We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data induce generalizable structural features that LSTMs can use for natural language. We find that training on non-linguistic data with latent structure (MIDI music or Java code) improves test performance on natural language, despite no overlap in surface form or vocabulary. To pinpoint the kinds of abstract structure that models may be encoding to lead to this improvement, we run similar experiments with two artificial parentheses languages: one which has a hierarchical recursive structure, and a control which has paired tokens but no recursion. Surprisingly, training a model on either of these artificial languages leads to the same substantial gains when testing on natural language. Further experiments on transfer between natural languages controlling for vocabulary overlap show that zero-shot performance on a test language is highly correlated with typological syntactic similarity to the training language, suggesting that representations induced by pre-training correspond to the cross-linguistic syntactic properties. Our results provide insights into the ways that neural models represent abstract syntactic structure, and also about the kind of structural inductive biases which allow for natural language acquisition.
University of Gothenburg（哥德堡大学）；Universität Tübingen（图宾根大学）
Corpora and web texts can become a rich language learning resource if we have a means of assessing whether they are linguistically appropriate for learners at a given proficiency level. In this paper, we aim at addressing this issue by presenting the first approach for predicting linguistic complexity for Swedish second language learning material on a 5-point scale. After showing that the traditional Swedish readability measure, Läsbarhetsindex (LIX), is not suitable for this task, we propose a supervised machine learning model, based on a range of linguistic features, that can reliably classi…
University of Amsterdam（阿姆斯特丹大学）；RWTH-Aachen University（亚琛工业大学）
There is a growing interest in the combined use of NLP and machine learning methods to predict gaze patterns during naturalistic reading. While promising results have been obtained through the use of transformer-based language models, little work has been undertaken to relate the performance of such models to general text characteristics. In this paper we report on experiments with two eye-tracking corpora of naturalistic reading and two language models (BERT and GPT-2). In all experiments, we test effects of a broad spectrum of features for predicting human reading behavior that fall into fiv…
This article discusses the extension of the notion of context from linguistics to the domain of music. In language, the statistical regularity known as Zipf's law -which concerns the frequency of usage of different words- has been quantitatively related to the process of text generation. This connection is established by Simon's model, on the basis of a few assumptions regarding the accompanying creation of context. Here, it is shown that the statistics of note usage in musical compositions are compatible with the predictions of Simon's model. This result, which gives objective support to the …
Taylor's law describes the fluctuation characteristics underlying a system in which the variance of an event within a time span grows by a power law with respect to the mean. Although Taylor's law has been applied in many natural and social systems, its application for language has been scarce. This article describes a new quantification of Taylor's law in natural language and reports an analysis of over 1100 texts across 14 languages. The Taylor exponents of written natural language texts were found to exhibit almost the same value. The exponent was also compared for other language-related da…
When looking at the structure of natural language, "phrases" and "words" are central notions. We consider the problem of identifying such "meaningful subparts" of language of any length and underlying composition principles in a completely corpus-based and language-independent way without using any kind of prior linguistic knowledge. Unsupervised methods for identifying "phrases", mining subphrase structure and finding words in a fully automated way are described. This can be considered as a step towards automatically computing a "general dictionary and grammar of the corpus". We hope that in …
This paper investigates censorship from a linguistic perspective. We collect a corpus of censored and uncensored posts on a number of topics, build a classifier that predicts censorship decisions independent of discussion topics. Our investigation reveals that the strongest linguistic indicator of censored content of our corpus is its readability.
We propose a multimodal singing language classification model that uses both audio content and textual metadata. LRID-Net, the proposed model, takes an audio signal and a language probability vector estimated from the metadata and outputs the probabilities of the target languages. Optionally, LRID-Net is facilitated with modality dropouts to handle a missing modality. In the experiment, we trained several LRID-Nets with varying modality dropout configuration and tested them with various combinations of input modalities. The experiment results demonstrate that using multimodal input improves pe…
University of Richmond（里士满大学）；IIIT Hyderabad（海得拉巴国际信息技术学院）；MIT（麻省理工学院）；Microsoft Research India（微软印度研究院）
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong lin…
Cognitive processing signals can be used to improve natural language processing (NLP) tasks. However, it is not clear how these signals correlate with linguistic information. Bridging between human language processing and linguistic features has been widely studied in neurolinguistics, usually via single-variable controlled experiments with highly-controlled stimuli. Such methods not only compromises the authenticity of natural reading, but also are time-consuming and expensive. In this paper, we propose a data-driven method to investigate the relationship between cognitive processing signals …
The music industry is a $130 billion industry. Predicting whether a song catches the pulse of the audience impacts the industry. In this paper we analyze language inside the lyrics of the songs using several computational linguistic algorithms and predict whether a song would make to the top or bottom of the billboard rankings based on the language features. We trained and tested an SVM classifier with a radial kernel function on the linguistic features. Results indicate that we can classify whether a song belongs to top and bottom of the billboard charts with a precision of 0.76.
This article describes a data driven method for deriving the relationship between personality and media preferences. A qunatifiable representation of such a relationship can be leveraged for use in recommendation systems and ameliorate the "cold start" problem. Here, the data is comprised of an original collection of 1,316 Okcupid dating profiles. Of these profiles, 800 are labeled with one of 16 possible Myers-Briggs Type Indicators (MBTI). A personality specific topic model describing a person's favorite books, movies, shows, music, and food was generated using latent Dirichlet allocation (L…
A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Huawei Technologies Co., Ltd.（华为技术有限公司）
A Predictive Model of Digital Information Engagement: Forecasting User Engagement With English Words by Incorporating Cognitive Biases, Computational Linguistics and Natural Language Processing
State University of New York at Albany（纽约州立大学奥尔巴尼分校）；Google（谷歌公司）
