首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 31 毫秒
1.
We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language detection. This way we can use existing data from higher-resource languages to build better detection systems for low-resource languages. Our datasets are from seven different languages from three language families. We measure the distance between the languages using several language similarity measures, especially by quantifying the World Atlas of Language Structures. We show that there is a correlation between linguistic similarity and classifier performance. This discovery allows us to choose an optimal transfer language for zero shot abusive language detection.  相似文献   

2.
Hate speech is an increasingly important societal issue in the era of digital communication. Hateful expressions often make use of figurative language and, although they represent, in some sense, the dark side of language, they are also often prime examples of creative use of language. While hate speech is a global phenomenon, current studies on automatic hate speech detection are typically framed in a monolingual setting. In this work, we explore hate speech detection in low-resource languages by transferring knowledge from a resource-rich language, English, in a zero-shot learning fashion. We experiment with traditional and recent neural architectures, and propose two joint-learning models, using different multilingual language representations to transfer knowledge between pairs of languages. We also evaluate the impact of additional knowledge in our experiment, by incorporating information from a multilingual lexicon of abusive words. The results show that our joint-learning models achieve the best performance on most languages. However, a simple approach that uses machine translation and a pre-trained English language model achieves a robust performance. In contrast, Multilingual BERT fails to obtain a good performance in cross-lingual hate speech detection. We also experimentally found that the external knowledge from a multilingual abusive lexicon is able to improve the models’ performance, specifically in detecting the positive class. The results of our experimental evaluation highlight a number of challenges and issues in this particular task. One of the main challenges is related to the issue of current benchmarks for hate speech detection, in particular how bias related to the topical focus in the datasets influences the classification performance. The insufficient ability of current multilingual language models to transfer knowledge between languages in the specific hate speech detection task also remain an open problem. However, our experimental evaluation and our qualitative analysis show how the explicit integration of linguistic knowledge from a structured abusive language lexicon helps to alleviate this issue.  相似文献   

3.
Cross-genre author profiling aims to build generalized models for predicting profile traits of authors that can be helpful across different text genres for computer forensics, marketing, and other applications. The cross-genre author profiling task becomes challenging when dealing with low-resourced languages due to the lack of availability of standard corpora and methods. The task becomes even more challenging when the data is code-switched, which is informal and unstructured. In previous studies, the problem of cross-genre author profiling has been mainly explored for mono-lingual texts in highly resourced languages (English, Spanish, etc.). However, it has not been thoroughly explored for the code-switched text which is widely used for communication over social media. To fulfill this gap, we propose a transfer learning-based solution for the cross-genre author profiling task on code-switched (English–RomanUrdu) text using three widely known genres, Facebook comments/posts, Tweets, and SMS messages. In this article, firstly, we experimented with the traditional machine learning, deep learning and pre-trained transfer learning models (MBERT, XLMRoBERTa, ULMFiT, and XLNET) for the same-genre and cross-genre gender identification task. We then propose a novel Trans-Switch approach that focuses on the code-switching nature of the text and trains on specialized language models. In addition, we developed three RomanUrdu to English translated corpora to study the impact of translation on author profiling tasks. The results show that the proposed Trans-Switch model outperforms the baseline deep learning and pre-trained transfer learning models for cross-genre author profiling task on code-switched text. Further, the experimentation also shows that the translation of RomanUrdu text does not improve results.  相似文献   

4.
Recently, sentiment classification has received considerable attention within the natural language processing research community. However, since most recent works regarding sentiment classification have been done in the English language, there are accordingly not enough sentiment resources in other languages. Manual construction of reliable sentiment resources is a very difficult and time-consuming task. Cross-lingual sentiment classification aims to utilize annotated sentiment resources in one language (typically English) for sentiment classification of text documents in another language. Most existing research works rely on automatic machine translation services to directly project information from one language to another. However, different term distribution between original and translated text documents and translation errors are two main problems faced in the case of using only machine translation. To overcome these problems, we propose a novel learning model based on active learning and semi-supervised co-training to incorporate unlabelled data from the target language into the learning process in a bi-view framework. This model attempts to enrich training data by adding the most confident automatically-labelled examples, as well as a few of the most informative manually-labelled examples from unlabelled data in an iterative process. Further, in this model, we consider the density of unlabelled data so as to select more representative unlabelled examples in order to avoid outlier selection in active learning. The proposed model was applied to book review datasets in three different languages. Experiments showed that our model can effectively improve the cross-lingual sentiment classification performance and reduce labelling efforts in comparison with some baseline methods.  相似文献   

5.
Recently, using a pretrained word embedding to represent words achieves success in many natural language processing tasks. According to objective functions, different word embedding models capture different aspects of linguistic properties. However, the Semantic Textual Similarity task, which evaluates similarity/relation between two sentences, requires to take into account of these linguistic aspects. Therefore, this research aims to encode various characteristics from multiple sets of word embeddings into one embedding and then learn similarity/relation between sentences via this novel embedding. Representing each word by multiple word embeddings, the proposed MaxLSTM-CNN encoder generates a novel sentence embedding. We then learn the similarity/relation between our sentence embeddings via Multi-level comparison. Our method M-MaxLSTM-CNN consistently shows strong performances in several tasks (i.e., measure textual similarity, identify paraphrase, recognize textual entailment). Our model does not use hand-crafted features (e.g., alignment features, Ngram overlaps, dependency features) as well as does not require pre-trained word embeddings to have the same dimension.  相似文献   

6.
Due to natural language morphology, words can take on various morphological forms. Morphological normalisation – often used in information retrieval and text mining systems – conflates morphological variants of a word to a single representative form. In this paper, we describe an approach to lexicon-based inflectional normalisation. This approach is in between stemming and lemmatisation, and is suitable for morphological normalisation of inflectionally complex languages. To eliminate the immense effort required to compile the lexicon by hand, we focus on the problem of acquiring automatically an inflectional morphological lexicon from raw corpora. We propose a convenient and highly expressive morphology representation formalism on which the acquisition procedure is based. Our approach is applied to the morphologically complex Croatian language, but it should be equally applicable to other languages of similar morphological complexity. Experimental results show that our approach can be used to acquire a lexicon whose linguistic quality allows for rather good normalisation performance.  相似文献   

7.
Probabilistic topic models are unsupervised generative models which model document content as a two-step generation process, that is, documents are observed as mixtures of latent concepts or topics, while topics are probability distributions over vocabulary words. Recently, a significant research effort has been invested into transferring the probabilistic topic modeling concept from monolingual to multilingual settings. Novel topic models have been designed to work with parallel and comparable texts. We define multilingual probabilistic topic modeling (MuPTM) and present the first full overview of the current research, methodology, advantages and limitations in MuPTM. As a representative example, we choose a natural extension of the omnipresent LDA model to multilingual settings called bilingual LDA (BiLDA). We provide a thorough overview of this representative multilingual model from its high-level modeling assumptions down to its mathematical foundations. We demonstrate how to use the data representation by means of output sets of (i) per-topic word distributions and (ii) per-document topic distributions coming from a multilingual probabilistic topic model in various real-life cross-lingual tasks involving different languages, without any external language pair dependent translation resource: (1) cross-lingual event-centered news clustering, (2) cross-lingual document classification, (3) cross-lingual semantic similarity, and (4) cross-lingual information retrieval. We also briefly review several other applications present in the relevant literature, and introduce and illustrate two related modeling concepts: topic smoothing and topic pruning. In summary, this article encompasses the current research in multilingual probabilistic topic modeling. By presenting a series of potential applications, we reveal the importance of the language-independent and language pair independent data representations by means of MuPTM. We provide clear directions for future research in the field by providing a systematic overview of how to link and transfer aspect knowledge across corpora written in different languages via the shared space of latent cross-lingual topics, that is, how to effectively employ learned per-topic word distributions and per-document topic distributions of any multilingual probabilistic topic model in various cross-lingual applications.  相似文献   

8.
Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model’s ability to persist over time can help design models that can be effectively used over a longer period of time. In this paper, we provide a thorough discussion into the problem, establish an evaluation setup for the task. We look at this problem from a practical perspective by assessing the ability of a wide range of language models and classification algorithms to persist over time, as well as how dataset characteristics can help predict the temporal stability of different models. We perform longitudinal classification experiments on three datasets spanning between 6 and 19 years, and involving diverse tasks and types of data. By splitting the longitudinal datasets into years, we perform a comprehensive set of experiments by training and testing across data that are different numbers of years apart from each other, both in the past and in the future. This enables a gradual investigation into the impact of the temporal gap between training and test sets on the classification performance, as well as measuring the extent of the persistence over time. Through experimenting with a range of language models and algorithms, we observe a consistent trend of performance drop over time, which however differs significantly across datasets; indeed, datasets whose domain is more closed and language is more stable, such as with book reviews, exhibit a less pronounced performance drop than open-domain social media datasets where language varies significantly more. We find that one can estimate how a model will retain its performance over time based on (i) how well the model performs over a restricted time period and its extrapolation to a longer time period, and (ii) the linguistic characteristics of the dataset, such as the familiarity score between subsets from different years. Findings from these experiments have important implications for the design of text classification models with the aim of preserving performance over time.  相似文献   

9.
We present two approaches to email thread summarization: collective message summarization (CMS) applies a multi-document summarization approach, while individual message summarization (IMS) treats the problem as a sequence of single-document summarization tasks. Both approaches are implemented in our general framework driven by sentence compression. Instead of a purely extractive approach, we employ linguistic and statistical methods to generate multiple compressions, and then select from those candidates to produce a final summary. We demonstrate these ideas on the Enron email collection – a very challenging corpus because of the highly technical language. Experimental results point to two findings: that CMS represents a better approach to email thread summarization, and that current sentence compression techniques do not improve summarization performance in this genre.  相似文献   

10.
Preprocessing is one of the key components in a typical text classification framework. This paper aims to extensively examine the impact of preprocessing on text classification in terms of various aspects such as classification accuracy, text domain, text language, and dimension reduction. For this purpose, all possible combinations of widely used preprocessing tasks are comparatively evaluated on two different domains, namely e-mail and news, and in two different languages, namely Turkish and English. In this way, contribution of the preprocessing tasks to classification success at various feature dimensions, possible interactions among these tasks, and also dependency of these tasks to the respective languages and domains are comprehensively assessed. Experimental analysis on benchmark datasets reveals that choosing appropriate combinations of preprocessing tasks, rather than enabling or disabling them all, may provide significant improvement on classification accuracy depending on the domain and language studied on.  相似文献   

11.
In opposition to the mother tongue hypothesis, the father tongue hypothesis states that humans tend to speak their fathers’ language, based on a stronger correlation of languages to paternal lineages (Y-chromosome) than to maternal lineages (mitochondria). To reassess these two competing hypotheses, we conducted a genetic–linguistic study of 34 modern Indo-European (IE) populations. In this study, genetic histories of paternal and maternal migrations in these IE populations were elucidated using phylogenetic networks of Y-chromosomal and mitochondrial DNA haplogroups, respectively. Unlike previous studies, we quantitatively characterized the languages based on lexical and phonemic systems separately. We showed that genetic and linguistic distances are significantly correlated with each other and that both are correlated with geographical distances among these populations. However, when controlling for geographical factors, only the correlation between the distances of paternal and lexical characteristics, and between those of maternal and phonemic characteristics, remained. These unbalanced correlations reconciled the two seemingly conflicting hypotheses.  相似文献   

12.
The wide spread of false information has detrimental effects on society, and false information detection has received wide attention. When new domains appear, the relevant labeled data is scarce, which brings severe challenges to the detection. Previous work mainly leverages additional data or domain adaptation technology to assist detection. The former would lead to a severe data burden; the latter underutilizes the pre-trained language model because there is a gap between the downstream task and the pre-training task, which is also inefficient for model storage because it needs to store a set of parameters for each domain. To this end, we propose a meta-prompt based learning (MAP) framework for low-resource false information detection. We excavate the potential of pre-trained language models by transforming the detection tasks into pre-training tasks by constructing template. To solve the problem of the randomly initialized template hindering excavation performance, we learn optimal initialized parameters by borrowing the benefit of meta learning in fast parameter training. The combination of meta learning and prompt learning for the detection is non-trivial: Constructing meta tasks to get initialized parameters suitable for different domains and setting up the prompt model’s verbalizer for classification in the noisy low-resource scenario are challenging. For the former, we propose a multi-domain meta task construction method to learn domain-invariant meta knowledge. For the latter, we propose a prototype verbalizer to summarize category information and design a noise-resistant prototyping strategy to reduce the influence of noise data. Extensive experiments on real-world data demonstrate the superiority of the MAP in new domains of false information detection.  相似文献   

13.
In order to successfully apply opinion mining (OM) to the large amounts of user-generated content produced every day, we need robust models that can handle the noisy input well yet can easily be adapted to a new domain or language. We here focus on opinion mining for YouTube by (i) modeling classifiers that predict the type of a comment and its polarity, while distinguishing whether the polarity is directed towards the product or video; (ii) proposing a robust shallow syntactic structure (STRUCT) that adapts well when tested across domains; and (iii) evaluating the effectiveness on the proposed structure on two languages, English and Italian. We rely on tree kernels to automatically extract and learn features with better generalization power than traditionally used bag-of-word models. Our extensive empirical evaluation shows that (i) STRUCT outperforms the bag-of-words model both within the same domain (up to 2.6% and 3% of absolute improvement for Italian and English, respectively); (ii) it is particularly useful when tested across domains (up to more than 4% absolute improvement for both languages), especially when little training data is available (up to 10% absolute improvement) and (iii) the proposed structure is also effective in a lower-resource language scenario, where only less accurate linguistic processing tools are available.  相似文献   

14.
A main challenge in Cross-Language Information Retrieval (CLIR) is to estimate a proper translation model from available translation resources, since translation quality directly affects the retrieval performance. Among different translation resources, we focus on obtaining translation models from comparable corpora, because they provide appropriate translations for both languages and domains with limited linguistic resources. In this paper, we employ a two-step approach to build an effective translation model from comparable corpora, without requiring any additional linguistic resources, for the CLIR task. In the first step, translations are extracted by deriving correlations between source–target word pairs. These correlations are used to estimate word translation probabilities in the second step. We propose a language modeling approach for the first step, where modeling based on probability distribution provides two key advantages. First, our approach can be tuned easier in comparison with heuristically adjusted previous work. Second, it provides a principled basis for integrating additional lexical and translational relations to improve the accuracy of translations from comparable corpora. As an indication, we integrate monolingual relations of word co-occurrences into the process of translation extraction, which helps to extract more reliable translations for low-frequency words in a comparable corpus. Experimental results on an English–Persian comparable corpus show that our method outperforms the previous approaches in terms of both translation quality and the performance of CLIR. Indeed, the proposed method is naturally applicable to any comparable corpus, regardless of its languages. In addition, we demonstrate the significant impact of word translation probabilities, estimated in the second step of our approach, on the performance of CLIR.  相似文献   

15.
In this paper, we propose a novel approach for multilingual story link detection. Our approach utilized the distributional features of terms in timelines and multilingual spaces, together with selected types of named entities in order to get distinctive weights for terms that constitute linguistic representation of events. On timelines term significance is calculated by comparing term distribution of the documents on a day with that of the total document collection. Since two languages can provide more information than one language, term significance is measured on each language space, which is then used as a bridge between two languages on multilingual spaces. Evaluating the method on Korean and Japanese news articles, our method achieved 14.3% improvement for monolingual story pairs, and 16.7% improvement for multilingual story pairs. By measuring the space density, the proposed weighting components are verified with a high density of the intra-event stories and a low density of the inter-events stories. This result indicates that the proposed method is helpful for multilingual story link detection.  相似文献   

16.
Knowledge acquisition and bilingual terminology extraction from multilingual corpora are challenging tasks for cross-language information retrieval. In this study, we propose a novel method for mining high quality translation knowledge from our constructed Persian–English comparable corpus, University of Tehran Persian–English Comparable Corpus (UTPECC). We extract translation knowledge based on Term Association Network (TAN) constructed from term co-occurrences in same language as well as term associations in different languages. We further propose a post-processing step to do term translation validity check by detecting the mistranslated terms as outliers. Evaluation results on two different data sets show that translating queries using UTPECC and using the proposed methods significantly outperform simple dictionary-based methods. Moreover, the experimental results show that our methods are especially effective in translating Out-Of-Vocabulary terms and also expanding query words based on their associated terms.  相似文献   

17.
[目的/意义] 从跨语言视角探究如何更好地解决低资源语言的实体抽取问题。[方法/过程] 以英语为源语言,西班牙语和荷兰语为目标语言,借助迁移学习和深度学习的思想,提出一种结合自学习和GRU-LSTM-CRF网络的无监督跨语言实体抽取方法。[结果/结论] 与有监督的跨语言实体抽取方法相比,本文提出的无监督跨语言实体抽取方法可以取得更好的效果,在西班牙语上,F1值为0.6419,在荷兰语上,F1值为0.6557。利用跨语言知识在源语言和目标语言间建立桥梁,提升低资源语言实体抽取的效果。  相似文献   

18.
This study proposes the codification of lexical information in electronic dictionaries, in accordance with a generic and extendable XML scheme model, and its conjunction with linguistic tools for the processing of natural language. Our approach is different from other similar studies in that we propose XML coding of those items from a dictionary of meanings that are less related to the lexical units. Linguistic information, such as morphology, syllables, phonology, etc., will be included by means of specific linguistic tools. The use of XML as a container for the information allows the use of other XML tools for carrying out searches or for enabling presentation of the information in different resources. This model is particularly important as it combines two parallel paradigms—extendable labelling of documents and computational linguistics—and it is also applicable to other languages. We have included a comparison with the labelling proposal of printed dictionaries carried out by the Text Encoding Initiative (TEI). The proposed design has been validated with a dictionary of more than 145 000 accepted meanings.  相似文献   

19.
Named entity recognition aims to detect pre-determined entity types in unstructured text. There is a limited number of studies on this task for low-resource languages such as Turkish. We provide a comprehensive study for Turkish named entity recognition by comparing the performances of existing state-of-the-art models on the datasets with varying domains to understand their generalization capability and further analyze why such models fail or succeed in this task. Our experimental results, supported by statistical tests, show that the highest weighted F1 scores are obtained by Transformer-based language models, varying from 80.8% in tweets to 96.1% in news articles. We find that Transformer-based language models are more robust to entity types with a small sample size and longer named entities compared to traditional models, yet all models have poor performance for longer named entities in social media. Moreover, when we shuffle 80% of words in a sentence to imitate flexible word order in Turkish, we observe more performance deterioration, 12% in well-written texts, compared to 7% in noisy text.  相似文献   

20.
Opinion mining is one of the most important research tasks in the information retrieval research community. With the huge volume of opinionated data available on the Web, approaches must be developed to differentiate opinion from fact. In this paper, we present a lexicon-based approach for opinion retrieval. Generally, opinion retrieval consists of two stages: relevance to the query and opinion detection. In our work, we focus on the second state which itself focusses on detecting opinionated documents . We compare the document to be analyzed with opinionated sources that contain subjective information. We hypothesize that a document with a strong similarity to opinionated sources is more likely to be opinionated itself. Typical lexicon-based approaches treat and choose their opinion sources according to their test collection, then calculate the opinion score based on the frequency of subjective terms in the document. In our work, we use different open opinion collections without any specific treatment and consider them as a reference collection. We then use language models to determine opinion scores. The analysis document and reference collection are represented by different language models (i.e., Dirichlet, Jelinek-Mercer and two-stage models). These language models are generally used in information retrieval to represent the relationship between documents and queries. However, in our study, we modify these language models to represent opinionated documents. We carry out several experiments using Text REtrieval Conference (TREC) Blogs 06 as our analysis collection and Internet Movie Data Bases (IMDB), Multi-Perspective Question Answering (MPQA) and CHESLY as our reference collection. To improve opinion detection, we study the impact of using different language models to represent the document and reference collection alongside different combinations of opinion and retrieval scores. We then use this data to deduce the best opinion detection models. Using the best models, our approach improves on the best baseline of TREC Blog (baseline4) by 30%.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号