اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAutomatic Alignment of English-Chinese Bilingual Texts of CNS News
67
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this paper we address a method to align English-Chinese bilingual news reports from China News Service, combining both lexical and satistical approaches. Because of the sentential structure differences between English and Chinese, matching at the sentence level as in many other works may result in frequent matching of several sentences en masse. In view of this, the current work also attempts to create shorter alignment pairs by permitting finer matching between clauses from both texts if possible. The current method is based on statiscal correlation between sentence or clause length of both texts and at the same time uses obvious anchors such as numbers and place names appearing frequently in the news reports as lexcial cues.
قيم البحث
اقرأ أيضاً
Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate across language barriers. The question naturally arises whether such syst
ems can approach or achieve parity with human translations. In this paper, we first address the problem of how to define and accurately measure human parity in translation. We then describe Microsofts machine translation system and measure the quality of its translations on the widely used WMT 2017 news translation task from Chinese to English. We find that our latest neural machine translation system has reached a new state-of-the-art, and that the translation quality is at human parity when compared to professional human translations. We also find that it significantly exceeds the quality of crowd-sourced non-professional translations.
The parallel corpus for multilingual NLP tasks, deep learning applications like Statistical Machine Translation Systems is very important. The parallel corpus of Hindi-English language pair available for news translation task till date is of very lim
ited size as per the requirement of the systems are concerned. In this work we have developed an automatic parallel corpus generation system prototype, which creates Hindi-English parallel corpus for news translation task. Further to verify the quality of generated parallel corpus we have experimented by taking various performance metrics and the results are quite interesting.
A comparison of two english texts from Lewis Carroll, one (Alice in wonderland), also translated into esperanto, the other (Through a looking glass) are discussed in order to observe whether natural and artificial languages significantly differ from
each other. One dimensional time series like signals are constructed using only word frequencies (FTS) or word lengths (LTS). The data is studied through (i) a Zipf method for sorting out correlations in the FTS and (ii) a Grassberger-Procaccia (GP) technique based method for finding correlations in LTS. Features are compared : different power laws are observed with characteristic exponents for the ranking properties, and the {it phase space attractor dimensionality}. The Zipf exponent can take values much less than unity ($ca.$ 0.50 or 0.30) depending on how a sentence is defined. This non-universality is conjectured to be a measure of the author $style$. Moreover the attractor dimension $r$ is a simple function of the so called phase space dimension $n$, i.e., $r = n^{lambda}$, with $lambda = 0.79$. Such an exponent should also conjecture to be a measure of the author $creativity$. However, even though there are quantitative differences between the original english text and its esperanto translation, the qualitative differences are very minutes, indicating in this case a translation relatively well respecting, along our analysis lines, the content of the author writing.
Automatic lyrics to polyphonic audio alignment is a challenging task not only because the vocals are corrupted by background music, but also there is a lack of annotated polyphonic corpus for effective acoustic modeling. In this work, we propose (1)
using additional speech and music-informed features and (2) adapting the acoustic models trained on a large amount of solo singing vocals towards polyphonic music using a small amount of in-domain data. Incorporating additional information such as voicing and auditory features together with conventional acoustic features aims to bring robustness against the increased spectro-temporal variations in singing vocals. By adapting the acoustic model using a small amount of polyphonic audio data, we reduce the domain mismatch between training and testing data. We perform several alignment experiments and present an in-depth alignment error analysis on acoustic features, and model adaptation techniques. The results demonstrate that the proposed strategy provides a significant error reduction of word boundary alignment over comparable existing systems, especially on more challenging polyphonic data with long-duration musical interludes.
People are often entities of interest in tasks such as search and information extraction. In these tasks, the goal is to find as much information as possible about people specified by their name. However in text, some of the references to people are
by pronouns (she, his) or generic descriptions (the professor, the German chancellor). It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct person name. Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase. Our analysis reveals that standard coreference metrics do not reflect adequately the requirements in this task: they do not penalize systems for not identifying any mentions by name and they reward systems even if systems find correctly mentions to the same entity but fail to link these to a proper name (she--the student---no name). We introduce new metrics for evaluating named person coreference that address these discrepancies. We present a simple rule-based named entity recognition driven system, which outperforms the current state-of-the-art systems on these task-specific metrics and performs on par with them on traditional coreference evaluations. Finally, we present similar evaluation for coreference resolution of other named entities and show that the rule-based approach is effective only for person named coreference, not other named entity types.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
