Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the content and even logic of original sentences, mainly due to the large unconstrained model space or too simplified assumptions on latent embedding space. Since language itself is an intelligent product of humans with certain grammars and has a limited rule-based model space by its nature, relieving this problem requires reconciling the model capacity of deep neural networks with the intrinsic model constraints from human linguistic rules. To this end, we propose a method called Graph Transformer based Auto Encoder (GTAE), which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences. Quantitative experiment results on three non-parallel text style transfer tasks show that our model outperforms state-of-the-art methods in content preservation, while achieving comparable performance on transfer accuracy and sentence naturalness.
South China University of Technology（华南理工大学）；Guangzhou Laboratory（广州实验室）；Kujiale, Inc.（酷家乐公司）；University of Adelaide（阿德莱德大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intuitively without knowing much knowledge about home design and experience of using complex designing tools, for example, via natural language. In this paper, we formulate it as a language conditioned visual content generation problem that is further divided into a floor plan generation and an interior texture (such as floor and wall) synthesis task. The only control signal of the generation process is the linguistic ex…
Chatlayer.ai by Sinch（Sinch旗下Chatlayer.ai）；Sinch；Ghent University - Imec（根特大学 - imec）
Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the presence of specific linguistic properties, it is unclear whether the vector representations can be manipulated to indirectly steer such properties. For efficient learning, we investigate the use of a geometric mapping in embedding space to transform linguistic properties, without any tuning of the pre-trained sentence encoder or decoder. We validate our approac…
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder
DCST, BNRist（DCST、BNRist；KIRC、人工智能研究院、清华大学，中国）；KIRC, Institute for Artificial Intelligence, Tsinghua University, China（中文语言文学系、北京大学，中国）；Department of Chinese Language and Literature, Peking University, China
In this paper I present a classifier for automatic identification of linguistic politeness in Hindi texts. I have used the manually annotated corpus of over 25,000 blog comments to train an SVM. Making use of the discursive and interactional approaches to politeness the paper gives an exposition of the normative, conventionalised politeness structures of Hindi. It is seen that using these manually recognised structures as features in training the SVM significantly improves the performance of the classifier on the test set. The trained system gives a significantly high accuracy of over 77% whic…
Automatic essay scoring (AES) refers to the process of scoring free text responses to given prompts, considering human grader scores as the gold standard. Writing such essays is an essential component of many language and aptitude exams. Hence, AES became an active and established area of research, and there are many proprietary systems used in real life applications today. However, not much is known about which specific linguistic features are useful for prediction and how much of this is consistent across datasets. This article addresses that by exploring the role of various linguistic featu…
Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder--Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous …
Natural language generation systems (NLG) map non-linguistic representations into strings of words through a number of steps using intermediate representations of various levels of abstraction. Template based systems, by contrast, tend to use only one representation level, i.e. fixed strings, which are combined, possibly in a sophisticated way, to generate the final text. In some circumstances, it may be profitable to combine NLG and template based techniques. The issue of combining generation techniques can be seen in more abstract terms as the issue of mixing levels of representation of diff…
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…
Guangdong University of Foreign Studies（广东外语外贸大学）；Renmin University of China（中国人民大学）；University of Montreal（蒙特利尔大学）
Deep learning models for automatic readability assessment generally discard linguistic features traditionally used in machine learning models for the task. We propose to incorporate linguistic features into neural network models by learning syntactic dense embeddings based on linguistic features. To cope with the relationships between the features, we form a correlation graph among features and use it to learn their embeddings so that similar features will be represented by similar embeddings. Experiments with six data sets of two proficiency levels demonstrate that our proposed methodology ca…
Linguistic steganography (LS) conceals the presence of communication by embedding secret information into a text. How to generate a high-quality text carrying secret information is a key problem. With the widespread application of deep learning in natural language processing, recent algorithms use a language model (LM) to generate the steganographic text, which provides a higher payload compared with many previous arts. However, the security still needs to be enhanced. To tackle with this problem, we propose a novel autoregressive LS algorithm based on BERT and consistency coding, which achiev…
Athens University of Economics and Business（雅典经济与商业大学）
Many concept-to-text generation systems require domain-specific linguistic resources to produce high quality texts, but manually constructing these resources can be tedious and costly. Focusing on NaturalOWL, a publicly available state of the art natural language generator for OWL ontologies, we propose methods to extract from the Web sentence plans and natural language names, two of the most important types of domain-specific linguistic resources used by the generator. Experiments show that texts generated using linguistic resources extracted by our methods in a semi-automatic manner, with mi…
Text documents are complex high dimensional objects. To effectively visualize such data it is important to reduce its dimensionality and visualize the low dimensional embedding as a 2-D or 3-D scatter plot. In this paper we explore dimensionality reduction methods that draw upon domain knowledge in order to achieve a better low dimensional embedding and visualization of documents. We consider the use of geometries specified manually by an expert, geometries derived automatically from corpus statistics, and geometries computed from linguistic resources.
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an acoustic encoder renders the language model from ground-truth sequences in an auto-regressive manner during training. However, the training corpus of the decoder is limited to the speech transcriptions, which is far less than the corpus needed to train an acceptable language model. This leads to poor robustness of decoder. To alleviate this problem, we propose…
This paper describes BACON, a basic prototype of an automatic poetry generator with author linguistic style transfer. It combines concepts and techniques from finite state machinery, probabilistic models, artificial neural networks and deep learning, to write original poetry with rich aesthetic-qualities in the style of any given author. Extrinsic evaluation of the output generated by BACON shows that participants were unable to tell the difference between human and AI-generated poems in any statistically significant way.
We present an unsupervised end-to-end training scheme where we discover discrete subword units from speech without using any labels. The discrete subword units are learned under an ASR-TTS autoencoder reconstruction setting, where an ASR-Encoder is trained to discover a set of common linguistic units given a variety of speakers, and a TTS-Decoder trained to project the discovered units back to the designated speech. We propose a discrete encoding method, Multilabel-Binary Vectors (MBV), to make the ASR-TTS autoencoder differentiable. We found that the proposed encoding method offers automatic …
It is reasonable to hypothesize that the divergence patterns formulated by historical linguists and typologists reflect constraints on human languages, and are thus consistent with Second Language Acquisition (SLA) in a certain way. In this paper, we validate this hypothesis on ten Indo-European languages. We formalize the delexicalized transfer as interpretable tree-to-string and tree-to-tree patterns which can be automatically induced from web data by applying neural syntactic parsing and grammar induction technologies. This allows us to quantitatively probe cross-linguistic transfer and ext…
We present a method of automatic translation (French/English) of Complex Lexical Units (CLU) for aiming at extracting a bilingual lexicon. Our modular system is based on linguistic properties (compositionality, polysemy, etc.). Different aspects of the multilingual Web are used to validate candidate translations and collect new terms. We first build a French corpus of Web pages to collect CLU. Three adapted processing stages are applied for each linguistic property : compositional and non polysemous translations, compositional polysemous translations and non compositional translations. Our eva…
National University（国立大学）；De La Salle University（德拉萨大学）
In order to ensure quality and effective learning, fluency, and comprehension, the proper identification of the difficulty levels of reading materials should be observed. In this paper, we describe the development of automatic machine learning-based readability assessment models for educational Filipino texts using the most diverse set of linguistic features for the language. Results show that using a Random Forest model obtained a high performance of 62.7% in terms of accuracy, and 66.1% when using the optimal combination of feature sets consisting of traditional and syllable pattern-based pr…
Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve higher steganalysis effects. However, we have found through experiments that there actually exists significant difference between automatically generated stego texts and carrier texts in terms of the conditional probability distribution of individual words. Such kind of difference can be naturally captured by the language model used for generating stego texts. Th…
National and Kapodistrian University of Athens（雅典国立与卡波迪斯特里亚大学）
One of the major challenges that NLP faces is metaphor detection, especially by automatic means, a task that becomes even more difficult for languages lacking in linguistic resources and tools. Our purpose is the automatic differentiation between literal and metaphorical meaning in authentic non-annotated phrases from the Corpus of Greek Texts by means of computational methods of machine learning. For this purpose the theoretical background of distributional semantics is discussed and employed. Distributional Semantics Theory develops concepts and methods for the quantification and classificat…
Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models. More recent methods have improved performance by discarding these features and utilizing deep learning models. However, it is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. This paper combines these two approaches with the goal of improving overall model performance and addressing th…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Automatic evaluation metrics are indispensable for evaluating generated text. To date, these metrics have focused almost exclusively on the content selection aspect of the system output, ignoring the linguistic quality aspect altogether. We bridge this gap by proposing GRUEN for evaluating Grammaticality, non-Redundancy, focUs, structure and coherENce of generated text. GRUEN utilizes a BERT-based model and a class of syntactic, semantic, and contextual features to examine the system output. Unlike most existing evaluation metrics which require human references as an input, GRUEN is reference-…
University of Augsburg（奥格斯堡大学）；audEERING GmbH（audEERING有限公司）；Imperial College（帝国理工学院）
Large, pre-trained neural networks consisting of self-attention layers (transformers) have recently achieved state-of-the-art results on several speech emotion recognition (SER) datasets. These models are typically pre-trained in self-supervised manner with the goal to improve automatic speech recognition performance -- and thus, to understand linguistic information. In this work, we investigate the extent in which this information is exploited during SER fine-tuning. Using a reproducible methodology based on open-source tools, we synthesise prosodically neutral speech utterances while varying…
Google UK（谷歌英国）；University of West Bohemia（西波西米亚大学）
The prosodic aspects of speech signals produced by current text-to-speech systems are typically averaged over training material, and as such lack the variety and liveliness found in natural speech. To avoid monotony and averaged prosody contours, it is desirable to have a way of modeling the variation in the prosodic aspects of speech, so audio signals can be synthesized in multiple ways for a given text. We present a new, hierarchically structured conditional variational autoencoder to generate prosodic features (fundamental frequency, energy and duration) suitable for use with a vocoder or a…
We introduce The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP), a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars, and aggregate human agreement with the labels is 96.4%. We use it to evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs. We find that state-of-the-art models identify morphological cont…
Medical University of Vienna（维也纳医科大学）；Graz University of Technology（格拉茨工业大学）；Complexity Science Hub Vienna（维也纳复杂性科学中心）
Recent approaches to text analysis from social media and other corpora rely on word lists to detect topics, measure meaning, or to select relevant documents. These lists are often generated by applying computational lexicon expansion methods to small, manually-curated sets of root words. Despite the wide use of this approach, we still lack an exhaustive comparative analysis of the performance of lexicon expansion methods and how they can be improved with additional linguistic data. In this work, we present LEXpander, a method for lexicon expansion that leverages novel data on colexification, i…
Multimedia Communications Lab, Technical University of Darmstadt（达姆施塔特工业大学多媒体通信实验室）
Most learners fail to develop deep text comprehension when reading textbooks passively. Posing questions about what learners have read is a well-established way of fostering their text comprehension. However, many textbooks lack self-assessment questions because authoring them is timeconsuming and expensive. Automatic question generators may alleviate this scarcity by generating sound pedagogical questions. However, generating questions automatically poses linguistic and pedagogical challenges. What should we ask? And, how do we phrase the question automatically? We address those challenges wi…
Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition-Informed Approach to Quantifying Identity Fusion from Text
Center for Complex Networks and Systems Research, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington（复杂网络与系统研究中心，信息学、计算与工程学院，印第安纳大学布卢明顿分校）；Cognitive Science Program, Indiana University Bloomington（认知科学项目，印第安纳大学布卢明顿分校）；School of Data Science, University of Virginia（数据科学学院，弗吉尼亚大学）；CulturePulse, Inc.（CulturePulse公司）
This paper addresses the task of user gender classification in social media, with an application to Twitter. The approach automatically predicts gender by leveraging observable information such as the tweet behavior, linguistic content of the user's Twitter feed and the celebrities followed by the user. This paper first evaluates linguistic content based features using LIWC dictionary and popular neighborhood features using Wikipedia and Freebase. Then augments both features which yielded a significant increase in the accuracy for gender prediction. Results show that rich linguistic features c…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic pre-training has already shown its amazing ASR performance, while the transcription is still inadequate for language modeling in end-to-end models. In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. The fused model only needs to learn the transfer from speech to language during fin…
