Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
16504 papers
AlpinoGraph is a graph-based search engine which provides treebank search using SQL database technology coupled with the Cypher query language for graphs. In the paper, we show that AlpinoGraph is a very powerful and very flexible approach towards treebank search. At the same time, AlpinoGraph is efficient. Currently, AlpinoGraph is applicable for all standard Dutch treebanks. We compare the Cypher queries in AlpinoGraph with the XPath queries used in earlier treebank search applications for the same treebanks. We also present a pre-processing technique which speeds up query processing dramatically in some cases, and is applicable beyond AlpinoGraph.
An exploration of the physiological correlates of subjective emotional states has theoretical and practical significance. Previous studies have reported that subjective valence and arousal correspond to facial electromyography (EMG) and electrodermal activity (EDA), respectively, across stimuli. However, the reported results were inconsistent, no study investigated subjective-physiological concordance across time, and measures of arousal remain controversial. To investigate these issues, while healthy adults (n = 20) viewed emotional films, we assessed overall and continuous ratings of valence and arousal and recorded EMG from the corrugator supercilii and zygomatic major, EDA from the palms and forehead, and nose-tip temperature. The corrugator and zygomatic EMG were negatively and positively associated with valence ratings, respectively, across stimuli and time. EDA (both sites) and nose-tip temperature were positively and negatively associated with arousal ratings, respectively, across stimuli and time. It is concluded that subjective emotional valence and arousal dynamics have specific physiological correlates.
We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled generalpurpose multilingual text. We introduce a data augmentation technique that uses synthetic treebanks to improve production-grade parsers. The synthetic treebanks are generated using a state-of-the-art biaffine parser adapted with pretrained Transformer models, such as Multilingual BERT (M-BERT). The new parser improves LAS by up to two points on seven languages. The production models' LAS performance improves as the augmented treebanks scale in size, surpassing performance of production models trained on originally annotated UD treebanks.
Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective cross-lingual UD parsing framework for transferring parser from only one source monolingual treebank to any other target languages without treebank available. To reach satisfactory parsing accuracy among quite different languages, we introduce two language modeling tasks into dependency parsing as multi-tasking. Assuming only unlabeled data from target languages plus the source treebank can be exploited together, we adopt a self-training strategy for further performance improvement in terms of our multi-task framework. Our proposed cross-lingual parsers are implemented for English, Chinese, and 22 UD treebanks. The empirical study shows that our cross-lingual parsers yield promising results for all target languages, for the first time, approaching the parser performance which is trained in its own target treebank.
The present article presents some challenges posed by lemmatization and PoS tagging of Latin, with reference to the ongoing work to revise the Latin Dependency Treebank. Current options available for lemmatization and morphological analysis of Latin are reviewed and discussed. The pipeline to annotate the morphological layer of the Latin Dependency Treebank is shown to consist of three main steps: (i) tokenization/sentence split, which is performed via a documented rule-based algorithm, (ii) pre-population by means of COMBO, a state-of-the-art joint lemmatizer, PoS tagger, and parser trained on the data of the Latin Dependency Treebank 2.1, and (iii) manual error correction informed by the attempt to identify and document lemmatization and morphology annotation rules.
Historical linguistics, whether synchronic or diachronic, is by definition based on corpora.Since we do not have access to the intuitions of native speakers we can only test linguistic hypotheses about historical languages by systematically collating information from our corpus of texts.For questions that typically concern linguists, this often means identifying every occurrence of a particular phenomenon in the corpus, analysing, classifying and counting the occurrences and then using this for testing hypotheses about the structure of the language.This can be done manually, but this is time-consuming and error-prone.As Haug (2015) points out, while reading the text and manually collating information from it is essential for hypothesis formation it is much less useful for hypothesis testing.Even if the text is in electronic form, it is easy to overlook an example, record it incorrectly or fail to apply test criteria consistently over time.This paper focuses on treebanks, which are corpora that have been annotated with morphosyntactic information so that we can extract linguistic structures like 'verb with an accusative noun'.High-quality treebanks for a range of historical languages now exist and are widely used in historical linguistic research.This includes treebanks that follow the Penn-style of annotation, e.g. the Penn-Helsinki
This paper reports on the analysis and annotation of Multiword Expressions in the Irish Universal Dependency Treebank. We provide a linguistic discussion around decisions on how to appropri- ately label Irish MWEs using the compound, flat and fixed dependency relation labels within the framework of the Universal Dependencies annotation guidelines. We discuss some nuances of the Irish language that pose challenges for assigning these UD labels and provide this report in support of the Irish UD annotation guidelines. With this we hope to ensure consistency in annotation across the dataset and provide a basis for future MWE annotation for Irish.
In this dataset, we introduce MS-TR a Morphologically Enriched Sentiment Treebank, which was implemented for training Recursive Deep Models to address compositional sentiment analysis in Turkish.
Two iconic twentieth-century print dictionaries provide a sampling of dictionary front matter in the Soviet–Russian lexicographic tradition; they demonstrate how front matter was used for overt and covert messaging about the linguistic norm. First is the one-volume bilingual English–Russian dictionary of Vladimir Karlovich Müller, and second is the one-volume monolingual Russian dictionary of Sergei Ivanovich Ozhegov; later it was published with Ozhegov and Nataliia Iul’evna Shvedova listed as co-authors. Both dictionaries were revised and reprinted over many decades. Only two editions of each dictionary are in focus, although there were more than sixty editions of Müller, 23 of Ozhegov, and several of Ozhegov and Shvedova.
Tae Hwan Oh, Ji Yoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, Hansaem Kim. Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. 2020.
We introduce a new symmetric measure (called pos ) that utilises the non-symmetric KL cpos 3 measure We can set a threshold for this new measure so that a pair of treebanks can be considered harmonious in their annotation if pos does not surpass the threshold. For the calculation of the threshold, we estimate the effects of (i) the size variation, and (ii) the genre variation in the considered pair of treebanks. The estimations are based on data from treebanks of distinct language families, making the threshold less dependent on the properties of individual languages. We demonstrate the utility of the proposed measure by listing the treebanks in Universal Dependencies version 2.5 (UDv2.5) (Zeman et al., 2019) data that are annotated consistently with other treebanks of the same language. However, the measure could be used to assess inter-treebank annotation consistency under other (non-UD) annotation guidelines as well.
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled and unlabeled data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowestresource cases, and demonstrate the importance of the relationship between such models' pretraining data and target language varieties.
Text structuring is a fundamental step in NLG, especially when generating multi-sentential text. With the goal of fostering more general and data-driven approaches to text structuring, we propose the new and domain-independent NLG task of structuring and ordering a (possibly large) set of EDUs. We then present a solution for this task that combines neural dependency tree induction with pointer networks and can be trained on large discourse treebanks that have only recently become available. Further, we propose a new evaluation metric that is arguably more suitable for our new task compared to existing content ordering metrics. Finally, we empirically show that our approach outperforms competitive alternatives on the proposed measure and is equivalent in performance with respect to previously established measures.
Abstract In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.
A recent advance in monolingual dependency parsing is the idea of a treebank embedding vector, which allows all treebanks for a particular language to be used as training data while at the same time allowing the model to prefer training data from one treebank over others and to select the preferred treebank at test time. We build on this idea by 1) introducing a method to predict a treebank vector for sentences that do not come from a treebank used in training, and 2) exploring what happens when we move away from predefined treebank embedding vectors during test time and instead devise tailored interpolations. We show that 1) there are interpolated vectors that are superior to the predefined ones, and 2) treebank vectors can be predicted with sufficient accuracy, for nine out of ten test languages, to match the performance of an oracle approach that knows the most suitable predefined treebank embedding for the test set.
International audience
Multiword Expression (MWE) has been a pain in the neck, especially in determining its word-classes in syntactic treebank. Previous work had proposed annotation guidelines for Indonesian MWEs that align to the Penn Treebank (PTB) format. However, we think that their proposed annotation still needs improvements. Therefore, this study proposes a new annotation guideline in labeling Indonesian MWE that conforms to PTB format. Moreover, we also revised the MWE annotation of an existing Indonesian constituency treebank consisting of 1030 sentences to conform to the new guidelines. To evaluate the revised treebank's quality, we built an Indonesian constituency parser model using the revised treebank and Stanford parser. The experiments show that the resulting parser has an F1-score of 69.97%.
The question whether a constitutive linguistic norm can be prescriptive is central to the debate on the normativity of meaning. Recently, the author has attempted to defend an affirmative answer, pointing to how speakers sporadically invoke constitutive linguistic norms in the service of linguistic calibration. Such invocations are clearly prescriptive. However, they are only appropriate if the invoked norms are applicable to the addressed speaker. But that can only be the case if the speaker herself generally accepts them. This qualification has led critics to argue that if an addressed speaker’s acceptance is a necessary condition for legitimate prescriptions (and reproach for failure to adhere to them), then the account becomes unable to underwrite actual normativity. Moreover, critics argue, a danger of vicious circularity arises from the calibration account. This paper shows that once a vantage point within the calibration practice is accepted, the criticisms lose their force. It then explores why a theorist might reject such a perspective and suggests, as a plausible candidate, implicit Humean assumptions about the proper explanation of (linguistic) action. The paper ends by sketching a way forward for the debate on the normativity of meaning in light of this diagnosis.
Treebanks are linguistically annotated corpus of natural language texts represented as a database. It is vital in natural language processing (NLP), which allows the interaction and communication between computers and the human language. It is behind the recent technological innovations of automated and smart assistants. This paper intends to create an English treebank for the usage of Mapua University in their future endeavors to develop Interactive Voice Response (IVR) systems. This study is accomplished by providing students with a connection to a communication server through their phones. Calls are made to the Asterisk server set up in a Raspberry Pi. When the intended audio message is forwarded to the system, it is converted to a text input using a Speech-to-Text algorithm. It then undergoes process and analysis divided into five parts: preprocessing, segmentation, tagging, creation of the grammar tree, and computation for the Probabilistic Context-Free Grammar (PCFG). Based on the testing results for this study, the system yielded a word error rate of 7.36%, a NER F1 score of 71.7%, and a PCFG calculation accuracy of 64.44%.
The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RSTstyle discourse parsing. In this work, we present a novel scalable methodology to automatically generate discourse treebanks using distant supervision from sentiment-annotated datasets, creating and publishing MEGA-DT, a new large-scale discourse-annotated corpus. Our approach generates discourse trees incorporating structure and nuclearity for documents of arbitrary length by relying on an efficient heuristic beam-search strategy, extended with a stochastic component. Experiments on multiple datasets indicate that a discourse parser trained on our MEGA-DT treebank delivers promising inter-domain performance gains when compared to parsers trained on human-annotated discourse corpora.
This chapter provides an overview of the contribution the Prague School of Linguistics has made to the study of linguistic norm. Departing from a functionalist approach to the analysis of language, the Prague School shaped and theorized the influential notions of language culture (jazykova kultura, Sprachkultur) and language cultivation (Sprachpflege) at a time when, in Western Europe, prescriptive approaches to language were considered unworthy of scientific attention. Distancing themselves from "purist" and "school-grammar" conceptions of language maintenance and based on the case of Czech language culture, the representatives of the Prague School advocated for the cultivation of the written (standard) language in functional terms in order to achieve a "stable" yet "elastic" concept of norm.
We take up the scientific question of what determines the preferred order of adjectives in English, in phrases such as big blue box where multiple adjectives modify a following noun. We implement and test four quantitative theories, all of which are theoretically motivated in terms of efficiency in human language production and comprehension. The four theories we test are subjectivity We evaluate theories based on their ability to predict orders of unseen adjectives in hand-parsed and automatically-parsed dependency treebanks. We find that subjectivity, information locality, and information gain are all strong predictors, with some evidence for a two-factor account, where subjectivity and information gain reflect a factor involving semantics, and information locality reflects collocational preferences.
Arousal is one of the dimensions of core affect and frequently used to describe experienced or observed emotional states. While arousal ratings of facial expressions are collected in many studies it is not well understood how arousal is displayed in or interpreted from facial expressions. In the context of socioemotional disorders such as Autism Spectrum Disorder, this poses the question of a differential use of facial information for arousal perception. In this study, we demonstrate how automated face-tracking tools can be used to extract predictors of arousal judgments. We find moderate to strong correlations among all measures of static information on one hand and all measures of dynamic information on the other. Based on these results, we tested two measures, average distance to the neutral face and average facial movement speed, within and between neurotypical individuals ( N = 401) and individuals with autism ( N = 19). Distance to the neutral face was predictive of arousal in both groups. Lower mean arousal ratings were found for the autistic group, but no difference in correlation of the measures and arousal ratings could be found between groups. Results were replicated in an high autistic traits group. The findings suggest a qualitatively similar perception of arousal for individuals with and without autism. No correlations between valence ratings and any of the measures could be found, emphasizing the specificity of our tested measures. Distance and speed predictors share variability and thus speed should not be discarded as a predictor of arousal ratings.
This paper presents the first proper syntactic treebank for Akkadian, an ancient Semitic language which can only be reconstructed from its textual data. We introduce our corpus of early Neo-Assyrian royal inscriptions, present some typical syntactic constructions of this genre and discuss the morphological and syntactic choices we have made. For developing a gold standard for morphological annotations, we tested the manually annotated material against BabyFST, a morphological analyzer of Akkadian. We also tested the reproducibility of the syntactic annotations using the TurkuNLP neural parser.
We present our contribution to the EvaLatin shared task, which is the first\nevaluation campaign devoted to the evaluation of NLP tools for Latin. We\nsubmitted a system based on UDPipe 2.0, one of the winners of the CoNLL 2018\nShared Task, The 2018 Shared Task on Extrinsic Parser Evaluation and SIGMORPHON\n2019 Shared Task. Our system places first by a wide margin both in\nlemmatization and POS tagging in the open modality, where additional supervised\ndata is allowed, in which case we utilize all Universal Dependency Latin\ntreebanks. In the closed modality, where only the EvaLatin training data is\nallowed, our system achieves the best performance in lemmatization and in\nclassical subtask of POS tagging, while reaching second place in cross-genre\nand cross-time settings. In the ablation experiments, we also evaluate the\ninfluence of BERT and XLM-RoBERTa contextualized embeddings, and the treebank\nencodings of the different flavors of Latin treebanks.\n
We describe an automatic method for converting the Persian Dependency Treebank (Rasooli et al, 2013) to Universal Dependencies. This treebank contains 29107 sentences. Our experiments along with manual linguistic analysis show that our data is more compatible with Universal Dependencies than the Uppsala Persian Universal Dependency Treebank (Seraji et al., 2016), and is larger in size and more diverse in vocabulary. Our data brings in a labeled attachment F-score of 85.2 in supervised parsing. Our delexicalized Persian-to-English parser transfer experiments show that a parsing model trained on our data is ~2% absolutely more accurate than that of Seraji et al. (2016) in terms of labeled attachment score.
This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework of syntactic analysis. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this article is twofold: (1) to provide a condensed, though comprehensive, overview of such treebanks -- based on available literature -- along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The overarching goal of this article is to provide a common framework for researchers interested in developing similar resources in UD, thus promoting cross-linguistic consistency, which is a principle that has always been central to the spirit of UD.
Large typological databases have permitted new ways of studying cross-linguistic morphological variation. Recently, computational modelers with typological interests have begun to turn to broad multilingual text databases. In this paper, we will focus particularly on the UniMorph database, a collection of morphological paradigms, mostly gathered automatically from the crowd-sourced multi-lingual dictionary Wiktionary. It was designed to make the large quantity of data contained in Wiktionary available for NLP researchers by standardizing the data and putting it into a form that is easy to access. For typological studies, however, the requirements for a linguistically informed view of morphological variation are quite different. They involve using a morphological database as a scientific instrument to both formulate and test hypotheses about the nature and organization of language systems. The requirements are, accordingly, much higher. In this paper, we survey some of the methodological challenges and pitfalls involved in using corpora for typological research, and we end with a proposal for best practices and directions for further research.
The paper presents a discussion on the main linguistic phenomena of user-generated texts found in web and social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this paper is twofold: (1) to provide a short, though comprehensive, overview of such treebanks - based on available literature - along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The main goal of this paper is to provide a common framework for those teams interested in developing similar resources in UD, thus enabling cross-linguistic consistency, which is a principle that has always been in the spirit of UD.
Ouyang and Jiang (2018) measured the second language proficiency of English as a foreign language (EFL) learners based on the probability distribution of dependency distance. However, the typological features of the native language (Chinese) and the target language (English) they adopted are generally considered similar in word order and dependency direction. In addition, their method of classifying the learners’ proficiency levels is based on the learners’ grades, which might weaken the validity of the results. These results are strengthened and verified further in the current research by analysing a treebank of Japanese EFL learners’ interlanguage since their native language and the target language are typologically distinctive. Moreover, the TOEIC score was used as a benchmark to classify the second language proficiency levels of the learners. We found that (1) the mean dependency distance can measure the syntactic complexity of Japanese EFL learners’ interlanguage; (2) constrained by human working memory, the probability distribution of dependency distance based on Japanese EFL learners’ interlanguage follows certain distribution patterns as unveiled in other natural human languages; (3) the parameters of the right truncated modified Zipf-Alekseev distribution can well reflect the changes of the Japanese EFL learners’ second language proficiency, indicating the development of interlanguage.
We used the tools of network science to examine different dimensions of phonological similarity. Data from a phonological associate task and from an identification of words in noise task were used to create two separate networks. The resulting networks were compared to each other and to a network formed by a computational metric (i.e., one-phoneme metric) widely-used to assess phonological similarity using an information-theoretic approach and a variety of network measures (e.g., small-world structure, scale-free structure, mixing by degree, location of nodes in the network, and community structure). While we found that a network formed by the one-phoneme metric was structurally less similar to the network formed from the phonological associate task and to the network formed from the identification of words in noise task than the latter two were to each other, there were also several common network structure features between the one-phoneme metric network and the phonological association network. We then compared the influence of degree (equivalent to neighborhood density) from each of the networks on behavioral data, namely reaction time on visual and auditory lexical decision tasks, obtained from two psycholinguistic megastudies to provide behavioral evidence for differences in network structures. We found that the effect of degree differed across network types and tasks. We discuss the advantages and disadvantages of each approach to determining phonological similarity, the implications of using each approach, and a possible direction forward for language research through the use of multiplex networks.
Przedmiotem badań jest jednojęzyczna leksykografia elektroniczna. Celem artykułujest ukazanie wpływu technik komputerowych na organizację, rozmiar, przeznaczeniei zawartość słowników. W swych badaniach autorka koncentruje się na elektronicznychbazach danych. Definiuje, czym są, oraz objaśnia, jak ich budowa i sposób organizacjizgromadzonych w nich danych wpływają na postać słowników elektronicznych. W artykulezostały poddane analizie trzy współczesne słowniki języka polskiego: Uniwersalny słownikjęzyka polskiego PWN, Wielki słownik języka polskiego PAN oraz Słownik gramatycznyjęzyka polskiego. Autorka dowodzi, że sposób organizacji i prezentacji wiedzy w omówionychdziełach umożliwia użytkownikom korzystanie z nich w sposób zaawansowany,co oznacza sprawne dotarcie do szczegółowych informacji o jednostkach leksykalnych,grupowanie ich, jak również doraźne kompilowanie „podsłowników”, spełniających określoneoczekiwania odbiorców.
We present our work of constructing the first treebank for the Xibe language following the Universal Dependencies (UD) annotation scheme. Xibe is a low-resourced and severely endangered Tungusic language spoken by the Xibe minority living in the Xinjiang Uygur Autonomous Region of China. We collected 810 sentences so far, including 544 sentences from a grammar book on written Xibe and 266 sentences from Cabcal News. We annotated those sentences manually from scratch. In this paper, we report the procedure of building this treebank and analyze several important annotation issues of our treebank. Finally, we propose our plans for future work.
Хухуни Е.А.Комарова Московский государственный областной университет НОРМА, СТАНДАРТ, УЗУС В век информационных технологий и глобализации процесс изменения языка ускоряется, что не может не влиять на узус и норму.Такая тенденция вызывает неоднозначную реакцию в русскоговорящем обществе, зачастую выражающуюся в
Tunisian Arabic (TA) is a morphologically and syntactically rich dialect, which presents an interesting challenge for Natural Language Processing (NLP) tasks such as part-of-speech tagging, parsing, semantic analysis, etc. It is classified as a low-resourced language. Tunisians use it in daily life communication, social media exchanges, etc. In this paper, we focus on Tunisian Arabic linguistic resources and tools creation. We present the creation and generation of Tunisian treebank and parser for social media texts. We use an existing state-of-the-art parser to build this treebank. Then, we investigate the effects of different data sizes and different combinations of Tunisian dialect forms in automatic parsing.
Human dialogue is governed by communicative norms that speakers are expected to follow in order to be viewed as cooperative dialogue partners. Accordingly, for language-capable autonomous agents to be effective human teammates they must be able to understand and generate language that complies with those norms. Moreover, these linguistic norms are highly context sensitive, requiring autonomous agents to be able to model the contextual factors that dictate when and how those norms are applied. In this work, we consider three key linguistic norms (directness, brevity, and politeness), and examine the extent to which adherence to these norms varies under changes to three key contextual factors (potential for harm, interlocutor authority, and time pressure). Our results, based on a human-subject study involving 5,642 human utterances, provide strong evidence that speakers do indeed vary their adherence to these norms under changes to these contextual factors.
This chapter gives an overview of the conception(s) of linguistic normativity in Cognitive Linguistics (CL) and the contributions of CL to the study of normativity on the level of language use (discourse). While normativity has never been a central concern of CL, it is most relevant - though in quite different ways - for both cognitive semantics and cognitive grammar models. The concept of sign of those grammar models is based on the assumption that the linguistic units which constitute a language do not only exist as entrenched units in speakers' minds but also as conventional units by virtue of being shared in a speech community. Cognitive semantics, on the other hand, is most relevant in the field of cognitive language criticism (Sprachkritik) and its application to the analysis of public discourse ("political correctness", "gender-neutral language").
Recommender systems often involve multi-aspect factors. For example, when shopping for shoes online, consumers usually look through their images, ratings, and product's reviews before making their decisions. To learn multi-aspect factors, many context-aware models have been developed based on tensor factorizations. However, existing models assume multilinear structures in the tensor data, thus failing to capture nonlinear feature interactions. To fill this gap, we propose a novel nonlinear tensor machine, which combines deep neural networks and tensor algebra to capture nonlinear interactions among multi-aspect factors. We further consider adversarial learning to assist the training of our model. Extensive experiments demonstrate the effectiveness of the proposed model.
The Neural Machine-Parsed IcePaHC is a machine-parsed treebank which consists of Icelandic texts from the 13th to 20th century, mostly Icelandic sagas. The texts were parsed using the IceNeuralParsingPipeline, a parsing pipeline which includes an Icelandic model of the Berkeley Neural Parser along with pre- and postprocessing steps. The parser was trained on IcePaHC and the parsing scheme of the treebank is therefore the same, although the treebank does not include empty phrases or lemmas. The treebank includes 52 texts. The total word count is 1,716,429 and the total number of clauses is 167,815.