Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts tagging accuracy for rare / unseen words. We also demonstrate that 3) the improved tagging performance by AT contributes to the downstream task of dependency parsing, and that 4) AT helps the model to learn cleaner word representations. 5) The proposed AT model is generally effective in different sequence labeling tasks. These positive results motivate further use of AT for natural language tasks.
We propose online unsupervised domain adaptation (DA), which is performed incrementally as data comes in and is applicable when batch DA is not possible. In a part-of-speech (POS) tagging evaluation, we find that online unsupervised DA performs as well as batch DA.
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；LISN（LISN实验室）
Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many low-resource languages lack labeled data for training. An established method for training a POS tagger in such a scenario is to create a labeled training set by transferring from high-resource languages. In this paper, we propose a novel method for transferring labels from multiple high-resource source to low-resource target languages. We formalize POS tag projection as graph-based label propagation. Given translations of a sentence in multiple languages, we create a graph with words as nodes and alignment lin…
We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework. The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.
Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of adapting to new domains, pre-trained units struggle with learning uncommon target-specific patterns. In this paper, we propose to augment the target-network with normalised, weighted and randomly initialised units that beget a better adaptation while maintaining the valuable source knowledge. Our experiments on POS tagging of social media texts (Tweets domai…
In natural language processing, the deep learning revolution has shifted the focus from conventional hand-crafted symbolic representations to dense inputs, which are adequate representations learned automatically from corpora. However, particularly when working with low-resource languages, small amounts of symbolic lexical resources such as user-generated lexicons are often available even when gold-standard corpora are not. Such additional linguistic information is though often neglected, and recent neural approaches to cross-lingual tagging typically rely only on word and subword embeddings. …
The performance of a Part-of-speech (POS) tagger is highly dependent on the domain ofthe processed text, and for many domains there is no or only very little training data available. This work addresses the problem of POS tagging noisy user-generated text using a neural network. We propose an architecture that trains an out-of-domain model on a large newswire corpus, and transfers those weights by using them as a prior for a model trained on the target domain (a data-set of German Tweets) for which there is very little an-notations available. The neural network has two standard bidirectional L…
Tagged corpora play a crucial role in a wide range of Natural Language Processing. The Part of Speech Tagging (POST) is essential in developing tagged corpora. It is time-and-effort-consuming and costly, and therefore, it could be more affordable if it is automated. The Kurdish language currently lacks publicly available tagged corpora of proper sizes. Tagging the publicly available Kurdish corpora can leverage the capability of those resources to a higher level than what raw or segmented corpora can provide. Developing POS-tagged lexicons can assist the mentioned task. We use a tagged corpus …
It is challenging to train and deploy Transformer LMs for hybrid speech recognition 2nd pass re-ranking in low-resource languages due to (1) data scarcity in low-resource languages, (2) expensive computing costs for training and refreshing 100+ monolingual models, and (3) hosting inefficiency considering sparse traffic. In this study, we present a new way to group multiple low-resource locales together and optimize the performance of Multilingual Transformer LMs in ASR. Our Locale-group Multilingual Transformer LMs outperform traditional multilingual LMs along with reducing maintenance costs a…
School of Interactive Computing（交互计算学院）；Georgia Institute of Technology（佐治亚理工学院）
As more historical texts are digitized, there is interest in applying natural language processing tools to these archives. However, the performance of these tools is often unsatisfactory, due to language change and genre differences. Spelling normalization heuristics are the dominant solution for dealing with historical texts, but this approach fails to account for changes in usage and vocabulary. In this empirical paper, we assess the capability of domain adaptation techniques to cope with historical texts, focusing on the classic benchmark task of part-of-speech tagging. We evaluate several …
Speech translation has recently become an increasingly popular topic of research, partly due to the development of benchmark datasets. Nevertheless, current datasets cover a limited number of languages. With the aim to foster research in massive multilingual speech translation and speech translation for low resource language pairs, we release CoVoST 2, a large-scale multilingual speech translation corpus covering translations from 21 languages into English and from English into 15 languages. This represents the largest open dataset available to date from total volume and language coverage pers…
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extra…
MINDsLab Inc.（MINDsLab公司）；Seoul National University（首尔国立大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora is unavoidable. We introduce speaker regularization loss that improves speech naturalness during cross-lingual synthesis as well as domain adversarial training, which is applied in other multilingual TTS models. Furthermore, by adding speaker regularization loss, replacing speaker embedding with zero vector in duration predictor stabilizes cross-lingual inference. With this repl…
Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) and XLMR (Conneau et al., 2020) have proven to be impressively effective at enabling transfer-learning of NLP systems from high-resource languages to low-resource languages. This success comes despite the fact that there is no explicit objective to align the contextual embeddings of words/sentences with similar meanings across languages together in the same space. In this paper, we present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bidirectional EncodeR). AMBER is trained on additional para…
Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired quality. Although multi-speaker modeling can reduce the data requirements necessary for a new voice, this approach is usually not viable for many low-resource languages for which abundant multi-speaker data is not available. In this paper, we therefore investigated to what extent multilingual multi-speaker modeling can be an alternative to monolingual multi-speake…
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We consider two ways of applying this intuition to the problem of unsupervised part-of-speech tagging: a model that directly merges tag structures for a pair of languages into a single sequence and a second model which instead incorporates multilingual context using latent variables. Both approaches are formulated as hierarchical Bayesian models, using Markov Chain Mo…
Techo Startup Center (TSC)（Techo创业中心）；Royal University of Phnom Penh (RUPP)（金边皇家大学）
Khmer text is written from left to right with optional space. Space is not served as a word boundary but instead, it is used for readability or other functional purposes. Word segmentation is a prior step for downstream tasks such as part-of-speech (POS) tagging and thus, the robustness of POS tagging highly depends on word segmentation. The conventional Khmer POS tagging is a two-stage process that begins with word segmentation and then actual tagging of each word, afterward. In this work, a joint word segmentation and POS tagging approach using a single deep learning model is proposed so tha…
RIKEN AIP（理化学研究所先进智能项目中心）；Tohoku University（东北大学）；Heidelberg Institute for Theoretical Studies gGmbH（海德堡理论研究所）
Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic evaluations makes it difficult for practitioners to choose between them. In this work, we conduct an extensive evaluation comparing non-contextual subword embeddings, namely FastText and BPEmb, and a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging. We find that overall, a combination of BERT, BPEmb…
We use a Dynamic Bayesian Network to represent compactly a variety of sublexical and contextual features relevant to Part-of-Speech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a benchmark corpus). We explore the effect of eliminating redundancy and radically reducing the size of feature vocabularies. We find that a small but linguistically motivated set of suffixes results in improved cross-corpora generalization. We also show that a minimal lexicon limited to function words is sufficient to ensure reasonable performance.
Sharif University of Technology（谢里夫理工大学）；Dathena Science Pte. Ltd.（达特纳科学私人有限公司）
Ezafe is a grammatical particle in some Iranian languages that links two words together. Regardless of the important information it conveys, it is almost always not indicated in Persian script, resulting in mistakes in reading complex sentences and errors in natural language processing tasks. In this paper, we experiment with different machine learning methods to achieve state-of-the-art results in the task of ezafe recognition. Transformer-based methods, BERT and XLMRoBERTa, achieve the best results, the latter achieving 2.68% F1-score more than the previous state-of-the-art. We, moreover, us…
University of Groningen（格罗宁根大学）；University of Copenhagen（哥本哈根大学）；Bar-Ilan University（巴伊兰大学）
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise. We address these issues and evaluate bi-LSTMs with word, character, and unicode byte embeddings for POS tagging. We compare bi-LSTMs to traditional POS taggers across languages and data sizes. We also present a novel bi-LSTM model, which combines the POS tagging loss function with an auxiliary loss function that accounts for rare words. The model obtai…
Developing an automatic part-of-speech (POS) tagging for any new language is considered a necessary step for further computational linguistics methodology beyond tagging, like chunking and parsing, to be fully applied to the language. Many POS disambiguation technologies have been developed for this type of research and there are factors that influence the choice of choosing one. This could be either corpus-based or non-corpus-based. In this paper, we present a review of POS tagging technologies.
We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.
This paper presents an algorithm for tagging words whose part-of-speech properties are unknown. Unlike previous work, the algorithm categorizes word tokens in context instead of word types. The algorithm is evaluated on the Brown Corpus.
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines w2v-BERT pre-training on speech with SpanBERT pre-training on character-level text, along with Connectionist Temporal Classification (CTC) losses on paired speech and transcript data, to learn a single model capable of learning from and representing both speech and text signals in a shared representation space. We evaluate mSLAM on several downstream speech …
Part-of-speech (POS) tagging is considered as one of the basic but necessary tools which are required for many Natural Language Processing (NLP) applications such as word sense disambiguation, information retrieval, information processing, parsing, question answering, and machine translation. Performance of the current POS taggers in Amharic is not as good as that of the contemporary POS taggers available for English and other European languages. The aim of this work is to improve POS tagging performance for the Amharic language, which was never above 91%. Usage of morphological knowledge, an …
Morphosyntactic lexicons and word vector representations have both proven useful for improving the accuracy of statistical part-of-speech taggers. Here we compare the performances of four systems on datasets covering 16 languages, two of these systems being feature-based (MEMMs and CRFs) and two of them being neural-based (bi-LSTMs). We show that, on average, all four approaches perform similarly and reach state-of-the-art results. Yet better performances are obtained with our feature-based models on lexically richer datasets (e.g. for morphologically rich languages), whereas neural-based resu…
Improved POS tagging for spontaneous, clinical speech using data augmentation
Linguistic Data Consortium, University of Pennsylvania（宾夕法尼亚大学语言数据联盟）；Penn Frontotemporal Degeneration Center, University of Pennsylvania（宾夕法尼亚大学宾夕法尼亚额颞叶变性中心）
Shanghai Jiao Tong University（上海交通大学）；Microsoft Research Asian（微软亚洲研究院）；Educational Testing Service Research（美国教育考试服务中心研究院）
Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.g. speech utterances or handwritten documents. While word embedding has been demoed as a powerful representation for characterizing the statistical properties of natural language. In this study, we propose to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task. When tested on Penn Treebank WSJ test set, a state-of-the-art performance of 97.40 tagging accuracy is achieved. Without using morphological features, this approach can also ach…
Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not available. We investigate the effect of automatic normalization on POS tagging of tweets. We also compare normalization to strategies that leverage large amounts of unlabeled data kept in its raw form. Our results show that normalization helps, but does not add consistently beyond just word embedding layer initialization. The latter approach yields a tagging mod…
Kata Research Team Kata.ai（卡塔人工智能公司卡塔研究团队）；School of Informatics University of Edinburgh（爱丁堡大学信息学院）
Previous work in Indonesian part-of-speech (POS) tagging are hard to compare as they are not evaluated on a common dataset. Furthermore, in spite of the success of neural network models for English POS tagging, they are rarely explored for Indonesian. In this paper, we explored various techniques for Indonesian POS tagging, including rule-based, CRF, and neural network-based models. We evaluated our models on the IDN Tagged Corpus. A new state-of-the-art of 97.47 F1 score is achieved with a recurrent neural network. To provide a standard for future work, we release the dataset split that we us…
Cummins College of Engineering for Women（卡明斯女子工程学院）；Banasthali University（班纳斯塔利大学）
Machine Translation for Indian languages is an emerging research area. Transliteration is one such module that we design while designing a translation system. Transliteration means mapping of source language text into the target language. Simple mapping decreases the efficiency of overall translation system. We propose the use of stemming and part-of-speech tagging for transliteration. The effectiveness of translation can be improved if we use part-of-speech tagging and stemming assisted transliteration.We have shown that much of the content in Gujarati gets transliterated while being processe…
Multimedia Communications Laboratory, University of Information Technology（信息技术大学多媒体通信实验室）；University of Information Technology（信息技术大学）；Vietnam National University（越南国立大学）
Chinese word segmentation and part-of-speech tagging are necessary tasks in terms of computational linguistics and application of natural language processing. Many re-searchers still debate the demand for Chinese word segmentation and part-of-speech tagging in the deep learning era. Nevertheless, resolving ambiguities and detecting unknown words are challenging problems in this field. Previous studies on joint Chinese word segmentation and part-of-speech tagging mainly follow the character-based tagging model focusing on modeling n-gram features. Unlike previous works, we propose a neural mode…
The shift of public debate to the digital sphere has been accompanied by a rise in online hate speech. While many promising approaches for hate speech classification have been proposed, studies often focus only on a single language, usually English, and do not address three key concerns: post-deployment performance, classifier maintenance and infrastructural limitations. In this paper, we introduce a new human-in-the-loop BERT-based hate speech classification pipeline and trace its development from initial data collection and annotation all the way to post-deployment. Our classifier, trained u…
Text corpora which are tagged with part-of-speech information are useful in many areas of linguistic research. In this paper, a new part-of-speech tagging method based on neural networks (Net- Tagger) is presented and its performance is compared to that of a HMM-tagger and a trigram-based tagger. It is shown that the Net- Tagger performs as well as the trigram-based tagger and better than the HMM-tagger.
This paper outlines the results of sentence level linguistics based rules for improving part-of-speech tagging. It is well known that the performance of complex NLP systems is negatively affected if one of the preliminary stages is less than perfect. Errors in the initial stages in the pipeline have a snowballing effect on the pipeline's end performance. We have created a set of linguistics based rules at the sentence level which adjust part-of-speech tags from state-of-the-art taggers. Comparison with state-of-the-art taggers on widely used benchmarks demonstrate significant improvements in t…
Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation and part of speech tagging rather than solely process word by word from left to right. In this paper, we implement this idea to improve word segmentation and part of speech tagging the Vietnamese language by employing a simplified constituency parser. Our neural model for joint word segmentation and part-of-speech tagging has the architecture of the syllable-…
This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part of speech tagging. Linguistic and statistical information is represented in terms of weights on transitions in weighted finite-state transducers. Another contribution is the successful combination of techniques -- linguistic and statistical -- for word disambiguation, compounded with the notion of word classes.
This paper describes our submission to CoNLL 2018 UD Shared Task. We have extended an LSTM-based neural network designed for sequence tagging to additionally generate character-level sequences. The network was jointly trained to produce lemmas, part-of-speech tags and morphological features. Sentence segmentation, tokenization and dependency parsing were handled by UDPipe 1.2 baseline. The results demonstrate the viability of the proposed multitask architecture, although its performance still remains far from state-of-the-art.
The Yunshan Cup 2020 track focused on creating a framework for evaluating different methods of part-of-speech (POS). There were two tasks for this track: (1) POS tagging for the Indonesian language, and (2) POS tagging for the Lao tagging. The Indonesian dataset is comprised of 10000 sentences from Indonesian news within 29 tags. And the Lao dataset consists of 8000 sentences within 27 tags. 25 teams registered for the task. The methods of participants ranged from feature-based to neural networks using either classical machine learning techniques or ensemble methods. The best performing result…
While the use of cluster features became ubiquitous in core NLP tasks, most cluster features in NLP are based on distributional similarity. We propose a new type of clustering criteria, specific to the task of part-of-speech tagging. Instead of distributional similarity, these clusters are based on the beha vior of a baseline tagger when applied to a large corpus. These cluster features provide similar gains in accuracy to those achieved by distributional-similarity derived clusters. Using both types of cluster features together further improve tagging accuracies. We show that the method is ef…
It has been argued that, when learning a first language, babies use a series of small clues to aid recognition and comprehension, and that one of these clues is word length. In this paper we present a statistical part of speech tagger which trains itself solely on the number of letters in each word in a sentence.
This squib claims that Large-scale Automatic Sense Tagging of text (LAST) can be done at a high-level of accuracy and with far less complexity and computational effort than has been believed until now. Moreover, it can be done for all open class words, and not just carefully selected opposed pairs as in some recent work. We describe two experiments: one exploring the amount of information relevant to sense disambiguation which is contained in the part-of-speech field of entries in Longman Dictionary of Contemporary English (LDOCE). Another, more practical, experiment attempts sense disambiguat…
Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different formats one could use for casting input text sentences and their output labels into the input and target…
The elastic-input neuro tagger and hybrid tagger, combined with a neural network and Brill's error-driven learning, have already been proposed for the purpose of constructing a practical tagger using as little training data as possible. When a small Thai corpus is used for training, these taggers have tagging accuracies of 94.4% and 95.5% (accounting only for the ambiguous words in terms of the part of speech), respectively. In this study, in order to construct more accurate taggers we developed new tagging methods using three machine learning methods: the decision-list, maximum entropy, and s…
University of Sfax（斯法克斯大学）；University of Gabes（加贝斯大学）
With the growing number of textual resources available, the ability to understand them becomes critical. An essential first step in understanding these sources is the ability to identify the part of speech in each sentence. Arabic is a morphologically rich language, wich presents a challenge for part of speech tagging. In this paper, our goal is to propose, improve and implement a part of speech tagger based on a genetic alorithm. The accuracy obtained with this method is comparable to that of other probabilistic approaches.
A technique for detecting errors made by Hidden Markov Model taggers is described, based on comparing observable values of the tagging process with a threshold. The resulting approach allows the accuracy of the tagger to be improved by accepting a lower efficiency, defined as the proportion of words which are tagged. Empirical observations are presented which demonstrate the validity of the technique and suggest how to choose an appropriate threshold.
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Ancient Chinese word segmentation (WSG) and part-of-speech tagging (POS) are important to study ancient Chinese, but the amount of ancient Chinese WSG and POS tagging data is still rare. In this paper, we propose a novel augmentation method of ancient Chinese WSG and POS tagging data using distant supervision over parallel corpus. However, there are still mislabeled and unlabeled ancient Chinese words inevitably in distant supervision. To address this problem, we take advantage of the memorization effects of deep neural networks and a small amount of annotated data to get a model with much kno…
Rewire；University of Oxford（牛津大学）；Bocconi University（博科尼大学）；Simon Fraser University（西蒙弗雷泽大学）
Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance because of increasingly well-documented systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, recent research has thus introduced functional tests for hate speech detection models. However, these tests currently only exist for English-language content, which means that they cannot support the development of more effective models in other languages spoken by billions across the wo…
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the complicated feature compositions as the traditional methods with discrete features. In this work, we propose a feature-enriched neural model for joint Chinese word segmentation and part-of-speech tagging task. Specifically, to simulate the feature templates of traditional discrete feature based models, we use different filters to model the complex compositional fe…
Swarm Intelligence algorithms have gained significant attention in recent years as a means of solving complex and non-deterministic problems. These algorithms are inspired by the collective behavior of natural creatures, and they simulate this behavior to develop intelligent agents for computational tasks. One such algorithm is Ant Colony Optimization (ACO), which is inspired by the foraging behavior of ants and their pheromone laying mechanism. ACO is used for solving difficult problems that are discrete and combinatorial in nature. Part-of-Speech (POS) tagging is a fundamental task in natura…
Institute of Computer Science, University of Tartu（塔尔图大学计算机科学研究所）
Recently, large pre-trained language models, such as BERT, have reached state-of-the-art performance in many natural language processing tasks, but for many languages, including Estonian, BERT models are not yet available. However, there exist several multilingual BERT models that can handle multiple languages simultaneously and that have been trained also on Estonian data. In this paper, we evaluate four multilingual models -- multilingual BERT, multilingual distilled BERT, XLM and XLM-RoBERTa -- on several NLP tasks including POS and morphological tagging, NER and text classification. Our ai…
The Hong Kong University of Science and Technology（香港科技大学）；Department of Computer Science and Engineering（计算机科学与工程系）
Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks. In this paper, we present a new multilingual multi-aspect hate speech analysis dataset and use it to test the current state-of-the-art multilingual multitask learning approaches. We evaluate our dataset in various classification settings, then we discuss how to leverage our annotations in order to improve hate speech detection and classification in general.
