印尼语、马来语自然语言处理研究综述

随着印尼语、马来语互联网普及率的上升,对海量印尼语、马来语文本进行信息处理存在重大需求.虽然研究人员对印尼语、马来语展开较广泛的研究,但是作为低资源语言,受到的关注远不及通用语,未能较好利用前沿的深度学习方法.文中梳理总结包括词法分析、句法分析、机器翻译、拼写检查等印尼语、马来语相关的自然语言处理技术.对比分析相关的研究成果发现,大多数研究因语料规模及评测标准不同难以客观对比各种算法的差异.最后结合印尼语、马来语现有的各领域语言资源开放情况,指出印尼语、马来语的自然语言处理研究面临的问题,并展望未来发展趋势.     

Interlingua-based English–Hindi Machine Translation and Language Divergence

Interlingua and transfer-based approaches tomachine translation have long been in use in competing and complementary ways. The former proves economical in situations where translation among multiple languages is involved, and can be used as a knowledge-representation scheme. But given a particular interlingua, its adoption depends on its ability (a) to capture the knowledge in texts precisely and accurately and (b) to handle cross-language divergences. This paper studies the language divergence between English and Hindi and its implication to machine translation between these languages using the Universal Networking Language (UNL). UNL has been introduced by the United Nations University, Tokyo, to facilitate the transfer and exchange of information over the internet. The representation works at the level of single sentences and defines a semantic net-like structure in which nodes are word concepts and arcs are semantic relations between these concepts. The language divergences between Hindi, an Indo-European language, and English can be considered as representing the divergences between the SOV and SVO classes of languages. The work presented here is the only one to our knowledge that describes language divergence phenomena in the framework of computational linguistics through a South Asian language.     

A framework for evolution of modelling languages

In model-driven engineering, evolution is inevitable over the course of the complete life cycle of complex software-intensive systems and more importantly of entire product families. Not only instance models, but also entire modelling languages are subject to change. This is in particular true for domain-specific languages, whose language constructs are tightly coupled to an application domain.The most popular approach to evolution in the modelling domain is a manual process, with tedious and error-prone migration of artefacts such as instance models as a result. This paper provides a taxonomy for evolution of modelling languages and discusses the different evolution scenarios for various kinds of modelling artefacts, such as instance models, meta-models, and transformation models. Subsequently, the consequences of evolution and the required remedial actions are decomposed into primitive scenarios such that all possible evolutions can be covered exhaustively. These primitives are then used in a high-level framework for the evolution of modelling languages.We suggest that our structured approach enables the design of (semi-)automatic modelling language evolution solutions.     

Factor-based evaluation for English to Hindi MT outputs

Design and implementation of automatic evaluation methods is an integral part of any scientific research in accelerating the development cycle of the output. This is no less true for automatic machine translation (MT) systems. However, no such global and systematic scheme exists for evaluation of performance of an MT system. The existing evaluation metrics, such as BLEU, METEOR, TER, although used extensively in literature have faced a lot of criticism from users. Moreover, performance of these metrics often varies with the pair of languages under consideration. The above observation is no less pertinent with respect to translations involving languages of the Indian subcontinent. This study aims at developing an evaluation metric for English to Hindi MT outputs. As a part of this process, a set of probable errors have been identified manually as well as automatically. Linear regression has been used for computing weight/penalty for each error, while taking human evaluations into consideration. A sentence score is computed as the weighted sum of the errors. A set of 126 models has been built using different single classifiers and ensemble of classifiers in order to find the most suitable model for allocating appropriate weight/penalty for each error. The outputs of the models have been compared with the state-of-the-art evaluation metrics. The models developed for manually identified errors correlate well with manual evaluation scores, whereas the models for the automatically identified errors have low correlation with the manual scores. This indicates the need for further improvement and development of sophisticated linguistic tools for automatic identification and extraction of errors. Although many automatic machine translation tools are being developed for many different language pairs, there is no such generalized scheme that would lead to designing meaningful metrics for their evaluation. The proposed scheme should help in developing such metrics for different language pairs in the coming days.     

Sememe knowledge computation: a review of recent advances in application and expansion of sememe knowledge bases

A sememe is defined as the minimum semantic unit of languages in linguistics. Sememe knowledge bases are built by manually annotating sememes for words and phrases. HowNet is the most well-known sememe knowledge base. It has been extensively utilized in many natural language processing tasks in the era of statistical natural language processing and proven to be effective and helpful to understanding and using languages. In the era of deep learning, although data are thought to be of vital importance, there are some studies working on incorporating sememe knowledge bases like HowNet into neural network models to enhance system performance. Some successful attempts have been made in the tasks including word representation learning, language modeling, semantic composition, etc. In addition, considering the high cost of manual annotation and update for sememe knowledge bases, some work has tried to use machine learning methods to automatically predict sememes for words and phrases to expand sememe knowledge bases. Besides, some studies try to extend HowNet to other languages by automatically predicting sememes for words and phrases in a new language. In this paper, we summarize recent studies on application and expansion of sememe knowledge bases and point out some future directions of research on sememes.     

Adaptive heterogeneous language support within a cloud runtime

Cloud runtimes are an effective method of distributing computations, but can force developers to use the runtime’s native language for all computations. We have extended the Granules cloud runtime with a bridge framework that allows computations to be written in C, C++, C#, Python, and R. We have additionally developed a diagnostics system which is capable of gathering information on system state, as well as modifying the underlying bridge framework in response to system load. Given the dynamic nature of Granules computations, which can be characterized as long-running with intermittent CPU bursts that allow a state to build up during successive rounds of execution, these bridges need to be bidirectional and the underlying communication mechanisms decoupled, robust and configurable. Granules bridges handle a number of different programming languages and support multiple methods of communication such as named pipes, unnamed pipes, and sockets. This choice of underlying communication mechanisms allows limited resources, such as sockets, to remain available for use by the runtime.     

XML语言在网页中的应用

SGML是一种在互联网上发布信息所使用的＂出版＂语言,是所有计算机都能够理解的标准通用标记语言,目前流行的HTML、XML等语言是SGML的实际应用。本文对网页制作中使用的HTML、XML尤其是XML等标记语言相关知识做了介绍,比较了两种种语言的不同与优缺点。     

Quantitative fine-grained human evaluation of machine translation systems: a case study on English to Croatian

This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established multidimensional quality metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to-Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different paradigms: pure phrase-based, factored phrase-based and neural. First, we design an MQM-compliant error taxonomy tailored to the relevant linguistic phenomena of Slavic languages, which made the annotation process feasible and accurate. Errors in MT outputs were then annotated by two annotators following this taxonomy. Subsequently, we carried out a statistical analysis which showed that the best-performing system (neural) reduces the errors produced by the worst system (pure phrase-based) by more than half (54%). Moreover, we conducted an additional analysis of agreement errors in which we distinguished between short (phrase-level) and long distance (sentence-level) errors. We discovered that phrase-based MT approaches are of limited use for long distance agreement phenomena, for which neural MT was found to be especially effective.     

Large-Scale Dictionary Construction for Foreign Language Tutoring and Interlingual Machine Translation

This paper describes techniques for automatic construction of dictionaries for use in large-scale foreign language tutoring (FLT) and interlingual machine translation (MT) systems. The dictionaries are based on a language-independent representation called lexical conceptual structure (LCS). A primary goal of the LCS research is to demonstrate that synonymous verb senses share distributional patterns. We show how the syntax–semantics relation can be used to develop a lexical acquisition approach that contributes both toward the enrichment of existing online resources and toward the development of lexicons containing more complete information than is provided in any of these resources alone. We start by describing the structure of the LCS and showing how this representation is used in FLT and MT. We then focus on the problem of building LCS dictionaries for large-scale FLT and MT. First, we describe authoring tools for manual and semi-automatic construction of LCS dictionaries; we then present a more sophisticated approach that uses linguistic techniques for building word definitions automatically. These techniques have been implemented as part of a set of lexicon-development tools used in the milt FLT project.     

“ちょっと”与独词句的机器翻译

机器翻译是对人工翻译的模拟。但是由于不同语言之间历史文化、风俗习惯等因素存在固有差异,所以相同的文字时常在不同环境下表达的意义不同,这使得机器翻译实现十分困难。独词句是语言学上的一种特殊的句型。独词句需要根据上下文环境来判断它的“句义”,而不仅仅是它的“词义”。然而目前大多数的计算机翻译软件,对独词句的处理都存在缺陷。本文希望能从语言学的角度,对翻译系统处理独词句提出更为合理的解决方法。     

BLARK for multi-dialect languages: towards the Kurdish BLARK

In this paper we introduce the Kurdish BLARK (Basic Language Resource Kit). The original BLARK has not considered multi-dialect characteristics and generally has targeted reasonably well-resourced languages. To consider these two features, we extended BLARK and applied the proposed extension to Kurdish. Kurdish language not only faces a paucity in resources, but also embraces several dialects within a complex linguistic context. This paper presents the Kurdish BLARK and shows that from Natural language processing and computational linguistics perspectives the revised BLARK provides a more applicable view of languages with similar characteristics to Kurdish.     

Matxin, an open-source rule-based machine translation system for Basque

We present the first publicly available machine translation (MT) system for Basque. The fact that Basque is both a morphologically rich and less-resourced language makes the use of statistical approaches difficult, and raises the need to develop a rule-based architecture which can be combined in the future with statistical techniques. The MT architecture proposed reuses several open-source tools and is based on a unique XML format to facilitate the flow between the different modules, which eases the interaction among different developers of tools and resources. The result is the rule-based Matxin MT system, an open-source toolkit, whose first implementation translates from Spanish to Basque. We have performed innovative work on the following tasks: construction of a dependency analyser for Spanish, use of rich linguistic information to translate prepositions and syntactic functions (such as subject and object markers), construction of an efficient module for verbal chunk transfer, and design and implementation of modules for ordering words and phrases, independently of the source language.     

Efficient Development of Lexical Language Resources and their Representation

Statistical approaches in speech technology, whether used for statistical language models, trees, hidden Markov models or neural networks, represent the driving forces for the creation of language resources (LR), e.g., text corpora, pronunciation and morphology lexicons, and speech databases. This paper presents a system architecture for the rapid construction of morphologic and phonetic lexicons, two of the most important written language resources for the development of ASR (automatic speech recognition) and TTS (text-to-speech) systems. The presented architecture is modular and is particularly suitable for the development of written language resources for inflectional languages. In this paper an implementation is presented for the Slovenian language. The integrated graphic user interface focuses on the morphological and phonetic aspects of language and allows experts to produce good performances during analysis. In multilingual TTS systems, many extensive external written language resources are used, especially in the text processing part. It is very important, therefore, that representation of these resources is time and space efficient. It is also very important that language resources for new languages can be easily incorporated into the system, without modifying the common algorithms developed for multiple languages. In this regard the use of large external language resources (e.g., morphology and phonetic lexicons) represent an important problem because of the required space and slow look-up time. This paper presents a method and its results for compiling large lexicons, using examples for compiling German phonetic and morphology lexicons (CISLEX), and Slovenian phonetic (SIflex) and morphology (SImlex) lexicons, into corresponding finite-state transducers (FSTs). The German lexicons consisted of about 300,000 words, SIflex consisted of about 60,000 and SImlex of about 600,000 words (where 40,000 words were used for representation using finite-state transducers). Representation of large lexicons using finite-state transducers is mainly motivated by considerations of space and time efficiency. A great reduction in size and optimal access time was achieved for all lexicons. The starting size for the German phonetic lexicon was 12.53 MB and 18.49 MB for the morphology lexicon. The starting size for the Slovenian phonetic lexicon was 1.8 MB and 1.4 MB for the morphology lexicon. The final size of the corresponding FSTs was 2.78 MB for the German phonetic lexicon, 6.33 MB for the German morphology lexicon, 253 KB for SIflex and 662 KB for the SImlex lexicon. The achieved look-up time is optimal, since it only depends on the length of the input word and not on the size of the lexicon. Integration of lexicons for new languages into the multilingual TTS system is easy when using such representations and does not require any changes in the algorithms used for such lexicons.     

Embedding Knowledge Elicitation and MT Systems within a Single Architecture

This paper describes Expedition, an environment designed to facilitate the quick ramp-up of MT systems from practically any alphabetic language (L) into English. The central component of Expedition is a knowledge-elicitation system that guides a linguistically naive bilingual speaker through the process of describing L in terms of its ecological, morphological, grammatical, lexical, and transfer information. Expedition also includes a module for converting the elicited information into the format expected by the underlying MT system and an MT engine that relies on both the elicited knowledge and resident knowledge about English. The Expedition environment is integrated using a configuration and control system. Expedition represents an innovative approach to answering the need for rapid-configuration MT by preparing an MT system in which the only missing link is information about L, which is elicited in a structured fashion such that it can be directly exploited by the system. In this paper we report on the current state of Expedition with an emphasis on the knowledge elicitation system.     

Interlingua-based English–Korean Two-way Speech Translation of Doctor–Patient Dialogues with CCLINC

Development of a robust two-way real-time speech translationsystem exposes researchers and system developers to various challenges of machine translation(MT) and spoken language dialogues. The need for communicating in at least two differentlanguages poses problems not present for a monolingual spoken language dialogue system,where no MT engine is embedded within the process flow. Integration of various componentmodules for real-time operation poses challenges not present for text translation. In this paper,we present the CCLINC (Common Coalition Language System at Lincoln Laboratory) English–Koreantwo-way speech translation system prototype trained on doctor–patient dialogues,which integrates various techniques to tackle the challenges of automatic real-time speechtranslation. Key features of the system include (i) language–independent meaning representation which preserves the hierarchicalpredicate–argument structure of an input utterance, providing a powerful mechanism for discourse understanding of utterances originating from different languages,word-sense disambiguation and generation of various word orders of many languages, (ii) adoptionof the DARPA Communicator architecture, a plug-and-play distributed system architecturewhich facilitates integration of component modules and system operation in real time, and (iii)automatic acquisition of grammar rules and lexicons for easy porting of the system to differentlanguages and domains. We describe these features in detail and present experimental results.     

Crawl and crowd to bring machine translation to under-resourced languages

We present a widely applicable methodology to bring machine translation (MT) to under-resourced languages in a cost-effective and rapid manner. Our proposal relies on web crawling to automatically acquire parallel data to train statistical MT systems if any such data can be found for the language pair and domain of interest. If that is not the case, we resort to (1) crowdsourcing to translate small amounts of text (hundreds of sentences), which are then used to tune statistical MT models, and (2) web crawling of vast amounts of monolingual data (millions of sentences), which are then used to build language models for MT. We apply these to two respective use-cases for Croatian, an under-resourced language that has gained relevance since it recently attained official status in the European Union. The first use-case regards tourism, given the importance of this sector to Croatia’s economy, while the second has to do with tweets, due to the growing importance of social media. For tourism, we crawl parallel data from 20 web domains using two state-of-the-art crawlers and explore how to combine the crawled data with bigger amounts of general-domain data. Our domain-adapted system is evaluated on a set of three additional tourism web domains and it outperforms the baseline in terms of automatic metrics and/or vocabulary coverage. In the social media use-case, we deal with tweets from the 2014 edition of the soccer World Cup. We build domain-adapted systems by (1) translating small amounts of tweets to be used for tuning by means of crowdsourcing and (2) crawling vast amounts of monolingual tweets. These systems outperform the baseline (Microsoft Bing) by 7.94 BLEU points (5.11 TER) for Croatian-to-English and by 2.17 points (1.94 TER) for English-to-Croatian on a test set translated by means of crowdsourcing. A complementary manual analysis sheds further light on these results.     

Automatic induction of bilingual resources from aligned parallel corpora: application to shallow-transfer machine translation

The availability of machine-readable bilingual linguistic resources is crucial not only for rule-based machine translation but also for other applications such as cross-lingual information retrieval. However, the building of such resources (bilingual single-word and multi-word correspondences, translation rules) demands extensive manual work, and, as a consequence, bilingual resources are usually more difficult to find than “shallow” monolingual resources such as morphological dictionaries or part-of-speech taggers, especially when they involve a less-resourced language. This paper describes a methodology to build automatically both bilingual dictionaries and shallow-transfer rules by extracting knowledge from word-aligned parallel corpora processed with shallow monolingual resources (morphological analysers, and part-of-speech taggers). We present experiments for Brazilian Portuguese–Spanish and Brazilian Portuguese–English parallel texts. The results show that the proposed methodology can enable the rapid creation of valuable computational resources (bilingual dictionaries and shallow-transfer rules) for machine translation and other natural language processing tasks).     

综合型语言知识库的建设与利用

语言知识库的规模和质量决定了自然语言处理系统的成败。经过18年的努力,北京大学计算语言学研究所已经积累了一系列颇具规模、质量上乘的语言数据资源:现代汉语语法信息词典,大规模基本标注语料库,现代汉语语义词典,中文概念词典,不同单位对齐的双语语料库,多个专业领域的术语库,现代汉语短语结构规则库,中国古代诗词语料库等等。本项研究将把这些语言数据资源集成为一个综合型的语言知识库。集成不同的语言数据资源时,必须克服它们之间的“缝隙”。规划中的综合型语言知识库除了有统一的友好的使用界面和方便的应用程序接口外,还将提供支持知识挖掘的工具软件,促使现有的语言数据资源从初级产品形式向深加工产品形式不断发展;提供多种形式的知识传播和信息服务机制,让综合型语言知识库为语言信息处理研究、语言学本体研究和语言教学提供全方位的、多层次的支持。