel text in Spanish, French, Russian, and Chinese can be utilized in this framework to improve translation performance on an Arabic-to-English task. 1

Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven’t yet been explored in MT. Recently, McDonald et al. (2005b) formalized dependency parsing as a maximum spanning tree (MST) problem, which can be solved in quadratic time relative to the length of the sentence. They show that MST parsing is almost as accurate as cubic-time dependency parsing in the case of English, and that it is more accurate with free word order languages. This paper applies MST parsing to MT, and describes how it can be integrated into a phrase-based decoder to compute dependency language model scores. Our results show that augmenting a state-ofthe-art phrase-based system with this dependency language model leads to significant improvements in TER (0.92%) and BLEU (0.45%) scores on five NIST Chinese-English evaluation test sets. 1

A novel and robust approach to improving statistical machine translation fluency is developed within a minimum Bayesrisk decoding framework. By segmenting translation lattices according to confidence measures over the maximum likelihood translation hypothesis we are able to focus on regions with potential translation errors. Hypothesis space constraints based on monolingual coverage are applied to the low confidence regions to improve overall translation fluency. 1

We posit that visually descriptive language offers computer vision researchers both information about the world, and information about how people describe the world. The potential benefit from this source is made more significant due to the enormous amount of language data easily available today. We present a system to automatically generate natural language descriptions from images that exploits both statistics gleaned from parsing large quantities of text data and recognition algorithms from computer vision. The system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work. 1.

Practical data analysis relies on the ability to count observations of objects succinctly and efficiently. Unfortunately the space usage of an exact estimator grows with the size of the a priori set from which objects are drawn while the time required to maintain such an estimator grows with the size of the data set. We present static and on-line approximation schemes that avoid these limitations when approximate frequency estimates are acceptable. Our Log-Frequency Sketch extends the approximate counting algorithm of Morris [1978] to estimate frequencies with bounded relative error via a single pass over a data set. It uses constant space per object when the frequencies follow a power law and can be maintained in constant time per observation. We give an (ɛ, δ)-approximation scheme which we verify empirically on a large natural language data set where, for instance, 95 percent of frequencies are estimated with relative error less than 0.25 using fewer than 11 bits per object in the static case and 15 bits per object on-line. 1

Abstract not found

In this paper, we explore a streaming algorithm paradigm to handle large amounts of data for NLP problems. We present an efficient low-memory method for constructing high-order approximate n-gram frequency counts. The method is based on a deterministic streaming algorithm which efficiently computes approximate frequency counts over a stream of data while employing a small memory footprint. We show that this method easily scales to billion-word monolingual corpora using a conventional (8 GB RAM) desktop machine. Statistical machine translation experimental results corroborate that the resulting high-n approximate small language model is as effective as models obtained from other count pruning methods. 1