近年来，大量研究致力于将神经模型应用于自然语言生成（natural language generation，NLG）领域，核心目标是生成既具备语言自然性、贴近人类表达，同时又能对生成过程加以控制的文本。本文对神经文本生成的最新进展开展了全面且任务无关的综述，这些进展依托多方面的研究突破，我们将其划分为四大核心方向：数据构建、神经框架、训练与推理策略以及评估指标。通过对上述不同维度的梳理，本文旨在呈现该领域研究进展的整体全貌。此外，本文还探讨了神经文本生成发展的未来方向，包括神经流水线的应用以及背景知识的融合，这些方向为进一步提升NLG系统的性能提供了颇具前景的研究路径。总体而言，本综述梳理了神经文本生成领域的当前最优技术水平，并指明了这一动态领域未来研发的潜在方向。
英文摘要：
In recent years, considerable research has been dedicated to the application of neural models in the field of natural language generation (NLG). The primary objective is to generate text that is both linguistically natural and human-like, while also exerting control over the generation process. This paper offers a comprehensive and task-agnostic survey of the recent advancements in neural text generation. These advancements have been facilitated through a multitude of developments, which we categorize into four key areas: data construction, neural frameworks, training and inference strategies, and evaluation metrics. By examining these different aspects, we aim to provide a holistic overview of the progress made in the field. Furthermore, we explore the future directions for the advancement of neural text generation, which encompass the utilization of neural pipelines and the incorporation of background knowledge. These avenues present promising opportunities to further enhance the capabilities of NLG systems. Overall, this survey serves to consolidate the current state of the art in neural text generation and highlights potential avenues for future research and development in this dynamic field.
Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation. In order to progress research in text generation, it is critical to absorb the existing research works and position ourselves in this massively growing field. Specifically, this paper surveys the fundamental components of modeling approaches relaying task agnostic impacts across various generation tasks such as storytelling, summarization, translation etc., In this context, we present an abstraction of the imperative techniques with respect to…
This paper describes the system description for the HinglishEval challenge at INLG 2022. The goal of this task was to investigate the factors influencing the quality of the code-mixed text generation system. The task was divided into two subtasks, quality rating prediction and annotators disagreement prediction of the synthetic Hinglish dataset. We attempted to solve these tasks using sentence-level embeddings, which are obtained from mean pooling the contextualized word embeddings for all input tokens in our text. We experimented with various classifiers on top of the embeddings produced for …
LIP6, Sorbonne Université（索邦大学LIP6实验室）；BNP Paribas（法国巴黎银行）；Criteo AI Lab（科睿唯安人工智能实验室）
In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset divergence (i.e., hallucinations or omissions), and to incorporate them erroneously in their own generations at inference. In this work, we build ontop of previous Reinforcement Learning based approaches and show that a model-agnostic framework relying on the recently introduced PARENT metric is efficient at reducing both hallucinations and omissions. Evaluations on the widely used WikiBIO and WebNLG benchmarks demonstrate the effectivenes…
Concept-to-text Natural Language Generation is the task of expressing an input meaning representation in natural language. Previous approaches in this task have been able to generalise to rare or unseen instances by relying on a delexicalisation of the input. However, this often requires that the input appears verbatim in the output text. This poses challenges in multilingual settings, where the task expands to generate the output text in multiple languages given the same input. In this paper, we explore the application of multilingual models in concept-to-text and propose Language Agnostic De…
We propose an end-to-end neural model for zero-shot abstractive text summarization of paragraphs, and introduce a benchmark task, ROCSumm, based on ROCStories, a subset for which we collected human summaries. In this task, five-sentence stories (paragraphs) are summarized with one sentence, using human summaries only for evaluation. We show results for extractive and human baselines to demonstrate a large abstractive gap in performance. Our model, SummAE, consists of a denoising auto-encoder that embeds sentences and paragraphs in a common space, from which either can be decoded. Summaries for…
This paper investigates how to correct Chinese text errors with types of mistaken, missing and redundant characters, which is common for Chinese native speakers. Most existing models based on detect-correct framework can correct mistaken characters errors, but they cannot deal with missing or redundant characters. The reason is that lengths of sentences before and after correction are not the same, leading to the inconsistence between model inputs and outputs. Although the Seq2Seq-based or sequence tagging methods provide solutions to the problem and achieved relatively good results on English…
With the emergence of automatic speech recognition (ASR) models, converting the spoken form text (from ASR) to the written form is in urgent need. This inverse text normalization (ITN) problem attracts the attention of researchers from various fields. Recently, several works show that data-driven ITN methods can output high-quality written form text. Due to the scarcity of labeled spoken-written datasets, the studies on non-English data-driven ITN are quite limited. In this work, we propose a language-agnostic data-driven ITN framework to fill this gap. Specifically, we leverage the data augme…
In recent years, creating and managing knowledge bases have become crucial to the retail product and enterprise domains. We present an automatic knowledge base construction system that mines data from documents. This system can generate training data during the training process without human intervention. Therefore, it is domain-agnostic trainable using only the target domain text corpus and a pre-defined knowledge base. This system is called OASYS and is the first system built with the Korean language in mind. In addition, we also have constructed a new human-annotated benchmark dataset of th…
Legend at ArAIEval Shared Task: Persuasion Technique Detection using a Language-Agnostic Text Representation Model
Instituto Politécnico Nacional（国立理工学院）；Montclair State University（蒙特克莱尔州立大学）；Caritas University（明爱大学）；Lead City University（利德城市大学）；Federal University Oye-Ekiti（奥耶埃基蒂联邦大学）
Institute for Natural Language Processing（自然语言处理研究所）；University of Stuttgart（斯图加特大学）
While neural text-to-speech systems perform remarkably well in high-resource scenarios, they cannot be applied to the majority of the over 6,000 spoken languages in the world due to a lack of appropriate training data. In this work, we use embeddings derived from articulatory vectors rather than embeddings derived from phoneme identities to learn phoneme representations that hold across languages. In conjunction with language agnostic meta learning, this enables us to fine-tune a high-quality text-to-speech model on just 30 minutes of data in a previously unseen language spoken by a previously…
We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or uninterpretable questions and that such errors can be ameliorated by providing summarized input. We find that giving these models human-written summaries instead of the original text results in a significant increase in acceptability of generated questions (33% $\rightarrow$ 83%) as determined by expert annotators. We also find that, in the absence of human-written summaries, automa…
SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心（DFKI GmbH））；Saarland Informatics Campus（萨尔兰信息技术校区）；Barcelona Supercomputing Center (BSC-CNS)（巴塞罗那超级计算中心（BSC-CNS））
Image retrieval with natural language feedback offers the promise of catalog search based on fine-grained visual features that go beyond objects and binary attributes, facilitating real-world applications such as e-commerce. Our Modality-Agnostic Attention Fusion (MAAF) model combines image and text features and outperforms existing approaches on two visual search with modifying phrase datasets, Fashion IQ and CSS, and performs competitively on a dataset with only single-word modifications, Fashion200k. We also introduce two new challenging benchmarks adapted from Birds-to-Words and Spot-the-D…
The Entity Disambiguation and Linking (EDL) task matches entity mentions in text to a unique Knowledge Base (KB) identifier such as a Wikipedia or Freebase id. It plays a critical role in the construction of a high quality information network, and can be further leveraged for a variety of information retrieval and NLP tasks such as text categorization and document tagging. EDL is a complex and challenging problem due to ambiguity of the mentions and real world text being multi-lingual. Moreover, EDL systems need to have high throughput and should be lightweight in order to scale to large datas…
Self-supervised learning algorithms, including BERT and SimCLR, have enabled significant strides in fields like natural language processing, computer vision, and speech processing. However, these algorithms are domain-specific, meaning that new self-supervised learning algorithms must be developed for each new setting, including myriad healthcare, scientific, and multimodal domains. To catalyze progress toward domain-agnostic methods, we introduce DABS: a Domain-Agnostic Benchmark for Self-supervised learning. To perform well on DABS, an algorithm is evaluated on seven diverse domains: natural…
Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）
A complex nature of big data resources demands new methods for structuring especially for textual content. WordNet is a good knowledge source for comprehensive abstraction of natural language as its good implementations exist for many languages. Since WordNet embeds natural language in the form of a complex network, a transformation mechanism WordNet2Vec is proposed in the paper. It creates vectors for each word from WordNet. These vectors encapsulate general position - role of a given word towards all other words in the natural language. Any list or set of such vectors contains knowledge abou…
A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
Northeastern University（东北大学）；Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Institute of Informatics, LMU Munich（慕尼黑大学信息学研究所）
End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Automatic Speech Recognition (ASR) and text Machine Translation (MT) models. However, collecting large amounts of parallel data for ST task is more difficult compared to the ASR and MT tasks. Previous studies have proposed the use of transfer learning approaches to overcome the above difficulty. These approaches benefit from weakly supervised training data, such as ASR speech-to-transcript or MT text-to-text translation…
University of Bern（伯尔尼大学）；University of Zurich（苏黎世大学）；University of Koblenz-Landau（科布伦茨-兰道大学）；University Carlos III of Madrid（马德里卡洛斯三世大学）
The growing availability of data about online information behaviour enables new possibilities for political communication research. However, the volume and variety of these data makes them difficult to analyse and prompts the need for developing automated content approaches relying on a broad range of natural language processing techniques (e.g. machine learning- or neural network-based ones). In this paper, we discuss how these techniques can be used to detect political content across different platforms. Using three validation datasets, which include a variety of political and non-political …
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder that requires both modalities, limiting their use for retrieval-style end tasks or more complex multitask learning with two unimodal encoders, limiting early cross-modal fusion. We instead introduce new pretraining masking schemes that better mix across modalities (e.g. by forcing masks for text to predict the closest video embeddings) while also maintainin…
Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks. However it is an open-question how to use similar techniques for language generation. Early results in the encoder-agnostic setting have been mostly negative. In this work we explore methods for adapting a pretrained language model to arbitrary conditional input. We observe that pretrained transformer models are sensitive to large parameter changes during tuning. We th…
Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal
1 Synchromedia Laboratory, \' E cole de Technologie Sup\' e rieure (\' E TS), 1100 Notre-Dame St W, Montreal, QC H3C 1K3, Canada；2 Department of Computer Science, University of Bari Aldo Moro, Via Orabona 4, 70125 Bari, Italy
Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced but much more under-resourced) natural languages and text genres (e.g., product reviews, tweets, news). The resulting heterogeneity makes data and software developed under these conflicting constraints hard to compare and challenging to integrate. To resolve this unsatisfactory state of affairs we here propose a training scheme that learns a shared latent repr…
University of Toronto（多伦多大学）；Vector Institute（向量研究院）；St Michael’s Hospital（圣迈克尔医院）
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the discrete nature of text, during training, using word embeddings. Our method is agnostic to vocabulary size and achieves competitive results relative to methods with various discrete gradient estimators.
EPFL（洛桑联邦理工学院）；AXA（安盛集团）；Inria（法国国家信息与自动化研究所）；Sorbonne Université（索邦大学）；Polish Academy of Science（波兰科学院）
Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using complex BERT-based classifiers: The word-based sampling produces texts that are out-of-distribution for the classifier and further gives rise to a high-dimensional search space, which can't be sufficiently explored when time or computation power is limited. Both of these challenges can be addressed by using segments as elementary building blocks for NLP interpre…
University of Maryland（马里兰大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability. Unlike images on which a single fixed-size adversarial perturbation can be found, text is of variable length, so we define the "universality" as "token-agnostic", where a single perturbation is applied to each token, resulting in different perturbations of flexible sizes at the sequence level. We propose an algorithm to compute universal adversarial perturbations, and sh…
University of Stuttgart（斯图加特大学）；Institut für Maschinelle Sprachverarbeitung（机器语言处理研究所）
Appraisal theories explain how the cognitive evaluation of an event leads to a particular emotion. In contrast to theories of basic emotions or affect (valence/arousal), this theory has not received a lot of attention in natural language processing. Yet, in psychology it has been proven powerful: Smith and Ellsworth (1985) showed that the appraisal dimensions attention, certainty, anticipated effort, pleasantness, responsibility/control and situational control discriminate between (at least) 15 emotion classes. We study different annotation strategies for these dimensions, based on the event-f…
Recently, deep learning based natural language processing techniques are being extensively used to deal with spam mail, censorship evaluation in social networks, among others. However, there is only a couple of works evaluating the vulnerabilities of such deep neural networks. Here, we go beyond attacks to investigate, for the first time, universal rules, i.e., rules that are sample agnostic and therefore could turn any text sample in an adversarial one. In fact, the universal rules do not use any information from the method itself (no information from the method, gradient information or train…
