The best systems for machine translation of natural language are based on statistical models learned from data. Conventional representation of a statistical translation model requires substantial offline computation and representation in main memory. Therefore, the principal bottlenecks to the amount of data we can exploit and the complexity of models we can use are available memory and CPU time, and current state of the art already pushes these limits. With data size and model complexity continually increasing, a scalable solution to this problem is central to future improvement. Callison-Burch et al. (2005) and Zhang and Vogel (2005) proposed a solution that we call translation by pattern matching, which we bring to fruition in this dissertation. The training data itself serves as a proxy to the model; rules and parameters are computed on demand. It achieves our desiderata of minimal offline computation and compact representation, but is dependent on fast pattern matching algorithms on text. They demonstrated its application to a common model based on the translation of contiguous substrings, but leave some open problems. Among these is a question: can this approach match the performance of conventional methods despite unavoidable differences that it induces in the model? We show how to answer this question affirmatively. The main

The lack of reliable Chinese sentiment resources limits research progress on Chinese sentiment classification. However, there are many freely available English sentiment resources on the Web. This article focuses on the problem of cross-lingual sentiment classification, which leverages only available English resources for Chinese sentiment classification. We first investigate several basic methods (including lexicon-based methods and corpus-based methods) for cross-lingual sentiment classification by simply leveraging machine translation services to eliminate the language gap, and then propose a bilingual co-training approach to make use of both the English view and the Chinese view based on additional unlabeled Chinese data. Experimental results on two test sets show the effectiveness of the proposed approach, which can outperform basic methods and transductive methods. 1.

Hadoop is an open source implementation of Google’s MapReduce programming model that has recently gained popularity as a practical approach to distributed information processing. This work explores the use of memcached, an open-source distributed in-memory object caching system, to provide low-latency, high-throughput access to static global resources in Hadoop. Such a capability is essential to a large class of MapReduce algorithms that require, for example, querying language model probabilities, accessing model parameters in iterative algorithms, or performing joins across relational datasets. Experimental results on a simple demonstration application illustrate that memcached provides a feasible general-purpose solution for rapidly accessing global key-value pairs from within Hadoop programs. Our proposed architecture exhibits the desirable scaling characteristic of linear increase in throughput with respect to cluster size. To our knowledge, this application of memcached in Hadoop is novel. Although considerable opportunities for increased performance remain, this work enables implementation of algorithms that do not have satisfactory solutions at scale today. 1

Abstract not found

An efficient decoding algorithm is a crucial element of any statistical machine translation system. Some researchers have noted certain similarities between SMT decoding and the famous Traveling Salesman Problem; in particular (Knight, 1999) has shown that any TSP instance can be mapped to a sub-case of a word-based SMT model, demonstrating NP-hardness of the decoding task. In this paper, we focus on the reverse mapping, showing that any phrase-based SMT decoding problem can be directly reformulated as a TSP. The transformation is very natural, deepens our understanding of the decoding problem, and allows direct use of any of the powerful existing TSP solvers for SMT decoding. We test our approach on three datasets, and compare a TSP-based decoder to the popular beam-search algorithm. In all cases, our method provides competitive or better performance. 1

We present a general method for incorporating an “expert ” model into a Statistical Machine Translation (SMT) system, in order to improve its performance on a particular “area of expertise”, and apply this method to the specific task of finding adequate replacements for Out-of-Vocabulary (OOV) words. Candidate replacements are paraphrases and entailed phrases, obtained using monolingual resources. These candidate replacements are transformed into “dynamic biphrases”, generated at decoding time based on the context of each source sentence. Standard SMT features are enhanced with a number of new features aimed at scoring translations produced by using different replacements. Active learning is used to discriminatively train the model parameters from human assessments of the quality of translations. The learning framework yields an SMT system which is able to deal with sentences containing OOV words but also guarantees that the performance is not degraded for input sentences without OOV words. Results of experiments on English-French translation show that this method outperforms previous work addressing OOV words in terms of acceptability. 1

We describe an approach for filtering phrase tables in a Statistical Machine Translation system, which relies on a statistical independence measure called Noise, first introduced in (Moore, 2004). While previous work by (Johnson et al., 2007) also addressed the question of phrase table filtering, it relied on a simpler independence measure, the p-value, which is theoretically less satisfying than the Noise in this context. In this paper, we use Noise as the filtering criterion, and show that when we partition the bi-phrase tables in several sub-classes according to their complexity, using Noise leads to improvements in BLEU score that are unreachable using p-value, while allowing a similar amount of pruning of the phrase tables. 1

Strictly corpus-based measures of semantic distance conflate co-occurrence information pertaining to the many possible senses of target words. We propose a corpus–thesaurus hybrid method that uses soft constraints to generate word-senseaware distributional profiles (DPs) from coarser “concept DPs ” (derived from a Roget-like thesaurus) and sense-unaware traditional word DPs (derived from raw text). Although it uses a knowledge source, the method is not vocabularylimited: if the target word is not in the thesaurus, the method falls back gracefully on the word’s co-occurrence information. This allows the method to access valuable information encoded in a lexical resource, such as a thesaurus, while still being able to effectively handle domainspecific terms and named entities. Experiments on word-pair ranking by semantic distance show the new hybrid method to be superior to others. 1

Abstract not found

We introduce a method for learning to find domain-specific translations for a given term on the Web. In our approach, the source term is transformed into an expanded query aimed at maximizing the probability of retrieving translations from a very large collection of mixed-code documents. The method involves automatically generating sets of targetlanguage words from training data in specific domains, automatically selecting target words for effectiveness in retrieving documents containing the sought-after translations. At run time, the given term is transformed into an expanded query and submitted to a search engine, and ranked translations are extracted from the document snippets returned by the search engine. We present a prototype, TermMine, which applies the method to a Web search engine. Evaluations over a set of domains and terms show that TermMine outperforms state-of-the-art machine translation systems. 1