scholarly journals Synthetic Treebanking for Cross-Lingual Dependency Parsing

2016 ◽  
Vol 55 ◽  
pp. 209-248 ◽  
Author(s):  
Jörg Tiedemann ◽  
Zeljko Agić
Keyword(s):  
Machine Translation ◽  
Target Language ◽  
Dependency Parsing ◽  
Practical Applications ◽  
Source Language ◽  
Part Of Speech ◽  
Statistical Dependency ◽  
Target Languages ◽  
Cross Lingual ◽  
The Impact

How do we parse the languages for which no treebanks are available? This contribution addresses the cross-lingual viewpoint on statistical dependency parsing, in which we attempt to make use of resource-rich source language treebanks to build and adapt models for the under-resourced target languages. We outline the benefits, and indicate the drawbacks of the current major approaches. We emphasize synthetic treebanking: the automatic creation of target language treebanks by means of annotation projection and machine translation. We present competitive results in cross-lingual dependency parsing using a combination of various techniques that contribute to the overall success of the method. We further include a detailed discussion about the impact of part-of-speech label accuracy on parsing results that provide guidance in practical applications of cross-lingual methods for truly under-resourced languages.

scholarly journals Multilingual Dependency Parsing: Using Machine Translated Texts Instead of Parallel Corpora

2014 ◽  
Vol 102 (1) ◽  
pp. 93-104
Author(s):  
Ramasamy Loganathan ◽  
Mareček David ◽  
Žabokrtský Zdenčk
Keyword(s):  
Machine Translation ◽  
The Other ◽  
Target Language ◽  
Grammar Induction ◽  
Language Resources ◽  
Parallel Corpora ◽  
Similar Performance ◽  
Part Of Speech ◽  
Target Languages ◽  
Cross Lingual

Abstract This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers.

scholarly journals Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification (Extended Abstract)

2020 ◽  
Author(s):  
Zhenpeng Chen ◽  
Sheng Shen ◽  
Ziniu Hu ◽  
Xuan Lu ◽  
Qiaozhu Mei ◽  
...  
Keyword(s):  
Machine Translation ◽  
Representation Learning ◽  
Sentiment Classification ◽  
Target Language ◽  
Learning Method ◽  
Source Language ◽  
Translation Tools ◽  
Target Languages ◽  
Cross Lingual ◽  
Cross Language

Sentiment classification typically relies on a large amount of labeled data. In practice, the availability of labels is highly imbalanced among different languages. To tackle this problem, cross-lingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i.e., the source language, usually English) to another language with fewer labels (i.e., the target language). The source and the target languages are usually bridged through off-the-shelf machine translation tools. Through such a channel, cross-language sentiment patterns can be successfully learned from English and transferred into the target languages. This approach, however, often fails to capture sentiment knowledge specific to the target language. In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. We propose a novel representation learning method that uses emoji prediction as an instrument to learn respective sentiment-aware representations for each language. The learned representations are then integrated to facilitate cross-lingual sentiment classification.

scholarly journals Optimizing Tokenization Choice for Machine Translation across Multiple Target Languages

2017 ◽  
Vol 108 (1) ◽  
pp. 257-269 ◽  
Author(s):  
Nasser Zalmout ◽  
Nizar Habash
Keyword(s):  
Machine Translation ◽  
Performance Enhancement ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Source Language ◽  
Context Variable ◽  
Significant Performance ◽  
Morphologically Rich Languages ◽  
Target Languages ◽  
Language Text

AbstractTokenization is very helpful for Statistical Machine Translation (SMT), especially when translating from morphologically rich languages. Typically, a single tokenization scheme is applied to the entire source-language text and regardless of the target language. In this paper, we evaluate the hypothesis that SMT performance may benefit from different tokenization schemes for different words within the same text, and also for different target languages. We apply this approach to Arabic as a source language, with five target languages of varying morphological complexity: English, French, Spanish, Russian and Chinese. Our results show that different target languages indeed require different source-language schemes; and a context-variable tokenization scheme can outperform a context-constant scheme with a statistically significant performance enhancement of about 1.4 BLEU points.

A classification approach for detecting cross-lingual biomedical term translations

2015 ◽  
Vol 23 (1) ◽  
pp. 31-51 ◽  
Author(s):  
H. HAKAMI ◽  
D. BOLLEGALA
Keyword(s):  
Machine Translation ◽  
Feature Space ◽  
Target Language ◽  
Average Precision ◽  
Common Features ◽  
Target Languages ◽  
Cross Lingual ◽  
Translation Accuracy ◽  
Translation Systems ◽  
Technical Terms

AbstractFinding translations for technical terms is an important problem in machine translation. In particular, in highly specialized domains such as biology or medicine, it is difficult to find bilingual experts to annotate sufficient cross-lingual texts in order to train machine translation systems. Moreover, new terms are constantly being generated in the biomedical community, which makes it difficult to keep the translation dictionaries up to date for all language pairs of interest. Given a biomedical term in one language (source language), we propose a method for detecting its translations in a different language (target language). Specifically, we train a binary classifier to determine whether two biomedical terms written in two languages are translations. Training such a classifier is often complicated due to the lack of common features between the source and target languages. We propose several feature space concatenation methods to successfully overcome this problem. Moreover, we study the effectiveness of contextual and character n-gram features for detecting term translations. Experiments conducted using a standard dataset for biomedical term translation show that the proposed method outperforms several competitive baseline methods in terms of mean average precision and top-k translation accuracy.

scholarly journals Reinforced Transformer with Cross-Lingual Distillation for Cross-Lingual Aspect Sentiment Classification

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 270
Author(s):  
Hanqian Wu ◽  
Zhike Wang ◽  
Feng Qing ◽  
Shoushan Li
Keyword(s):  
General Purpose ◽  
Sentiment Classification ◽  
Training Data ◽  
Target Language ◽  
Source Language ◽  
Domain Specific ◽  
Novel Approach ◽  
The Rich ◽  
Target Languages ◽  
Cross Lingual

Though great progress has been made in the Aspect-Based Sentiment Analysis(ABSA) task through research, most of the previous work focuses on English-based ABSA problems, and there are few efforts on other languages mainly due to the lack of training data. In this paper, we propose an approach for performing a Cross-Lingual Aspect Sentiment Classification (CLASC) task which leverages the rich resources in one language (source language) for aspect sentiment classification in a under-resourced language (target language). Specifically, we first build a bilingual lexicon for domain-specific training data to translate the aspect category annotated in the source-language corpus and then translate sentences from the source language to the target language via Machine Translation (MT) tools. However, most MT systems are general-purpose, it non-avoidably introduces translation ambiguities which would degrade the performance of CLASC. In this context, we propose a novel approach called Reinforced Transformer with Cross-Lingual Distillation (RTCLD) combined with target-sensitive adversarial learning to minimize the undesirable effects of translation ambiguities in sentence translation. We conduct experiments on different language combinations, treating English as the source language and Chinese, Russian, and Spanish as target languages. The experimental results show that our proposed approach outperforms the state-of-the-art methods on different target languages.

scholarly journals Source Language Adaptation Approaches for Resource-Poor Machine Translation

2016 ◽  
Vol 42 (2) ◽  
pp. 277-306 ◽  
Author(s):  
Pidong Wang ◽  
Preslav Nakov ◽  
Hwee Tou Ng
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Source Language ◽  
World Languages ◽  
Word Level ◽  
Resource Poor ◽  
Morphological Variants ◽  
Cross Lingual ◽  
Translation Systems

Most of the world languages are resource-poor for statistical machine translation; still, many of them are actually related to some resource-rich language. Thus, we propose three novel, language-independent approaches to source language adaptation for resource-poor statistical machine translation. Specifically, we build improved statistical machine translation models from a resource-poor language POOR into a target language TGT by adapting and using a large bitext for a related resource-rich language RICH and the same target language TGT. We assume a small POOR–TGT bitext from which we learn word-level and phrase-level paraphrases and cross-lingual morphological variants between the resource-rich and the resource-poor language. Our work is of importance for resource-poor machine translation because it can provide a useful guideline for people building machine translation systems for resource-poor languages. Our experiments for Indonesian/Malay–English translation show that using the large adapted resource-rich bitext yields 7.26 BLEU points of improvement over the unadapted one and 3.09 BLEU points over the original small bitext. Moreover, combining the small POOR–TGT bitext with the adapted bitext outperforms the corresponding combinations with the unadapted bitext by 1.93–3.25 BLEU points. We also demonstrate the applicability of our approaches to other languages and domains.

Word Sense Based Hindi-Tamil Statistical Machine Translation

2018 ◽  
Vol 14 (1) ◽  
pp. 17-27
Author(s):  
Vimal Kumar K. ◽  
Divakar Yadav
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Semantic Analysis ◽  
Target Language ◽  
Translation System ◽  
Great Success ◽  
Source Language ◽  
Additional Information ◽  
Part Of Speech ◽  
Preceding Word

Corpus based natural language processing has emerged with great success in recent years. It is not only used for languages like English, French, Spanish, and Hindi but also is widely used for languages like Tamil, Telugu etc. This paper focuses to increase the accuracy of machine translation from Hindi to Tamil by considering the word's sense as well as its part-of-speech. This system works on word by word translation from Hindi to Tamil language which makes use of additional information such as the preceding words, the current word's part of speech and the word's sense itself. For such a translation system, the frequency of words occurring in the corpus, the tagging of the input words and the probability of the preceding word of the tagged words are required. Wordnet is used to identify various synonym for the words specified in the source language. Among these words, the one which is more relevant to the word specified in source language is considered for the translation to target language. The introduction of the additional information such as part-of-speech tag, preceding word information and semantic analysis has greatly improved the accuracy of the system.

scholarly journals New treebank or repurposed? On the feasibility of cross-lingual parsing of Romance languages with Universal Dependencies

2017 ◽  
Vol 24 (1) ◽  
pp. 91-122 ◽  
Author(s):  
MARCOS GARCIA ◽  
CARLOS GÓMEZ-RODRÍGUEZ ◽  
MIGUEL A. ALONSO
Keyword(s):  
Direct Application ◽  
Lessons Learned ◽  
Target Language ◽  
Romance Languages ◽  
Manual Annotation ◽  
Training Corpus ◽  
Target Languages ◽  
Cross Lingual ◽  
The Impact ◽  
Selection Of

AbstractThis paper addresses the feasibility of cross-lingual parsing with Universal Dependencies (UD) between Romance languages, analyzing its performance when compared to the use of manually annotated resources of the target languages. Several experiments take into account factors such as the lexical distance between the source and target varieties, the impact of delexicalization, the combination of different source treebanks or the adaptation of resources to the target language, among others. The results of these evaluations show that the direct application of a parser from one Romance language to another reaches similar labeled attachment score (LAS) values to those obtained with a manual annotation of about 3,000 tokens in the target language, and unlabeled attachment score (UAS) results equivalent to the use of around 7,000 tokens, depending on the case. These numbers can noticeably increase by performing a focused selection of the source treebanks. Furthermore, the removal of the words in the training corpus (delexicalization) is not useful in most cases of cross-lingual parsing of Romance languages. The lessons learned with the performed experiments were used to build a new UD treebank for Galician, with 1,000 sentences manually corrected after an automatic cross-lingual annotation. Several evaluations in this new resource show that a cross-lingual parser built with the best combination and adaptation of the source treebanks performs better (77 percent LAS and 82 percent UAS) than using more than 16,000 (for LAS results) and more than 20,000 (UAS) manually labeled tokens of Galician.

scholarly journals Inflection rules for Marathi to English in rule based machine translation

2021 ◽  
Vol 10 (3) ◽  
pp. 780
Author(s):  
Namrata G Kharate ◽  
Varsha H Patil
Keyword(s):  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
Important Application ◽  
Target Language ◽  
Rule Based ◽  
Parts Of Speech ◽  
Source Language ◽  
Target Languages ◽  
Correct Translation

Machine translation is important application in natural language processing. Machine translation means translation from source language to target language to save the meaning of the sentence. A large amount of research is going on in the area of machine translation. However, research with machine translation remains highly localized to the particular source and target languages as they differ syntactically and morphologically. Appropriate inflections result correct translation. This paper elaborates the rules for inflecting the parts-of-speech and implements the inflection for Marathi to English translation. The inflection of nouns, pronouns, verbs, adjectives are carried out on the basis of semantics of the sentence. The results are discussed with examples.

scholarly journals Reusing Monolingual Pre-Trained Models by Cross-Connecting Seq2seq Models for Machine Translation

2021 ◽  
Vol 11 (18) ◽  
pp. 8737
Author(s):  
Jiun Oh ◽  
Yong-Suk Choi
Keyword(s):  
Machine Translation ◽  
Intermediate Layer ◽  
Language Model ◽  
Target Language ◽  
Source Language ◽  
Performance Change ◽  
The Cross ◽  
Target Languages ◽  
Cross Connection

This work uses sequence-to-sequence (seq2seq) models pre-trained on monolingual corpora for machine translation. We pre-train two seq2seq models with monolingual corpora for the source and target languages, then combine the encoder of the source language model and the decoder of the target language model, i.e., the cross-connection. We add an intermediate layer between the pre-trained encoder and the decoder to help the mapping of each other since the modules are pre-trained completely independently. These monolingual pre-trained models can work as a multilingual pre-trained model because one model can be cross-connected with another model pre-trained on any other language, while their capacity is not affected by the number of languages. We will demonstrate that our method improves the translation performance significantly over the random baseline. Moreover, we will analyze the appropriate choice of the intermediate layer, the importance of each part of a pre-trained model, and the performance change along with the size of the bitext.

Sign in / Sign up

Export Citation Format

Share Document