CharBERT: Character-aware Pre-trained Language Model
iFLYTEK Research（科大讯飞研究）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Research Center for Social Computing and Information Retrieval (SCIR)（社会计算与信息检索研究中心（SCIR））；iFLYTEK AI Research (Hebei)（科大讯飞AI研究（河北））；University of Maryland（马里兰大学）
Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into subword units and make the representation incomplete and fragile. In this paper, we propose a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) to tackle these problems. We first construct the contextual word embedding for each token from the sequential character representations, then fuse the representations of characters and the subword representations by a novel heterogeneous interaction module. We also propose a new pre-training task named NLM (Noisy LM) for unsupervised character representation learning. We evaluate our method on question answering, sequence labeling, and text classification tasks, both on the original datasets and adversarial misspelling test sets. The experimental results show that our method can significantly improve the performance and robustness of PLMs simultaneously. Pretrained models, evaluation sets, and code are available at https://github.com/wtma/CharBERT
TempCharBERT: Keystroke Dynamics for Continuous Access Control Based on Pre-trained Language Models
Institut national de la recherche scientifique (INRS-EMT)（国家科学研究院（INRS-EMT））；Université du Québec（魁北克大学）；INRS-UQO Mixed Research Unit on Cybersecurity（INRS-UQO网络安全混合研究单元）；Polytechnique Montréal（蒙特利尔理工学院）；São Paulo State Technological College（圣保罗州立技术学院）
University of Haifa（海法大学）；Braude College of Engineering（布劳德工程学院）；McGovern Institute for Brain Research, MIT（麻省理工学院麦戈文脑科学研究所）
The massive spread of hate speech, hateful content targeted at specific subpopulations, is a problem of critical social importance. Automated methods of hate speech detection typically employ state-of-the-art deep learning (DL)-based text classifiers-large pretrained neural language models of over 100 million parameters, adapting these models to the task of hate speech detection using relevant labeled datasets. Unfortunately, there are only a few public labeled datasets of limited size that are available for this purpose. We make several contributions with high potential for advancing this sta…
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
Institute of Computing and Intelligence（计算与智能研究院）；Harbin Institute of Technology（哈尔滨工业大学）；Shenzhen Loop Area Institute (SLAI)（深圳Loop区研究院）；The Chinese University of Hong Kong（香港中文大学）
Neural machine translation (NMT) systems operate primarily on words (or sub-words), ignoring lower-level patterns of morphology. We present a character-aware decoder designed to capture such patterns when translating into morphologically rich languages. We achieve character-awareness by augmenting both the softmax and embedding layers of an attention-based encoder-decoder model with convolutional neural networks that operate on the spelling of a word. To investigate performance on a wide variety of morphological phenomena, we translate English into 14 typologically diverse target languages usi…
The University of Melbourne（墨尔本大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Derivational morphology is a fundamental and complex characteristic of language. In this paper we propose the new task of predicting the derivational form of a given base-form lemma that is appropriate for a given context. We present an encoder--decoder style neural network to produce a derived form character-by-character, based on its corresponding character-level representation of the base form and the context. We demonstrate that our model is able to generate valid context-sensitive derivations from known base forms, but is less accurate under a lexicon agnostic setting.
Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
Institute of Computing and Intelligence, Harbin Institute of Technology（计算与智能研究所，哈尔滨工业大学）；Shenzhen Loop Area Institute (SLAI)（深圳环城研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Beijing University of Aeronautics and Astronautics（北京航空航天大学）；Baidu Inc.（百度公司）
Syllabification does not seem to improve word-level RNN language modeling quality when compared to character-based segmentation. However, our best syllable-aware language model, achieving performance comparable to the competitive character-aware model, has 18%-33% fewer parameters and is trained 1.2-2.2 times faster.
Renmin University of China（中国人民大学）；Boss Zhipin（BOSS直聘）
Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natural languages. In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process. First, we model the aspect transitions to capture the overall content flow. Then, to generate a sentence, an aspect-aware sketch will be predicted using an aspect-aware decoder. Finally, another decoder fills in the se…
Natural languages are complexly structured entities. They exhibit characterising regularities that can be exploited to link them one another. In this work, I compare two morphological aspects of languages: Written Patterns and Sentence Structure. I show how languages spontaneously group by similarity in both analyses and derive an average language distance. Finally, exploiting Sentence Structure I developed an Artificial Neural Network capable of distinguishing languages suggesting that not only word roots but also grammatical sentence structure is a characterising trait which alone suffice to…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）
Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to i…
An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translation
Leiden University Medical Center（莱顿大学医学中心）；Leiden University（莱顿大学）；ADAPT Research Centre（ADAPT研究中心）；Dublin City University（都柏林城市大学）；Insight Centre for Data Analytics（洞察数据分析中心）
We propose a new character-based text classification framework for non-alphabetic languages, such as Chinese and Japanese. Our framework consists of a variational character encoder (VCE) and character-level text classifier. The VCE is composed of a $β$-variational auto-encoder ($β$-VAE) that learns the proposed glyph-aware disentangled character embedding (GDCE). Since our GDCE provides zero-mean unit-variance character embeddings that are dimensionally independent, it is applicable for our interpretable data augmentation, namely, semantic sub-character augmentation (SSA). In this paper, we ev…
Words in some natural languages can have a composite structure. Elements of this structure include the root (that could also be composite), prefixes and suffixes with which various nuances and relations to other words can be expressed. Thus, in order to build a proper word representation one must take into account its internal structure. From a corpus of texts we extract a set of frequent subwords and from the latter set we select patterns, i.e. subwords which encapsulate information on character $n$-gram regularities. The selection is made using the pattern-based Conditional Random Field mode…
National Institute of Information and Communications Technology (NICT)（日本国立信息与通信技术研究所）
For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone problems. In this study, we propose to use a novel pronunciation-aware unique character encoding for building E2E RNN-T-based Mandarin ASR systems. The proposed encoding is a combination of pronunciation-base syllable and character index (CI). By introducing the CI, the RNN-T model can overcome the homophone problem while utilizing the pronunciation information for …
Columbia University（哥伦比亚大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Carnegie Observatories（卡内基天文台）；University of Southern California（南加州大学）；Sapienza University of Rome（罗马第一大学）；Stanford University（斯坦福大学）；University of California, Berkeley（加州大学伯克利分校）；Haas Business School（哈斯商学院）
Natural language processing models learn word representations based on the distributional hypothesis, which asserts that word context (e.g., co-occurrence) correlates with meaning. We propose that $n$-grams composed of random character sequences, or $garble$, provide a novel context for studying word meaning both within and beyond extant language. In particular, randomly generated character $n$-grams lack meaning but contain primitive information based on the distribution of characters they contain. By studying the embeddings of a large corpus of garble, extant language, and pseudowords using …
Harvard University（哈佛大学）；New York University（纽约大学）
We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a highway network over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language model (RNN-LM). On the English Penn Treebank the model is on par with the existing state-of-the-art despite having 60% fewer parameters. On languages with rich morphology (Arabic, Czech, French, German, Spanish, Russian), the model outperforms word-level/morpheme-level LSTM baselin…
IDLab, Ghent University - imec（根特大学-imec IDLab实验室）
Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us …
University of Siena（锡耶纳大学）；University of Firenze（佛罗伦萨大学）
In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised large corpora, they can be transferred to different tasks with positive effects in terms of performances, especially when only a few supervisions are available. In this work, we further extend this concept, and we present an unsupervised neural architecture that jointly learns word and context embeddings, processing words as sequences of characters. This allows…
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing parsers. We present a simple but highly effective approach for training neural LMs using both lexical and syntactic information, and a novel approach for applying such LMs to unparsed text using sequential Monte Carlo sampling. In experiments on a range of corpora and corpus sizes, we show our approach consistently outperforms standard lexical LMs in charac…
Predicting words and subword units (WSUs) as the output has shown to be effective for the attention-based encoder-decoder (AED) model in end-to-end speech recognition. However, as one input to the decoder recurrent neural network (RNN), each WSU embedding is learned independently through context and acoustic information in a purely data-driven fashion. Little effort has been made to explicitly model the morphological relationships among WSUs. In this work, we propose a novel character-aware (CA) AED model in which each WSU embedding is computed by summarizing the embeddings of its constituent …
We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models. The proposed techniques do not benefit a competitive character-aware model, but some of them improve the performance of syllable- and morpheme-aware models while showing significant reductions in model sizes. We discover a simple hands-on principle: in a multi-layer input embedding model, layers should be tied consecutively bottom-up if reused at output. Our best morpheme-aware model with properly reused weights beats the competitive word-level model by a large margin across multipl…
In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far o…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Southern California（南加州大学）；Shanghai Jiao Tong University（上海交通大学）；Facebook
Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable models without handcrafted features. However, in many cases, it is hard to obtain sufficient annotations to train these models. In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task. Besides word-level knowledge contained in pre-trained word embeddings, character-aware neural l…
Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is to define a metric over a word space that quantifies and sums up the differences between characters in two strings. The state-of-the-art in the area has, surprisingly, not evolved much during the last few decades. The majority of the metrics are based on a simple comparison between character and character distributions without consideration for the context …
