Phrase Pairs Research Articles

Bilingual phrase induction with local hard negative sampling

AbstractBilingual lexicon induction focuses on learning word translation pairs, also known as bitexts, from monolingual corpora by establishing a mapping between the source and target embedding spaces. Despite recent advancements, bilingual lexicon induction is limited to inducing bitexts consisting of individual words, lacking the ability to handle semantics‐rich phrases. To bridge this gap and support downstream cross‐lingual tasks, it is practical to develop a method for bilingual phrase induction that extracts bilingual phrase pairs from monolingual corpora without relying on cross‐lingual knowledge. In this paper, the authors propose a novel phrase embedding training method based on the skip‐gram structure. Specifically, a local hard negative sampling strategy that utilises negative samples of central tokens in sliding windows to enhance phrase embedding learning is introduced. The proposed method achieves competitive or superior performance compared to baseline approaches, with exceptional results recorded for distant languages. Additionally, we develop a phrase representation learning method that leverages multilingual pre‐trained language models. These mPLMs‐based representations can be combined with the above‐mentioned static phrase embeddings to further improve the accuracy of the bilingual phrase induction task. We manually construct a dataset of bilingual phrase pairs and integrate it with MUSE to facilitate the bilingual phrase induction task.

Age effects on prosodic boundary perception.

The redundancy hypothesis proposes that older listeners need a larger array of acoustic cues than younger listeners for effective speech perception. This research investigated this hypothesis by examining the aging effects on the use of prosodic cues in speech segmentation in Mandarin Chinese. We examined how younger and older listeners perceived prosodic boundaries using three main prosodic cues (pause, final lengthening, and pitch change) across eight conditions involving different cue combinations. The stimuli consisted of syntactically ambiguous phrase pairs, each containing two or three objects. Participants (22 younger listeners and 22 older listeners) performed a speech recognition task to judge the number of objects they heard. Both groups primarily relied on the pause cue for identifying prosodic boundaries, using final lengthening and pitch change as secondary cues. However, older listeners showed reduced sensitivity to these cues, compensating by integrating the primary cue pause with the secondary cue pitch change for more precise segmentation. The present study reveals older listeners' integration strategy in using prosodic cues for speech segmentation, supporting the redundancy hypothesis. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Lexico-syntactic analysis of antonyms in some speeches of John Dramani Mahama

Language and politics are intertwined. This is because in order to champion political interest, politicians rely on some powerful linguistic resources to communicate with their audience. Available literature suggests that one of such linguistic resources is antonyms. However, researchers have not paid attention to the use of antonyms in political discourse, especially, in Ghana. On account of this, the present study investigated the lexico-syntactic features of antonyms in some speeches of John Dramani Mahama, a former President of the Republic of Ghana. The study is an interface between cognitive semantics and political discourse which sought to discover the lexico-syntactic features and the functional implications of the antonym pairs used in the speeches of John Dramani Mahama. The study was conducted within the framework of the Lexical Field Theory and the speeches were analysed, using the qualitative research method. Through the use of purposive sampling method, sixteen (16) political speeches of John Dramani Mahama were selected for the analysis. The study relied on Cruse’s (1986) outlined features of antonymy and Murphy’s (2003) theoretical view on context-derived antonymy to identify the antonym pairs in the speeches. The study discovered one hundred and seventy-three (173) antonym pairs in the sixteen (16) selected speeches. The outcome of the study further revealed the noun phrase pair as the largest grammatical category in the selected speeches. The study again showed that John Dramani Mahama usually uses noun antonymic pairs and the coordinated frame X and Y in his political speeches. The study concluded that John Dramani Mahama uses antonyms in his speeches to persuade his audience, establish association, inspire hope and confidence, call for patriotism and hardworking towards national development, and finally, to present his political vision to Ghanaians.

PhrasIS: Phrase Inference and Similarity benchmark

Abstract We present PhrasIS, a benchmark dataset composed of natural occurring Phrase pairs with Inference and Similarity annotations for the evaluation of semantic representations. The described dataset fills the gap between word and sentence-level datasets, allowing to evaluate compositional models at a finer granularity than sentences. Contrary to other datasets, the phrase pairs are extracted from naturally occurring text in image captions and news headlines. All the text fragments have been annotated by experts following a rigorous process also described in the manuscript achieving high inter annotator agreement. In this work we analyse the dataset, showing the relation between inference labels and similarity scores. With 10K phrase pairs split in development and test, the dataset is an excellent benchmark for testing meaning representation systems.

Addressing data scarcity issue for English–Mizo neural machine translation using data augmentation and language model

Low-resource language in machine translation systems poses multiple complications regarding accuracy in translation due to insufficient incorporation of linguistic information. The difference in the linguistic information between the language pair also significantly impacts the dataset creation for improving translation accuracy. Although neural machine translation achieves a state-of-the-art approach, dealing with low-resource language is challenging since it struggled with limited resources. This paper attempts to address the data scarcity problem using augmentation of synthetic parallel sentences, source-target phrase pairs, and language models at the target side for English-to-Mizo and Mizo-to-English translation via transformer-based neural machine translation. We have attained state-of-the-art results for both directions of translation.

Exploration and Research on Chinese Culture in University English Translation Teaching in the Background of Internet+

Abstract Under the background of Internet+, for the problems of high comprehension difficulty and inaccurate translation in university English translation teaching, this paper proposes the skeleton knowledge translation model to assist university English translation teaching that integrates Chinese culture. Starting from the objectives of university English translation teaching, Chinese culture is explored in university English translation materials to complete the design of university English translation teaching that integrates Chinese culture. Propose the application of Internet technology in the above teaching design, utilize the IBM word alignment model and TF-IDF similarity to preprocess the university English translation textbooks, and on the basis of preprocessing, estimate the probability and decode the generated phrase pairs, and then complete the construction of the English translation model based on skeleton knowledge. The English translation model’s performance analysis is carried out using skeleton knowledge after determining the data set and evaluation criteria. The results show that for the whole 400 000 batch training, the training time of the English translation model based on skeleton knowledge is about one-fifth less than that of the unsupervised neural machine translation model, indicating that with the increase of the number of rounds, the performance of the English translation model based on skeleton knowledge is also better. This study serves as a guide for exploring and researching Chinese culture in university English translation teaching and promotes the development of university English translation teaching in colleges and universities.

CORRECTION OF TINNITUS AND NEUROPSYCHOLOGICAL STATUS OF PATIENTS WITH CEREBRAL ATHEROSCLEROSIS AND ESSENTIAL HYPERTENSION USING CITICOLINE AS PART OF COMPREHENSIVE THERAPY

Objective : to analyze the effect of neuroprotective therapy with citicoline in combination with hypotensive and hypolipidemic therapy on the correction of tinnitus and neuropsychological status in patients with atherosclerosis of the brachiocephalic and cerebral arteries and essential hypertension. Materials and methods. We examined 86 patients aged between 60 and 68 years with essential hypertension and atherosclerosis of the brachiocephalic and cerebral arteries. All patients were diagnosed with decompensated tinnitus that affected their quality of life. The Multidimensional Fatigue Inventory (MFI) was used to assess the severity of asthenic syndrome. The cognitive status was evaluated using the Schulte tables, word pair memory tests, and phrase pair memory tests. Study participants were divided into two groups. Patients in Group 1 ( n = 43) received nootropic therapy with citicoline at a dose of 1000 mg/day for 3 months in addition to standard hypotensive, hypolipidemic, and antiplatelet therapies. We found that citicoline as a part of comprehensive therapy facilitated regression of actual and moderate tinnitus in patients with atherosclerosis of the brachiocephalic and cerebral arteries and essential hypertension. This optimized the neurovegetative status of patients and improved their cognitive functions.

ECCParaCorp: a cross-lingual parallel corpus towards cancer education, dissemination and application

BackgroundThe increasing global cancer incidence corresponds to serious health impact in countries worldwide. Knowledge-powered health system in different languages would enhance clinicians’ healthcare practice, patients’ health management and public health literacy. High-quality corpus containing cancer information is the necessary foundation of cancer education. Massive non-structural information resources exist in clinical narratives, electronic health records (EHR) etc. They can only be used for training AI models after being transformed into structured corpus. However, the scarcity of multilingual cancer corpus limits the intelligent processing, such as machine translation in medical scenarios. Thus, we created the cancer specific cross-lingual corpus and open it to the public for academic use.MethodsAiming to build an English-Chinese cancer parallel corpus, we developed a workflow of seven steps including data retrieval, data parsing, data processing, corpus implementation, assessment verification, corpus release, and application. We applied the workflow to a cross-lingual, comprehensive and authoritative cancer information resource, PDQ (Physician Data Query). We constructed, validated and released the parallel corpus named as ECCParaCorp, made it openly accessible online.ResultsThe proposed English-Chinese Cancer Parallel Corpus (ECCParaCorp) consists of 6685 aligned text pairs in Xml, Excel, Csv format, containing 5190 sentence pairs, 1083 phrase pairs and 412 word pairs, which involved information of 6 cancers including breast cancer, liver cancer, lung cancer, esophageal cancer, colorectal cancer, and stomach cancer, and 3 cancer themes containing cancer prevention, screening, and treatment. All data in the parallel corpus are online, available for users to browse and download (http://www.phoc.org.cn/ECCParaCorp/).ConclusionsECCParaCorp is a parallel corpus focused on cancer in a cross-lingual form, which is openly accessible. It would make up the imbalance of scarce multilingual corpus resources, bridge the gap between human readable information and machine understanding data resources, and would contribute to intelligent technology application as a preparatory data foundation e.g. cancer-related machine translation, cancer system development towards medical education, and disease-oriented knowledge extraction.

Neural machine translation of low-resource languages using SMT phrase pair injection

AbstractNeural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence, many existing large-scale parallel corpus are limited to the specific languages and domains. In this paper, we propose an effective approach to improve an NMT system in low-resource scenario without using any additional data. Our approach aims at augmenting the original training data by means of parallel phrases extracted from the original training data itself using a statistical machine translation (SMT) system. Our proposed approach is based on the gated recurrent unit (GRU) and transformer networks. We choose the Hindi–English, Hindi–Bengali datasets for Health, Tourism, and Judicial (only for Hindi–English) domains. We train our NMT models for 10 translation directions, each using only 5–23k parallel sentences. Experiments show the improvements in the range of 1.38–15.36 BiLingual Evaluation Understudy points over the baseline systems. Experiments show that transformer models perform better than GRU models in low-resource scenarios. In addition to that, we also find that our proposed method outperforms SMT—which is known to work better than the neural models in low-resource scenarios—for some translation directions. In order to further show the effectiveness of our proposed model, we also employ our approach to another interesting NMT task, for example, old-to-modern English translation, using a tiny parallel corpus of only 2.7K sentences. For this task, we use publicly available old-modern English text which is approximately 1000 years old. Evaluation for this task shows significant improvement over the baseline NMT.

Distributed Representation of Words in Cause and Effect Spaces

This paper focuses on building up distributed representation of words in cause and effect spaces, a task-specific word embedding technique for causality. The causal embedding model is trained on a large set of cause-effect phrase pairs extracted from raw text corpus via a set of high-precision causal patterns. Three strategies are proposed to transfer the positive or negative labels from the level of phrase pairs to the level of word pairs, leading to three causal embedding models (Pairwise-Matching, Max-Matching, and AttentiveMatching) correspondingly. Experimental results have shown that Max-Matching and Attentive-Matching models significantly outperform several state-of-the-art competitors by a large margin on both English and Chinese corpora.

Syntactic Matching Methods in Pivot Translation

The pivot translation is useful method for translating between languages that contain little or no parallel data by utilizing equivalents in an intermediate language such as English. Commonly, phrase-based or tree-based pivot translation methods merge source–pivot and pivot–target translation models into a source–target model. This tactic is known as triangulation. However, the combination is based on the surface forms of constituent words, and it often produces incorrect source–target phrase pairs because of interlingual differences and semantic ambiguities in the pivot language. The translation accuracy is thus degraded. This paper proposes a triangulation approach that utilizes syntactic subtrees in the pivot language to avoid incorrect phrase combinations by distinguishing pivot language words by their syntactic roles. The results of the experiments conducted on the United Nations Parallel Corpus demonstrate that the proposed method is superior to other pivot translation approaches in all tested combinations of languages.

A unified framework and models for integrating translation memory into phrase-based statistical machine translation

Since statistical machine translation (SMT) and translation memory (TM) complement each other in TM matched and unmatched regions, a unified framework for integrating TM into phrase-based SMT is proposed in this paper. Unlike previous two-stage pipeline approaches, which directly merge TM results into the input sentences and subsequently let the SMT only translates those unmatched regions, the proposed framework refers to the corresponding TM information associated with each phrase at the SMT decoding. Under this unified framework, several integrated models are proposed to incorporate different types of information extracted from TM to guide the SMT decoding. We thus let SMT implicitly and indirectly utilize global context with a local dependency model. Furthermore, the SMT phrase table is dynamically enhanced with TM phrase pairs when the TM database and the SMT training set are different.On a Chinese–English TM database, our experiments show that the proposed Model-I significantly improves over both SMT and TM when the SMT training set is also adopted as the TM database and when the fuzzy match score is over 0.4 (overall 3.5 BLEU points improvement and 2.6 TER points reduction). In addition, the proposed Model-II is significantly better than the TM and the SMT systems when the SMT training set and the TM database are different. Furthermore, the proposed Model-III outperforms both the TM and the SMT systems even when the SMT training set and the TM database are from different domains. Additionally, the proposed Model-IV further achieves significant improvements with the help of Top-N TM sentence pairs. Lastly, all our models significantly outperform those state-of-the-art approaches under all test conditions.

Research on the Information Processing Model of Source Language of Parallel Corpus

The rapid development of corpus-based machine translation brings opportunities and challenges to the construction of corpus. With the continuous development of information technology, the information processing model of the source language has always been an academic hot topic in natural language processing. In the current machine translation framework, this paper proposes a parallel corpora source language processing model for translation equivalent trees. Firstly, the phrases in the source language and the target language sentence are tagged with parts of speech respectively; Secondly, the word alignment tool is used to align the phrase pairs of the source language and the target language; Syntax analysis is used to parse the source language sentence; Then, a translation equivalence tree is constructed based on the source language syntax tree, target language sentence and word alignment results. Finally, phrase translation pairs are extracted from the translation equivalent tree.

Integrating Shallow Syntactic Labels in the Phrase-Boundary Translation Model

Using a novel rule labeling method, this article proposes a hierarchical model for statistical machine translation. The proposed model labels translation rules by matching the boundaries of target side phrases with the shallow syntactic labels including POS tags and chunk labels on the target side of the training corpus. The boundary labels are concatenated if there is no label for the whole target span. Labeling with the classes of boundary words on the target side phrases has been previously proposed as a phrase-boundary model which can be considered as the base form of our model. In the extended model, the labeler uses a POS tag if there is no chunk label in one boundary. Using chunks as phrase labels, the proposed model generalizes the rules to decrease the model sparseness. The sparseness is a more important issue in the language pairs with a lot of differences in the word order because they have less number of aligned phrase pairs for extraction of rules. The extended phrase-boundary model is also applicable for low-resource languages having no syntactic parser. Some experiments are performed with the proposed model, the base phrase-boundary model, and variants of Syntax Augmented Machine Translation (SAMT) in translation from Persian and German to English as source and target languages with different word orders. According to the results, the proposed model improves the translation performance in the quality and decoding time aspects. Using BLEU as our metric, the proposed model has achieved a statistically significant improvement of about 0.5 point over the base phrase-boundary model.

Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation

We propose a new method for inducing a phrase-based translation model from a pair of unrelated monolingual corpora. Our method is able to deal with phrases of arbitrary length and to find phrase pairs that are useful for statistical machine translation, without requiring large parallel or comparable corpora. First, our method generates phrase pairs through coupling source and target phrases separately collected from respective monolingual data. Then, for each phrase pair, we compute features using the monolingual data and a small quantity of parallel sentences. Finally, incorrect phrase pairs are pruned, and a phrase table is made using the remaining phrase pairs. In our experiments on French--Japanese and Spanish--Japanese translation tasks under low-resource conditions, we observe that incorporating a phrase table induced by our method to the machine translation system leads to large improvements in translation quality. Furthermore, we show that a phrase table induced by our method can also be useful in a wide range of configurations, including configurations where we have already access to large parallel corpora and configurations where only small monolingual corpora are available.

Minimum Bayes-Risk Phrase Table Pruning for Pivot-Based Machine Translation in Internet of Things

Machine translation, which will be used widely in human-computer interaction services to Internet of Things (IoT), is a key technology in artificial intelligence field. This paper presents a minimum Bayes-risk (MBR) phrase table pruning method for pivot-based statistical machine translation (SMT). The SMT system requires a great amount of bilingual data to build a high-performance translation model. For some language pairs, such as Chinese-English, massive bilingual data are available on the web. However, for most language pairs, large-scale bilingual data are hard to obtain. Pivot-based SMT is proposed to solve the data scarcity problem: it introduces a pivot language to bridge the source language and the target language. Therefore, a source-target translation model based on well-trained source-pivot and pivot-target translation models can be derived with the pivot-based approach. However, due to the ambiguities of the pivot language, source and target phrases with different meanings may be wrongly matched. Consequently, the derived source-target phrase table may contain incorrect phrase pairs. To alleviate this problem, we apply the MBR method to prune the phrase table. The MBR pruning method removes the phrase pairs with the lowest risk from the phrase table. Experimental results on Europarl data show that the proposed method can both reduce the size of phrase tables and improve the performance of translations. This study also gives a useful reference to many IoT research field and smart web services.

Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation

We present a new framework to induce an in-domain phrase table from in-domain monolingual data that can be used to adapt a general-domain statistical machine translation system to the targeted domain. Our method first compiles sets of phrases in source and target languages separately and generates candidate phrase pairs by taking the Cartesian product of the two phrase sets. It then computes inexpensive features for each candidate phrase pair and filters them using a supervised classifier in order to induce an in-domain phrase table. We experimented on the language pair English–French, both translation directions, in two domains and obtained consistently better results than a strong baseline system that uses an in-domain bilingual lexicon. We also conducted an error analysis that showed the induced phrase tables proposed useful translations, especially for words and phrases unseen in the parallel data used to train the general-domain baseline system.

Extracting parallel phrases from comparable data for machine translation

AbstractMining parallel data from comparable corpora is a promising approach for overcoming the data sparseness in statistical machine translation and other natural language processing applications. In this paper, we address the task of detecting parallel phrase pairs embedded in comparable sentence pairs. We present a novel phrase alignment approach that is designed to only align parallel sections bypassing non-parallel sections of the sentence. We compare the proposed approach with two other alignment methods: (1) the standard phrase extraction algorithm, which relies on the Viterbi path of the word alignment, (2) a binary classifier to detect parallel phrase pairs when presented with a large collection of phrase pair candidates. We evaluate the accuracy of these approaches using a manually aligned data set, and show that the proposed approach outperforms the other two approaches. Finally, we demonstrate the effectiveness of the extracted phrase pairs by using them in Arabic–English and Urdu–English translation systems, which resulted in improvements upto 1.2 Bleu over the baseline. The main contributions of this paper are two-fold: (1) novel phrase alignment algorithms to extract parallel phrase pairs from comparable sentences, (2) evaluating the utility of the extracted phrases by using them directly in the MT decoder.

Integrating Rules and Dictionaries from Shallow-Transfer Machine Translation into Phrase-Based Statistical Machine Translation

We describe a hybridisation strategy whose objective is to integrate linguistic resources from shallow-transfer rule-based machine translation (RBMT) into phrase-based statistical machine translation (PBSMT). It basically consists of enriching the phrase table of a PBSMT system with bilingual phrase pairs matching transfer rules and dictionary entries from a shallow-transfer RBMT system. This new strategy takes advantage of how the linguistic resources are used by the RBMT system to segment the source-language sentences to be translated, and overcomes the limitations of existing hybrid approaches that treat the RBMT systems as a black box. Experimental results confirm that our approach delivers translations of higher quality than existing ones, and that it is specially useful when the parallel corpus available for training the SMT system is small or when translating out-of-domain texts that are well covered by the RBMT dictionaries. A combination of this approach with a recently proposed unsupervised shallow-transfer rule inference algorithm results in a significantly greater translation quality than that of a baseline PBSMT; in this case, the only hand-crafted resource used are the dictionaries commonly used in RBMT. Moreover, the translation quality achieved by the hybrid system built with automatically inferred rules is similar to that obtained by those built with hand-crafted rules.

Extraction and Presentation of Bilingual Correspondences from Slovak-Bulgarian Parallel Corpus

Extraction and Presentation of Bilingual Correspondences from Slovak-Bulgarian Parallel CorpusIn this paper the results of the automatic extraction and presentation of bilingual correspondences from Slovak-Bulgarian Parallel corpus are described. The equivalent phrases are extracted from sentence and word level automatically aligned corpus, filtered, indexed and presented in a dictionary-like interface. The bilingual dictionary database contains 80 thousand phrase pairs consisting of approximately 350 thousand words (per each language). Counting unique word forms, the size is 31 thousand in the Slovak part of the dictionary, 26 thousand in the Bulgarian part.