This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect co-reference chains, and translate Spanish zero pronouns into English---issues hardly considered by other systems. The paper presents the resolution and evaluation of these anaphora problems in AGIR with the use of different kinds of knowledge (lexical, morphological, syntactic, and semantic). The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora. We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively. Although we have only studied the Spanish and English languages, our approach can be easily extended to other languages such as Portuguese, Italian, or Japanese.

Correction of Noisy Natural Language Text is an important and well studied problem in Natural Language Processing. It has a number of applications in domains like Statistical Machine Translation, Second Language Learning and Natural Language Generation. In this work, we consider some statistical techniques for Text Correction. We define the classes of errors commonly found in text and describe algorithms to correct them. The data has been taken from a poorly trained Machine Translation system. The algorithms use only a language model in the target language in order to correct the sentences. We use phrase based correction methods in both the algorithms. The phrases are replaced and combined to give us the final corrected sentence. We also present the methods to model different kinds of errors, in addition to results of the working of the algorithms on the test set. We show that one of the approaches fail to achieve the desired goal, whereas the other succeeds well. In the end, we analyze the possible reasons for such a trend in performance.

Expressions (MWEs) (Okita et al. 2010), this may improve the overall translation. For example in EN-JP, the empirical evidences 2007; Koehn 2010) intends to handle morphologically rich suggest that we separate affix(es) and word stem(s) since it languages in the target side by integrating additional linguistic obtains better BLEU score than the case when we do not separate markup at the word level, where each type of additional them although the adequacy decreases.

This paper considers a scenario when we are given almost perfect knowledge about bilingual terminology in terms of a test corpus in Statistical Machine Translation (SMT). When the given terminology is part of a training corpus, one natural strategy in SMT is to use the trained translation model ignoring the given terminology. Then, two questions arises here. 1) Can a word aligner capture the given terminology? This is since even if the terminology is in a training corpus, it is often the case that a resulted translation model may not include these terminology. 2) Are probabilities in a translation model correctly calculated? In order to answer these questions, we did experiment introducing a Multi-Word Expression-sensitive (MWE-sensitive) word aligner and a hierarchical Pitman-Yor process-based translation model smoothing. Using 200k JP--EN NTCIR corpus, our experimental results show that if we introduce an MWE-sensitive word aligner and a new translation model smoothing, the overall improvement was 1.35 BLEU point absolute and 6.0% relative compared to the case we do not introduce these two.

We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an $d$-dimensional space, such that n-grams that are the translation of each other are close with respect to some metric. Good n-grams to n-grams translation results were achieved, but full sentences translation is still problematic. We realized that learning semantics of sentences and documents was the key for solving a lot of natural language processing problems, and thus moved to the second part of our work: sentence compression. We introduce a flexible neural network architecture for learning embeddings of words and sentences that extract their semantics, propose an efficient implementation in the Torch framework and present embedding results comparable to the ones obtained with classical neural language models, while being more powerful.

This book presents a methodology and philosophy of empirical science based on large scale lossless data compression. In this view a theory is scientific if it can be used to build a data compression program, and it is valuable if it can compress a standard benchmark database to a small size, taking into account the length of the compressor itself. This methodology therefore includes an Occam principle as well as a solution to the problem of demarcation. Because of the fundamental difficulty of lossless compression, this type of research must be empirical in nature: compression can only be achieved by discovering and characterizing empirical regularities in the data. Because of this, the philosophy provides a way to reformulate fields such as computer vision and computational linguistics as empirical sciences: the former by attempting to compress databases of natural images, the latter by attempting to compress large text databases. The book argues that the rigor and objectivity of the compression principle should set the stage for systematic progress in these fields. The argument is especially strong in the context of computer vision, which is plagued by chronic problems of evaluation. The book also considers the field of machine learning. Here the traditional approach requires that the models proposed to solve learning problems be extremely simple, in order to avoid overfitting. However, the world may contain intrinsically complex phenomena, which would require complex models to understand. The compression philosophy can justify complex models because of the large quantity of data being modeled (if the target database is 100 Gb, it is easy to justify a 10 Mb model). The complex models and abstractions learned on the basis of the raw data (images, language, etc) can then be reused to solve any specific learning problem, such as face recognition or machine translation.

This article gives a detailed description of True Knowledge: a commercial, open-domain question answering platform. The system combines a large and growing structured knowledge base of common sense, factual and lexical knowledge; a natural language translation system that turns user questions into internal language-independent queries and an inference system that can answer those queries using both directly represented and inferred knowledge. The system is live and answers millions of questions per month asked by internet users.

The bare minimum lexical resource required to translate between a pair of languages is a translation dictionary. Unfortunately, dictionaries exist only between a tiny fraction of the 49 million possible language-pairs making machine translation virtually impossible between most of the languages. This paper summarizes the last four years of our research motivated by the vision of panlingual communication. Our research comprises three key steps. First, we compile over 630 freely available dictionaries over the Web and convert this data into a single representation – the translation graph. Second, we build several inference algorithms that infer translations between word pairs even when no dictionary lists them as translations. Finally, we run our inference procedure offline to construct PANDICTIONARY– a sense-distinguished, massively multilingual dictionary that has translations in more than 1000 languages. Our experiments assess the quality of this dictionary and find that we have 4 times as many translations at a high precision of 0.9 compared to the English Wiktionary, which is the lexical resource closest to PANDICTIONARY.

We discuss challenges and opportunities for developing generalized task markets where human and machine intelligence are enlisted to solve problems, based on a consideration of the competencies, availabilities, and pricing of different problem-solving resources. The approach couples human computation with machine learning and planning, and is aimed at optimizing the flow of subtasks to people and to computational problem solvers. We illustrate key ideas in the context of Lingua Mechanica, a project focused on harnessing human and machine translation skills to perform translation among languages. We present infrastructure and methods for enlisting and guiding human and machine computation for language translation, including details about the hardness of generating plans for assigning tasks to solvers. Finally, we discuss studies performed with machine and human solvers, focusing on components of a Lingua Mechanica prototype.

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.