This article presents the most up-to-date, influential automated, semiautomated and human metrics used to evaluate the quality of machine translation (MT) output and provides the necessary background for MT evaluation projects. Evaluation is, as repeatedly admitted, highly relevant for the improvement of MT. This article is divided into three parts: the first one is dedicated to automated metrics; the second, to human metrics; and the last, to the challenges posed by neural machine translation (NMT) regarding its evaluation. The first part includes reference translation–based metrics; confidence or quality estimation (QE) metrics, which are used as alternatives for quality assessment; and diagnostic evaluation based on linguistic checkpoints. Human evaluation metrics are classified according to the criterion of whether human judges directly express a so-called subjective evaluation judgment, such as ‘good’ or ‘better than’, or not, as is the case in error classification. The former methods are based on directly expressed judgment (DEJ); therefore, they are called ‘DEJ-based evaluation methods’, while the latter are called ‘non-DEJ-based evaluation methods’. In the DEJ-based evaluation section, tasks such as fluency and adequacy annotation, ranking and direct assessment (DA) are presented, whereas in the non-DEJ-based evaluation section, tasks such as error classification and postediting are detailed, with definitions and guidelines, thus rendering this article a useful guide for evaluation projects. Following the detailed presentation of the previously mentioned metrics, the specificities of NMT are set forth along with suggestions for its evaluation, according to the latest studies. As human translators are the most adequate judges of the quality of a translation, emphasis is placed on the human metrics seen from a translator-judge perspective to provide useful methodology tools for interdisciplinary research groups that evaluate MT systems.

Twitter and other social media platforms are often used for sharing interest in products. The identification of purchase decision stages, such as in the AIDA model (Awareness, Interest, Desire, and Action), can enable more personalized e-commerce services and a finer-grained targeting of advertisements than predicting purchase intent only. In this paper, we propose and analyze neural models for identifying the purchase stage of single tweets in a user’s tweet sequence. In particular, we identify three challenges of purchase stage identification: imbalanced label distribution with a high number of non-purchase-stage instances, limited amount of training data, and domain adaptation with no or only little target domain data. Our experiments reveal that the imbalanced label distribution is the main challenge for our models. We address it with ranking loss and perform detailed investigations of the performance of our models on the different output classes. In order to improve the generalization of the models and augment the limited amount of training data, we examine the use of sentiment analysis as a complementary, secondary task in a multitask framework. For applying our models to tweets from another product domain, we consider two scenarios: for the first scenario without any labeled data in the target product domain, we show that learning domain-invariant representations with adversarial training is most promising, while for the second scenario with a small number of labeled target examples, fine-tuning the source model weights performs best. Finally, we conduct several analyses, including extracting attention weights and representative phrases for the different purchase stages. The results suggest that the model is learning features indicative of purchase stages and that the confusion errors are sensible.

Due to the considerable growth of the volume of text documents on the Internet and in digital libraries, manual analysis of these documents is no longer feasible. Having efficient approaches to keyword extraction in order to retrieve the ‘key’ elements of the studied documents is now a necessity. Keyword extraction has been an active research field for many years, covering various applications in Text Mining, Information Retrieval, and Natural Language Processing, and meeting different requirements. However, it is not a unified domain of research. In spite of the existence of many approaches in the field, there is no single approach that effectively extracts keywords from different data sources. This shows the importance of having a comprehensive review, which discusses the complexity of the task and categorizes the main approaches of the field based on the features and methods of extraction that they use. This paper presents a general introduction to the field of keyword/keyphrase extraction. Unlike the existing surveys, different aspects of the problem along with the main challenges in the field are discussed. This mainly includes the unclear definition of ‘keyness’, complexities of targeting proper features for capturing desired keyness properties and selecting efficient extraction methods, and also the evaluation issues. By classifying a broad range of state-of-the-art approaches and analysing the benefits and drawbacks of different features and methods, we provide a clearer picture of them. This review is intended to help readers find their way around all the works related to keyword extraction and guide them in choosing or designing a method that is appropriate for the application they are targeting.

This paper describes experiments in which I tried to distinguish between Flemish and Netherlandic Dutch subtitles, as originally proposed in the VarDial 2018 Dutch–Flemish Subtitle task. However, rather than using all data as a monolithic block, I divided them into two non-overlapping domains and then investigated how the relation between training and test domains influences the recognition quality. I show that the best estimate of the level of recognizability of the language varieties is derived when training on one domain and testing on another. Apart from the quantitative results, I also present a qualitative analysis, by investigating in detail the most distinguishing features in the various scenarios. Here too, it is with the out-of-domain recognition that some genuine differences between Flemish and Netherlandic Dutch can be found.

Humans proficiently interpret the true sense of an ambiguous word by establishing association among words in a sentence. The complete sense of text is also based on implicit information, which is not explicitly mentioned. The absence of this implicit information is a significant problem for a computer program that attempts to determine the correct sense of ambiguous words. In this paper, we propose a novel method to uncover the implicit information that links the words of a sentence. We reveal this implicit information using a graph, which is then used to disambiguate the ambiguous word. The experiments show that the proposed algorithm interprets the correct sense for both homonyms and polysemous words. Our proposed algorithm has performed better than the approaches presented in the SemEval-2013 task for word sense disambiguation and has shown an accuracy of 79.6 percent, which is 2.5 percent better than the best unsupervised approach in SemEval-2007.

There has been a lot of recent interest in the natural language processing (NLP) community in the computational processing of language varieties and dialects, with the aim to improve the performance of applications such as machine translation, speech recognition, and dialogue systems. Here, we attempt to survey this growing field of research, with focus on computational methods for processing similar languages, varieties, and dialects. In particular, we discuss the most important challenges when dealing with diatopic language variation, and we present some of the available datasets, the process of data collection, and the most common data collection strategies used to compile datasets for similar languages, varieties, and dialects. We further present a number of studies on computational methods developed and/or adapted for preprocessing, normalization, part-of-speech tagging, and parsing similar languages, language varieties, and dialects. Finally, we discuss relevant applications such as language and dialect identification and machine translation for closely related languages, language varieties, and dialects.

Some languages have very few NLP resources, while many of them are closely related to better-resourced languages. This paper explores how the similarity between the languages can be utilised by porting resources from better- to lesser-resourced languages. The paper introduces a way of building a representation shared across related languages by combining cross-lingual embedding methods with a lexical similarity measure which is based on the weighted Levenshtein distance. One of the outcomes of the experiments is a Panslavonic embedding space for nine Balto-Slavonic languages. The paper demonstrates that the resulting embedding space helps in such applications as morphological prediction, named-entity recognition and genre classification.

In this paper, we address query-based summarization of discussion threads. New users can profit from the information shared in the forum, Please check if the inserted city and country names in the affiliations are correct. if they can find back the previously posted information. However, discussion threads on a single topic can easily comprise dozens or hundreds of individual posts. Our aim is to summarize forum threads given real web search queries. We created a data set with search queries from a discussion forum’s search engine log and the discussion threads that were clicked by the user who entered the query. For 120 thread–query combinations, a reference summary was made by five different human raters. We compared two methods for automatic summarization of the threads: a query-independent method based on post features, and Maximum Marginal Relevance (MMR), a method that takes the query into account. We also compared four different word embeddings representations as alternative for standard word vectors in extractive summarization. We find (1) that the agreement between human summarizers does not improve when a query is provided that: (2) the query-independent post features as well as a centroid-based baseline outperform MMR by a large margin; (3) combining the post features with query similarity gives a small improvement over the use of post features alone; and (4) for the word embeddings, a match in domain appears to be more important than corpus size and dimensionality. However, the differences between the models were not reflected by differences in quality of the summaries created with help of these models. We conclude that query-based summarization with web queries is challenging because the queries are short, and a click on a result is not a direct indicator for the relevance of the result.

Talking about odors and flavors is difficult for most people, yet experts appear to be able to convey critical information about wines in their reviews. This seems to be a contradiction, and wine expert descriptions are frequently received with criticism. Here, we propose a method for probing the language of wine reviews, and thus offer a means to enhance current vocabularies, and as a by-product question the general assumption that wine reviews are gibberish. By means of two different quantitative analyses—support vector machines for classification and Termhood analysis—on a corpus of online wine reviews, we tested whether wine reviews are written in a consistent manner, and thus may be considered informative; and whether reviews feature domain-specific language. First, a classification paradigm was trained on wine reviews from one set of authors for which the color, grape variety, and origin of a wine were known, and subsequently tested on data from a new author. This analysis revealed that, regardless of individual differences in vocabulary preferences, color and grape variety were predicted with high accuracy. Second, using Termhood as a measure of how words are used in wine reviews in a domain-specific manner compared to other genres in English, a list of 146 wine-specific terms was uncovered. These words were compared to existing lists of wine vocabulary that are currently used to train experts. Some overlap was observed, but there were also gaps revealed in the extant lists, suggesting these lists could be improved by our automatic analysis.

Extraction keyphrase systems traditionally use classification algorithms and do not consider the fact that part of the keyphrases may not be found in the text, reducing the accuracy of such algorithms a priori. In this work, we propose to improve the accuracy of these systems with inferential mechanisms that use a knowledge representation model, including symbolic models of knowledge bases and distributional semantics, to expand the set of keyphrase candidates to be submitted to the classification algorithm with terms that are not in the text (not-in-text terms). The basic assumption we have is that not-in-text terms have a semantic relationship with terms that are in the text. To represent this relationship, we have defined two new features to be represented as input to the classification algorithms. The first feature refers to the power of discrimination of the inferred not-in-text terms. The intuition behind this is that good candidates for a keyphrase are those that are deduced from various textual terms in a specific document and that are not often deduced in other documents. The other feature represents the descriptive strength of a not-in-text candidate. We argue that not-in-text keyphrases must have a strong semantic relationship with the text and that the power of this semantic relationship can be measured in a similar way as popular metrics like TFxIDF. The method proposed in this work was compared with state-of-the-art systems using five corpora and the results show that it has significantly improved automatic keyphrase extraction, dealing with the limitation of extracting keyphrases absent from the text.

This paper proposes four novel term evaluation metrics to represent documents in the text categorization where class distribution is imbalanced. These metrics are achieved from the revision of the four common term evaluation metrics: chi-square, information gain, odds ratio, and relevance frequency. While the common metrics require a balanced class distribution, our proposed metrics evaluate the document terms under an imbalanced distribution. They calculate the degree of relatedness of terms with respect to minor and major classes by considering their imbalanced distribution. Using these metrics in the document representation makes a better distinction between the documents of the minor and major classes and improves the performance of machine learning algorithms. The proposed metrics are assessed over three popular benchmarks (two subsets of Reuters-21578 and WebKB) by using four classification algorithms: support vector machines, naive Bayes, decision trees, and centroid-based classifiers. Our empirical results indicate that the proposed metrics outperform the common metrics in the imbalanced text categorization.

The objective of this work is to set a corpus-driven methodology to quantify automatically diachronic language distance between chronological periods of several languages. We apply a perplexity-based measure to written text representing different historical periods of three languages: European English, European Portuguese, and European Spanish. For this purpose, we have built historical corpora for each period, which have been compiled from different open corpus sources containing texts as close as possible to its original spelling. The results of our experiments show that a diachronic language distance based on perplexity detects the linguistic evolution that had already been explained by the historians of the three languages. It is remarkable to underline that it is an unsupervised multilingual method which only needs a raw corpora organized by periods.

Virtual patient software allows health professionals to practise their skills by interacting with tools simulating clinical scenarios. A natural language dialogue system can provide natural interaction for medical history-taking. However, the large number of concepts and terms in the medical domain makes the creation of such a system a demanding task. We designed a dialogue system that stands out from current research by its ability to handle a wide variety of medical specialties and clinical cases. To address the task, we designed a patient record model, a knowledge model for the task and a termino-ontological model that hosts structured thesauri with linguistic, terminological and ontological knowledge. We used a frame- and rule-based approach and terminology-rich resources to handle the medical dialogue. This work focuses on the termino-ontological model, the challenges involved and how the system manages resources for the French language. We adopted a comprehensive approach to collect terms and ontological knowledge, and dictionaries of affixes, synonyms and derivational variants. Resources include domain lists containing over 161,000 terms, and dictionaries with over 959,000 word/concept entries. We assessed our approach by having 71 participants (39 medical doctors and 32 non-medical evaluators) interact with the system and use 35 cases from 18 specialities. We conducted a quantitative evaluation of all components by analysing interaction logs (11,834 turns). Natural language understanding achieved an F-measure of 95.8%. Dialogue management provided on average 74.3 (±9.5)% of correct answers. We performed a qualitative evaluation by collecting 171 five-point Likert scale questionnaires. All evaluated aspects obtained mean scores above the Likert mid-scale point. We analysed the vocabulary coverage with regard to unseen cases: the system covered 97.8% of their terms. Evaluations showed that the system achieved high vocabulary coverage on unseen cases and was assessed as relevant for the task.

Entities play an essential role in understanding textual documents, regardless of whether the documents are short, such as tweets, or long, such as news articles. In short textual documents, all entities mentioned are usually considered equally important because of the limited amount of information. In long textual documents, however, not all entities are equally important: some are salient and others are not. Traditional entity topic models (ETMs) focus on ways to incorporate entity information into topic models to better explain the generative process of documents. However, entities are usually treated equally, without considering whether they are salient or not. In this work, we propose a novel ETM, Salient Entity Topic Model, to take salient entities into consideration in the document generation process. In particular, we model salient entities as a source of topics used to generate words in documents, in addition to the topic distribution of documents used in traditional topic models. Qualitative and quantitative analysis is performed on the proposed model. Application to entity salience detection demonstrates the effectiveness of our model compared to the state-of-the-art topic model baselines.

Light verb constructions (LVCs) are verb and noun combinations in which the verb has lost its meaning to some degree and the noun is used in one of its original senses, typically denoting an event or an action. They exhibit special linguistic features, especially when regarded in a multilingual context. In this paper, we focus on the automatic detection of LVCs in raw text in four different languages, namely, English, German, Spanish, and Hungarian. First, we analyze the characteristics of LVCs from a linguistic point of view based on parallel corpus data. Then, we provide a standardized (i.e., language-independent) representation of LVCs that can be used in machine learning experiments. After, we experiment on identifying LVCs in different languages: we exploit language adaptation techniques which demonstrate that data from an additional language can be successfully employed in improving the performance of supervised LVC detection for a given language. As there are several annotated corpora from several domains in the case of English and Hungarian, we also investigate the effect of simple domain adaptation techniques to reduce the gap between domains. Furthermore, we combine domain adaptation techniques with language adaptation techniques for these two languages. Our results show that both out-domain and additional language data can improve performance. We believe that our language adaptation method may have practical implications in several fields of natural language processing, especially in machine translation.

This paper proposes a robust text classification and correspondence analysis approach to identification of similar languages. In particular, we propose to use the readily available information of clauses and word length distribution to model similar languages. The modeling and classification are based on the hypothesis that languages are self-adaptive complex systems and hence can be classified by dynamic features describing the system, especially in terms of distributional relations of constituents of a system. For similar languages whose grammatical differences are often subtle, classification based on dynamic system features should be more effective. To test this hypothesis, we considered both regional and genre varieties of Mandarin Chinese for classification. The data are extracted from two comparable balanced corpora to minimize possible confounding factors. The two corpora are the Sinica Corpus from Taiwan and the Lancaster Corpus of Mandarin Chinese from Mainland China, and the two genres are reportage and review. Our text classification and correspondence analysis results show that the linguistically felicitous two-level constituency model combining power functions between word and clauses effectively classifies the two varieties of Chinese for both genres. In addition, we found that genres do have compounding effect on classification of regional varieties. In particular, reportage in two varieties is more likely to be classified than review, corroborating the complex system view of language variations. That is, language variations and changes typically do not take place evenly across the board for the complete language system. This further enhances our hypothesis that dynamic complex system features, such as the power functions captured by the Menzerath–Altmann law, provide effective models in classifications of similar languages.

In this paper, we present two approaches and the implemented system for bilingual terminology extraction that rely on an aligned bilingual domain corpus, a terminology extractor for a target language, and a tool for chunk alignment. The two approaches differ in the way terminology for the source language is obtained: the first relies on an existing domain terminology lexicon, while the second one uses a term extraction tool. For both approaches, four experiments were performed with two parameters being varied. In the experiments presented in this paper, the source language was English, and the target language Serbian, and a selected domain was Library and Information Science, for which an aligned corpus exists, as well as a bilingual terminological dictionary. For term extraction, we used the FlexiTerm tool for the source language and a shallow parser for the target language, while for word alignment we used GIZA++. The evaluation results show that for the first approach the F1 score varies from 29.43% to 51.15%, while for the second it varies from 61.03% to 71.03%. On the basis of the evaluation results, we developed a binary classifier that decides whether a candidate pair, composed of aligned source and target terms, is valid. We trained and evaluated different classifiers on a list of manually labeled candidate pairs obtained after the implementation of our extraction system. The best results in a fivefold cross-validation setting were achieved with the Radial Basis Function Support Vector Machine classifier, giving a F1 score of 82.09% and accuracy of 78.49%.

In this article, we propose an innovative and robust approach to stylometric analysis without annotation and leveraging lexical and sub-lexical information. In particular, we propose to leverage the phonological information of tones and rimes in Mandarin Chinese automatically extracted from unannotated texts. The texts from different authors were represented by tones, tone motifs, and word length motifs as well as rimes and rime motifs. Support vector machines and random forests were used to establish the text classification model for authorship attribution. From the results of the experiments, we conclude that the combination of bigrams of rimes, word-final rimes, and segment-final rimes can discriminate the texts from different authors effectively when using random forests to establish the classification model. This robust approach can in principle be applied to other languages with established phonological inventory of onset and rimes.