In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task ("sentence boundary" or "not sentence boundary"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams.
We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the trained models in posterior real life ASR transcriptions.
Three different architectures are tested showing similar results; general accuracy for all models overpasses 0.96. All three models have good F1 scores reaching values over 0.97 regarding the "not sentence boundary" class. However, the "sentence boundary" class reflects lower scores decreasing the F1 metric to 0.778 for one of the models.
Using subword-level information vectors seem to be very effective leading to conclude that the morphology of words encoded in the embeddings representations behave like pixels in an image making feasible the use of convolutional neural network architectures.
Airudit（艾鲁迪特）；ENSEIRB-MATMECA（ENSEIRB-MATMECA工程学院）；Univ. de Bordeaux（波尔多大学）；INP（波尔多国立综合理工学院）；CNRS（法国国家科学研究中心）；LaBRI（波尔多计算机科学研究所）
Recently, end-to-end ASR based either on sequence-to-sequence networks or on the CTC objective function gained a lot of interest from the community, achieving competitive results over traditional systems using robust but complex pipelines. One of the main features of end-to-end systems, in addition to the ability to free themselves from extra linguistic resources such as dictionaries or language models, is the capacity to model acoustic units such as characters, subwords or directly words; opening up the capacity to directly translate speech with different representations or levels of knowledg…
This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword units. While existing subword segmentation tools assume that the input is pre-tokenized into word sequences, SentencePiece can train subword models directly from raw sentences, which allows us to make a purely end-to-end and language independent system. We perform a validation experiment of NMT on English-Japanese machine translation, and find that it is po…
Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear fastText models is mostly due to their use of subword information. In previous work, the optimization of fastText's subword sizes has not been fully explored, and non-English fastText models were trained using subword sizes optimized for English and German word analogy tasks. In our work, we find the optimal subword sizes on the English, German, Czech, Ita…
Recent works in spoken language translation (SLT) have attempted to build end-to-end speech-to-text translation without using source language transcription during learning or decoding. However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (100h) and open source parallel corpora that include speech in a source language aligned to text in a target language. This paper tries to fill this gap by augmenting an existing (monolingual) corpus: LibriSpeech. This corpus, used for automatic speech rec…
Volkswagen AG（大众汽车集团）；Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）
Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods are designed for a high resource setting in machine translation where millions of parallel sentences are available. This amount reduces to a few thousands of sentences when dealing with low-resource languages failing the existing established IBM models. In this paper, we propose subword sampling-based alignment of text units. This method's hypothesis is that …
In this paper, we present a data set and methods to compare speech processing models and human behaviour on a phone discrimination task. We provide Perceptimatic, an open data set which consists of French and English speech stimuli, as well as the results of 91 English- and 93 French-speaking listeners. The stimuli test a wide range of French and English contrasts, and are extracted directly from corpora of natural running read speech, used for the 2017 Zero Resource Speech Challenge. We provide a method to compare humans' perceptual space with models' representational space, and we apply it t…
Department of Computer Science and Engineering（计算机科学与工程系）；Ohio State University（俄亥俄州立大学）
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with s…
This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out for learning and inference. A mixed character-subword transformer is proposed, which enables exact log marginal likelihood estimation and exact MAP inference to find target segmentations with maximum posterior probability. DPE uses a lightweight mixed character-subword transformer as a means of pre-processing parallel data to segment output sentences using dyn…
A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is also impacted by the specific choice of data format for representing the sentences as subwords. In a phrase-based SMT framework, we investigate different choices of decoder parameters as well as data format and their impact on decoding time and translation accuracy. We suggest best options for these settings that significantly improve decoding time with lit…
Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and multiple segmentations are possible even with the same vocabulary. The question addressed in this paper is whether it is possible to harness the segmentation ambiguity as a noise to improve the robustness of NMT. We present a simple regularization method, subword regularization, which trains the model with multiple subword segmentations probabilistically sampled du…
We present a challenge set for French --> English machine translation based on the approach introduced in Isabelle, Cherry and Foster (EMNLP 2017). Such challenge sets are made up of sentences that are expected to be relatively difficult for machines to translate correctly because their most straightforward translations tend to be linguistically divergent. We present here a set of 506 manually constructed French sentences, 307 of which are targeted to the same kinds of structural divergences as in the paper mentioned above. The remaining 199 sentences are designed to test the ability of the sy…
M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR
School of Computer Science and Engineering, Northeastern University, Shenyang, China（计算机科学与工程学院，东北大学，沈阳，中国）；NiuTrans Research（NiuTrans研究院）；Kunming University of Science and Technology, China（昆明理工大学，中国）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Key Laboratory of Intelligent Information Processing（智能信息处理重点实验室）；ADAPT Centre, School of Computing, Dublin City University（都柏林城市大学计算学院 ADAPT 中心）
We participated in the MLWS 2017 on Tibetan word segmentation task, our system is trained in a unrestricted way, by introducing a baseline system and 76w tibetan segmented sentences of ours. In the system character sequence is processed by the baseline system into word sequence, then a subword unit (BPE algorithm) split rare words into subwords with its corresponding features, after that a neural network classifier is adopted to token each subword into "B,M,E,S" label, in decoding step a simple rule is used to recover a final word sequence. The candidate system for submition is selected by eva…
We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and the substitution between two close subtokens has a similar effect to the character modification. Our method mainly contains three steps. First, a gradient-based method is adopted to find the most vulnerable words in the sentence. Then we split the selected words into subtokens to replace the origin tokenization result from the transformer tokenizer. Finally…
How Important Is Tokenization in French Medical Masked Language Models?
LIA, Avignon University（阿维尼翁大学计算机科学与人工智能实验室）；Zenidoc（Zenidoc公司）；Nantes Université（南特大学）；École Centrale Nantes（南特中央理工学院）；CNRS（法国国家科学研究中心）；LS2N, UMR 6004（南特数字科学实验室）
Uppsala University（乌普萨拉大学）；University of Edinburgh（爱丁堡大学）
Pronouns are a long-standing challenge in machine translation. We present a study of the performance of a range of rule-based, statistical and neural MT systems on pronoun translation based on an extensive manual evaluation using the PROTEST test suite, which enables a fine-grained analysis of different pronoun types and sheds light on the difficulties of the task. We find that the rule-based approaches in our corpus perform poorly as a result of oversimplification, whereas SMT and early NMT systems exhibit significant shortcomings due to a lack of awareness of the functional and referential p…
University of Grenoble（格勒诺布尔大学）；University of Neuchatel（纳沙泰尔大学）
Presidential speeches indicate the government's intentions and justifications supported by a dedicated style and rhetoric oscillating between explanation and controversy. Over a period of sixty years, can we observe stylistic variations by the different French presidents of the Fifth Republic (1958-2018)? Based on official transcripts of all their allocution, this paper illustrates the stylistic evolution and presents the underlying main trends. This study shows that de Gaulle's rhetoric is not mainly dedicated to his own person, or that the two terms of J. Chirac are not fully similar. Accord…
In this paper we present a new method to learn a model robust to typos for a Named Entity Recognition task. Our improvement over existing methods helps the model to take into account the context of the sentence inside a court decision in order to recognize an entity with a typo. We used state-of-the-art models and enriched the last layer of the neural network with high-level information linked with the potential of the word to be a certain type of entity. More precisely, we utilized the similarities between the word and the potential entity candidates in the tagged sentence context. The experi…
Trinity College Dublin（都柏林圣三一学院）；Dublin City University（都柏林城市大学）
Building Machine Translation (MT) systems for low-resource languages remains challenging. For many language pairs, parallel data are not widely available, and in such cases MT models do not achieve results comparable to those seen with high-resource languages. When data are scarce, it is of paramount importance to make optimal use of the limited material available. To that end, in this paper we propose employing the same parallel sentences multiple times, only changing the way the words are split each time. For this purpose we use several Byte Pair Encoding models, with various merge operation…
Many recent works have demonstrated that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject. We take a critical look at this line of research by showing that it is possible to achieve high accuracy on this agreement task with simple surface heuristics, indicating a possible flaw in our assessment of neural networks' syntactic ability. Our fine-grained analyses of results on the long-range French object-verb agreement show that contrary to LSTMs, Transform…
Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale. This work improves the prediction and annotation of fine-grained semantic divergences. We introduce a training strategy for multilingual BERT models by learning to rank synthetic divergent examples of varying granularity. We evaluate our models on the Rationalized English-French Semantic Divergences, a new dataset released with this work, consisting of Engl…
Universite Gaston Berger (UGB)（加斯顿·伯杰大学）；University of Bergen（卑尔根大学）；Universite Virtuelle du Senegal (UVS)（塞内加尔虚拟大学）；Dailymotion（Dailymotion公司）
In this paper, we propose a neural machine translation system for Wolof, a low-resource Niger-Congo language. First we gathered a parallel corpus of 70000 aligned French-Wolof sentences. Then we developped a baseline LSTM based encoder-decoder architecture which was further extended to bidirectional LSTMs with attention mechanisms. Our models are trained on a limited amount of parallel French-Wolof data of approximately 35000 parallel sentences. Experimental results on French-Wolof translation tasks show that our approach produces promising translations in extremely low-resource conditions. Th…
University of Oslo（奥斯陆大学）；University of Copenhagen（哥本哈根大学）；Uppsala University（乌普萨拉大学）
Recent studies have shown that language models pretrained and/or fine-tuned on randomly permuted sentences exhibit competitive performance on GLUE, putting into question the importance of word order information. Somewhat counter-intuitively, some of these studies also report that position embeddings appear to be crucial for models' good performance with shuffled text. We probe these language models for word order information and investigate what position embeddings learned from shuffled text encode, showing that these models retain information pertaining to the original, naturalistic word orde…
Enhancing Neural Machine Translation with Semantic Units
Key Laboratory of Intelligent Information Processing（智能信息处理重点实验室）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well done by an encoder with self-attention mechanism. Though Transformer-based encoder may effectively capture general information in its resulting source sentence representation, the backbone information, which stands for the gist of a sentence, is not specifically focused on. In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT. In practice, an explicit …
In this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences sampled from two vicinity distributions, of which the crucial one is a novel vicinity distribution for adversarial sentences that describes a smooth interpolated embedding space centered around observed training sentence pairs. We then discuss our approach, AdvAug, to train NMT models using the embeddings of virtual sentences in sequence-to-sequence learning. Experiments on Chinese-English, English-French, and English-German …
This paper describes the design principles behind jsRealB (Version 4.0), a surface realizer written JavaScript for English or French sentences from a specification inspired by the constituent syntax formalism but for which a dependency-based input notation is also available. jsRealB can be used either within a web page or as a node.js module. We show that the seemingly simple process of text realization involves many interesting implementation challenges in order to take into account the specifics of each language. jsRealB has a large coverage of English and French and has been used to develop…
University of La Rochelle（拉罗谢尔大学）；University of Avignon（阿维尼翁大学）；Polytechnique Montréal（蒙特利尔高等理工学院）；Inst. Federal de Educação, Ciência e Tecnologia da Paraiba（帕拉伊巴联邦教育、科学与技术学院）；Univ. Federal Fluminense（弗鲁米嫩塞联邦大学）；Universidade Federal do Ceará（塞阿拉联邦大学）
Multi-Sentence Compression (MSC) aims to generate a short sentence with the key information from a cluster of similar sentences. MSC enables summarization and question-answering systems to generate outputs combining fully formed sentences from one or several documents. This paper describes an Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, with the goal of generating more informative sentences while maintaining their grammaticality. Our system is of good quality and outperforms the state of the art for evaluations led on news datasets in thr…
The success of deep learning in natural language processing raises intriguing questions about the nature of linguistic meaning and ways in which it can be processed by natural and artificial systems. One such question has to do with subword segmentation algorithms widely employed in language modeling, machine translation, and other tasks since 2016. These algorithms often cut words into semantically opaque pieces, such as 'period', 'on', 't', and 'ist' in 'period|on|t|ist'. The system then represents the resulting segments in a dense vector space, which is expected to model grammatical relatio…
The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., "wine" (word-level) in English vs.\ "v i n" (character-level) in French, which make it …
In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary. For each sentence or batch, we only predict the target words in its sentence-level or batch-level vocabulary. Thus, we reduce both the computing time and the memory usage. Our method simply takes into account the translation options of each word or phrase in th…
In this paper we present a set of experiments carried out with BERT on a number of Italian sentences taken from poetry domain. The experiments are organized on the hypothesis of a very high level of difficulty in predictability at the three levels of linguistic complexity that we intend to monitor: lexical, syntactic and semantic level. To test this hypothesis we ran the Italian version of BERT with 80 sentences for a total of 900 tokens mostly extracted from Italian poetry of the first half of last century. Then we alternated canonical and noncanonical versions of the same sentence before pro…
This repport concerns automatic understanding of (french) iterative sentences, i.e. sentences where one single verb has to be interpreted by a more or less regular plurality of events. A linguistic analysis is proposed along an extension of Reichenbach's theory, several formal representations are considered and a corpus of 18000 newspaper extracts is described.
University of California, Santa Barbara（加州大学圣巴巴拉分校）
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences fro…
Although many context-aware neural machine translation models have been proposed to incorporate contexts in translation, most of those models are trained end-to-end on parallel documents aligned in sentence-level. Because only a few domains (and language pairs) have such document-level parallel data, we cannot perform accurate context-aware translation in most domains. We therefore present a simple method to turn a sentence-level translation model into a context-aware model by incorporating a document-level language model into the decoder. Our context-aware decoder is built upon only a sentenc…
Recovering document annotations for sentence-level bitext
Johns Hopkins University（约翰斯·霍普金斯大学）；Human Language Technology Center of Excellence（卓越人类语言技术中心）；Center of Language and Speech Processing（语言与言语处理中心）；Microsoft（微软公司）
This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parall…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data. The models proposed for unsupervised NMT often use only one shared encoder to map the pairs of sentences from different languages to a shared-latent space, which is weak in keeping the unique and internal characteristics of each language, such as the style, terminology, and sentence structure. To address this issue, we introduce an extension by utilizing two independent encoders but sharing some partial weights which are responsible…
State-of-the-art (SOTA) neural machine translation (NMT) systems translate texts at sentence level, ignoring context: intra-textual information, like the previous sentence, and extra-textual information, like the gender of the speaker. Because of that, some sentences are translated incorrectly. Personalised NMT (PersNMT) and document-level NMT (DocNMT) incorporate this information into the translation process. Both fields are relatively new and previous work within them is limited. Moreover, there are no readily available robust evaluation metrics for them, which makes it difficult to develop …
In this paper, we describe an approach to sentence categorization which has the originality to be based on natural properties of languages with no training set dependency. The implementation is fast, small, robust and textual errors tolerant. Tested for french, english, spanish and german discrimination, the system gives very interesting results, achieving in one test 99.4% correct assignments on real sentences. The resolution power is based on grammatical words (not the most common words) and alphabet. Having the grammatical words and the alphabet of each language at its disposal, the system …
The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers. This allows to encode the entire source sentence simultaneously compared to recurrent networks for which computation is constrained by temporal dependencies. On WMT'16 English-Romanian translation we achieve competitive accuracy to the state-of-the-art and we outperform several recently published results on the WMT'15 English-German task. Our models obtain almost the same accu…
ByteDance AI Lab（字节跳动人工智能实验室）；Mobile Internet Group, Tencent Technology Co., Ltd（腾讯科技有限公司移动互联网事业群）；Xiamen University（厦门大学）；Tianjin University（天津大学）
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}. \textsc{CapsNMT} uses an aggregation mechanism to map the source sentence into a matrix with pre-determined size, and then applys a deep LSTM network to decode the target sequence from the source representation. Unlike the previous work \cite{sutskever2014sequence} to store the source sentence with a passive and bottom-up way, the dynamic routing policy encodes the source sentence with an iterative process to decide the credit attribut…
Laboratoire Informatique d’Avignon（阿维尼翁计算机实验室）；École Polytechnique de Montréal（蒙特利尔综合理工学院）
This paper describes Artex, another algorithm for Automatic Text Summarization. In order to rank sentences, a simple inner product is calculated between each sentence, a document vector (text topic) and a lexical vector (vocabulary used by a sentence). Summaries are then generated by assembling the highest ranked sentences. No ruled-based linguistic post-processing is necessary in order to obtain summaries. Tests over several datasets (coming from Document Understanding Conferences (DUC), Text Analysis Conferences (TAC), evaluation campaigns, etc.) in French, English and Spanish have shown tha…
University of Zurich（苏黎世大学）；LIMSI, CNRS, Univ. Paris-Sud, Université Paris-Saclay（法国国家科学研究中心、巴黎第十一大学、巴黎萨克雷大学联合计算机科学与数学应用实验室）；University of Edinburgh（爱丁堡大学）
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models' ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to Fren…
CLLE-ERSS, CNRS and Université Toulouse 2 – Le Mirail（CLLE-ERSS，法国国家科学研究中心和图卢兹第二大学）；CNES（法国国家空间研究中心）
The long term aim of the project carried out by the French National Space Agency (CNES) is to design a writing guide based on the real and regular writing of requirements. As a first step in the project, this paper proposes a lin-guistic analysis of requirements written in French by CNES engineers. The aim is to determine to what extent they conform to two rules laid down in INCOSE, a recent guide for writing requirements. Although CNES engineers are not obliged to follow any Controlled Natural Language in their writing of requirements, we believe that language regularities are likely to emerg…
This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection. The main contributions of this paper are the following: (a) we introduce new cross-language similarity detection methods based on distributed representation of words; (b) we combine the different methods proposed to verify their complementarity and finally obtain an overall F1 score of 89.15% for English-French similarity detection at chunk level (88.5% at sentence level) on a very challenging corpus.
We present the contribution of the Unbabel team to the WMT 2019 Shared Task on Quality Estimation. We participated on the word, sentence, and document-level tracks, encompassing 3 language pairs: English-German, English-Russian, and English-French. Our submissions build upon the recent OpenKiwi framework: we combine linear, neural, and predictor-estimator systems with new transfer learning approaches using BERT and XLM pre-trained models. We compare systems individually and propose new ensemble techniques for word and sentence-level predictions. We also propose a simple technique for convertin…
Indian Institute of Technology Patna（印度理工学院巴特那分校）；International Institute of Information Technology Bhubaneswar（布巴内斯瓦尔国际信息技术研究所）
Analyzing customer feedback is the best way to channelize the data into new marketing strategies that benefit entrepreneurs as well as customers. Therefore an automated system which can analyze the customer behavior is in great demand. Users may write feedbacks in any language, and hence mining appropriate information often becomes intractable. Especially in a traditional feature-based supervised model, it is difficult to build a generic system as one has to understand the concerned language for finding the relevant features. In order to overcome this, we propose deep Convolutional Neural Netw…
The internet increased the amount of information available. However, the reading and understanding of this information are costly tasks. In this scenario, the Natural Language Processing (NLP) applications enable very important solutions, highlighting the Automatic Text Summarization (ATS), which produce a summary from one or more source texts. Automatically summarizing one or more texts, however, is a complex task because of the difficulties inherent to the analysis and generation of this summary. This master's thesis describes the main techniques and methodologies (NLP and heuristics) to gen…
Vasile Alecsandri University of Bacau（巴克乌瓦西里·亚历山德里大学）；EduSoft Bacau（巴克乌EduSoft公司）
This paper refers to the syntactic analysis of phrases in Romanian, as an important process of natural language processing. We will suggest a real-time solution, based on the idea of using some words or groups of words that indicate grammatical category; and some specific endings of some parts of sentence. Our idea is based on some characteristics of the Romanian language, where some prepositions, adverbs or some specific endings can provide a lot of information about the structure of a complex sentence. Such characteristics can be found in other languages, too, such as French. Using a special…
