PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1311.5836

Automatic Ranking of MT Outputs using Approximations

Since long, research on machine translation has been ongoing. Still, we do not get good translations from MT engines so developed. Manual ranking of these outputs tends to be very time consuming and expensive. Identifying which one is better or worse than the others is a very taxing task. In this paper, we show an approach which can provide automatic ranks to MT outputs (translations) taken from different MT Engines and which is based on N-gram approximations. We provide a solution where no human intervention is required for ranking systems. Further we also show the evaluations of our results which show equivalent results as that of human ranking.

arXiv:1311.3961

HEVAL: Yet Another Human Evaluation Metric

Machine translation evaluation is a very important activity in machine translation development. Automatic evaluation metrics proposed in literature are inadequate as they require one or more human reference translations to compare them with output produced by machine translation. This does not always give accurate results as a text can have several different translations. Human evaluation metrics, on the other hand, lacks inter-annotator agreement and repeatability. In this paper we have proposed a new human evaluation metric which addresses these issues. Moreover this metric also provides solid grounds for making sound assumptions on the quality of the text produced by a machine translation.

arXiv:1312.0482

Learning Semantic Representations for the Phrase Translation Model

This paper presents a novel semantic-based phrase translation model. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent semantic space, where their translation score is computed by the distance between the pair in this new space. The projection is performed by a multi-layer neural network whose weights are learned on parallel training data. The learning is aimed to directly optimize the quality of end-to-end machine translation results. Experimental evaluation has been performed on two Europarl translation tasks, English-French and German-English. The results show that the new semantic-based phrase translation model significantly improves the performance of a state-of-the-art phrase-based statistical machine translation sys-tem, leading to a gain of 0.7-1.0 BLEU points.

arXiv:1312.7223

Quality Estimation of English-Hindi Outputs using Naive Bayes Classifier

In this paper we present an approach for estimating the quality of machine translation system. There are various methods for estimating the quality of output sentences, but in this paper we focus on Na\"ive Bayes classifier to build model using features which are extracted from the input sentences. These features are used for finding the likelihood of each of the sentences of the training data which are then further used for determining the scores of the test data. On the basis of these scores we determine the class labels of the test data.

arXiv:1401.2258

Assessing Wikipedia-Based Cross-Language Retrieval Models

This work compares concept models for cross-language retrieval: First, we adapt probabilistic Latent Semantic Analysis (pLSA) for multilingual documents. Experiments with different weighting schemes show that a weighting method favoring documents of similar length in both language sides gives best results. Considering that both monolingual and multilingual Latent Dirichlet Allocation (LDA) behave alike when applied for such documents, we use a training corpus built on Wikipedia where all documents are length-normalized and obtain improvements over previously reported scores for LDA. Another focus of our work is on model combination. For this end we include Explicit Semantic Analysis (ESA) in the experiments. We observe that ESA is not competitive with LDA in a query based retrieval task on CLEF 2000 data. The combination of machine translation with concept models increased performance by 21.1% map in comparison to machine translation alone. Machine translation relies on parallel corpora, which may not be available for many language pairs. We further explore how much cross-lingual information can be carried over by a specific information source in Wikipedia, namely linked text. The best results are obtained using a language modeling approach, entirely without information from parallel corpora. The need for smoothing raises interesting questions on soundness and efficiency. Link models capture only a certain kind of information and suggest weighting schemes to emphasize particular words. For a combined model, another interesting question is therefore how to integrate different weighting schemes. Using a very simple combination scheme, we obtain results that compare favorably to previously reported results on the CLEF 2000 dataset.

arXiv:1401.5700

Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora

This paper describes a method for the automatic inference of structural transfer rules to be used in a shallow-transfer machine translation (MT) system from small parallel corpora. The structural transfer rules are based on alignment templates, like those used in statistical MT. Alignment templates are extracted from sentence-aligned parallel corpora and extended with a set of restrictions which are derived from the bilingual dictionary of the MT system and control their application as transfer rules. The experiments conducted using three different language pairs in the free/open-source MT platform Apertium show that translation quality is improved as compared to word-for-word translation (when no transfer rules are used), and that the resulting translation quality is close to that obtained using hand-coded transfer rules. The method we present is entirely unsupervised and benefits from information in the rest of modules of the MT system in which the inferred rules are applied.

arXiv:1401.2943

ONTS: "Optima" News Translation System

We propose a real-time machine translation system that allows users to select a news category and to translate the related live news articles from Arabic, Czech, Danish, Farsi, French, German, Italian, Polish, Portuguese, Spanish and Turkish into English. The Moses-based system was optimised for the news domain and differs from other available systems in four ways: (1) News items are automatically categorised on the source side, before translation; (2) Named entity translation is optimised by recognising and extracting them on the source side and by re-inserting their translation in the target language, making use of a separate entity repository; (3) News titles are translated with a separate translation system which is optimised for the specific style of news titles; (4) The system was optimised for speed in order to cope with the large volume of daily news articles.

arXiv:1401.6876

Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source language X_1 into a resource-rich language Y given a bi-text containing a limited number of parallel sentences for X_1-Y and a larger bi-text for X_2-Y for some resource-rich language X_2 that is closely related to X_1. This is achieved by taking advantage of the opportunities that vocabulary overlap and similarities between the languages X_1 and X_2 in spelling, word order, and syntax offer: (1) we improve the word alignments for the resource-poor language, (2) we further augment it with additional translation options, and (3) we take care of potential spelling differences through appropriate transliteration. The evaluation for Indonesian- >English using Malay and for Spanish -> English using Portuguese and pretending Spanish is resource-poor shows an absolute gain of up to 1.35 and 3.37 BLEU points, respectively, which is an improvement over the best rivaling approaches, while using much less additional data. Overall, our method cuts the amount of necessary "real training data by a factor of 2--5.

arXiv:1401.4869

Does Syntactic Knowledge help English-Hindi SMT?

In this paper we explore various parameter settings of the state-of-art Statistical Machine Translation system to improve the quality of the translation for a `distant' language pair like English-Hindi. We proposed new techniques for efficient reordering. A slight improvement over the baseline is reported using these techniques. We also show that a simple pre-processing step can improve the quality of the translation significantly.

arXiv:1402.0563

Evaluating Indirect Strategies for Chinese-Spanish Statistical Machine Translation

Although, Chinese and Spanish are two of the most spoken languages in the world, not much research has been done in machine translation for this language pair. This paper focuses on investigating the state-of-the-art of Chinese-to-Spanish statistical machine translation (SMT), which nowadays is one of the most popular approaches to machine translation. For this purpose, we report details of the available parallel corpus which are Basic Traveller Expressions Corpus (BTEC), Holy Bible and United Nations (UN). Additionally, we conduct experimental work with the largest of these three corpora to explore alternative SMT strategies by means of using a pivot language. Three alternatives are considered for pivoting: cascading, pseudo-corpus and triangulation. As pivot language, we use either English, Arabic or French. Results show that, for a phrase-based SMT system, English is the best pivot language between Chinese and Spanish. We propose a system output combination using the pivot strategies which is capable of outperforming the direct translation strategy. The main objective of this work is motivating and involving the research community to work in this important pair of languages given their demographic impact.

arXiv:1403.7455

Hybrid Approach to English-Hindi Name Entity Transliteration

Machine translation (MT) research in Indian languages is still in its infancy. Not much work has been done in proper transliteration of name entities in this domain. In this paper we address this issue. We have used English-Hindi language pair for our experiments and have used a hybrid approach. At first we have processed English words using a rule based approach which extracts individual phonemes from the words and then we have applied statistical approach which converts the English into its equivalent Hindi phoneme and in turn the corresponding Hindi word. Through this approach we have attained 83.40% accuracy.

arXiv:1403.6381

An efficiency dependency parser using hybrid approach for tamil language

Natural language processing is a prompt research area across the country. Parsing is one of the very crucial tool in language analysis system which aims to forecast the structural relationship among the words in a given sentence. Many researchers have already developed so many language tools but the accuracy is not meet out the human expectation level, thus the research is still exists. Machine translation is one of the major application area under Natural Language Processing. While translation between one language to another language, the structure identification of a sentence play a key role. This paper introduces the hybrid way to solve the identification of relationship among the given words in a sentence. In existing system is implemented using rule based approach, which is not suited in huge amount of data. The machine learning approaches is suitable for handle larger amount of data and also to get better accuracy via learning and training the system. The proposed approach takes a Tamil sentence as an input and produce the result of a dependency relation as a tree like structure using hybrid approach. This proposed tool is very helpful for researchers and act as an odd-on improve the quality of existing approaches.

arXiv:1404.1847

Evaluation and Ranking of Machine Translated Output in Hindi Language using Precision and Recall Oriented Metrics

Evaluation plays a crucial role in development of Machine translation systems. In order to judge the quality of an existing MT system i.e. if the translated output is of human translation quality or not, various automatic metrics exist. We here present the implementation results of different metrics when used on Hindi language along with their comparisons, illustrating how effective are these metrics on languages like Hindi (free word order language).

arXiv:1405.2434

Coordinate System Selection for Minimum Error Rate Training in Statistical Machine Translation

Minimum error rate training (MERT) is a widely used training procedure for statistical machine translation. A general problem of this approach is that the search space is easy to converge to a local optimum and the acquired weight set is not in accord with the real distribution of feature functions. This paper introduces coordinate system selection (RSS) into the search algorithm for MERT. Contrary to previous approaches in which every dimension only corresponds to one independent feature function, we create several coordinate systems by moving one of the dimensions to a new direction. The basic idea is quite simple but critical that the training procedure of MERT should be based on a coordinate system formed by search directions but not directly on feature functions. Experiments show that by selecting coordinate systems with tuning set results, better results can be obtained without any other language knowledge.

arXiv:1405.2048

Learning Alternative Name Spellings

Name matching is a key component of systems for entity resolution or record linkage. Alternative spellings of the same names are a com- mon occurrence in many applications. We use the largest collection of genealogy person records in the world together with user search query logs to build name matching models. The procedure for building a crowd-sourced training set is outlined together with the presentation of our method. We cast the problem of learning alternative spellings as a machine translation problem at the character level. We use in- formation retrieval evaluation methodology to show that this method substantially outperforms on our data a number of standard well known phonetic and string similarity methods in terms of precision and re- call. Additionally, we rigorously compare the performance of standard methods when compared with each other. Our result can lead to a significant practical impact in entity resolution applications.

arXiv:1405.1397

Analysis Tool for UNL-Based Knowledge Representation

The fundamental issue in knowledge representation is to provide a precise definition of the knowledge that they possess in a manner that is independent of procedural considerations, context free and easy to manipulate, exchange and reason about. Knowledge must be accessible to everyone regardless of their native languages. Universal Networking Language (UNL) is a declarative formal language and a generalized form of human language in a machine independent digital platform for defining, recapitulating, amending, storing and dissipating knowledge among people of different affiliations. UNL extracts semantic data from a native language for Interlingua machine translation. This paper presents the development of a graphical tool that incorporates UNL to provide a visual mean to represent the semantic data available in a native text. UNL represents the semantics of a sentence as a conceptual hyper-graph. We translate this information into XML format and create a graph from XML, representing the actual concepts available in the native language

arXiv:1405.4273

Compositional Morphology for Word Representations and Language Modelling

This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. When used for translation into morphologically rich languages with large vocabularies, our models obtain improvements of up to 1.2 BLEU points relative to a baseline system using back-off n-gram models.

arXiv:1405.3451

Developing Corpus-based Translation Methods between Informal and Formal Mathematics: Project Description

The goal of this project is to (i) accumulate annotated informal/formal mathematical corpora suitable for training semi-automated translation between informal and formal mathematics by statistical machine-translation methods, (ii) to develop such methods oriented at the formalization task, and in particular (iii) to combine such methods with learning-assisted automated reasoning that will serve as a strong semantic component. We describe these ideas, the initial set of corpora, and some initial experiments done over them.

arXiv:1405.5654

Machine Translation Model based on Non-parallel Corpus and Semi-supervised Transductive Learning

Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and other natural language processing tasks. This article proposes a semi-supervised transductive learning method for expanding the training corpus in statistical machine translation system by extracting parallel sentences from the non-parallel corpus. This method only requires a small amount of labeled corpus and a large unlabeled corpus to build a high-performance classifier, especially for when there is short of labeled corpus. The experimental results show that by combining the non-parallel corpus alignment and the semi-supervised transductive learning method, we can more effectively use their respective strengths to improve the performance of machine translation system.

arXiv:1405.4918

Fighting Authorship Linkability with Crowdsourcing

Massive amounts of contributed content -- including traditional literature, blogs, music, videos, reviews and tweets -- are available on the Internet today, with authors numbering in many millions. Textual information, such as product or service reviews, is an important and increasingly popular type of content that is being used as a foundation of many trendy community-based reviewing sites, such as TripAdvisor and Yelp. Some recent results have shown that, due partly to their specialized/topical nature, sets of reviews authored by the same person are readily linkable based on simple stylometric features. In practice, this means that individuals who author more than a few reviews under different accounts (whether within one site or across multiple sites) can be linked, which represents a significant loss of privacy. In this paper, we start by showing that the problem is actually worse than previously believed. We then explore ways to mitigate authorship linkability in community-based reviewing. We first attempt to harness the global power of crowdsourcing by engaging random strangers into the process of re-writing reviews. As our empirical results (obtained from Amazon Mechanical Turk) clearly demonstrate, crowdsourcing yields impressively sensible reviews that reflect sufficiently different stylometric characteristics such that prior stylometric linkability techniques become largely ineffective. We also consider using machine translation to automatically re-write reviews. Contrary to what was previously believed, our results show that translation decreases authorship linkability as the number of intermediate languages grows. Finally, we explore the combination of crowdsourcing and machine translation and report on the results.