Stroke order and velocity are helpful features in the fields of signature verification, handwriting recognition, and handwriting synthesis. Recovering these features from offline handwritten text is a challenging and well-studied problem. We propose a new model called TRACE (Trajectory Recovery by an Adaptively-trained Convolutional Encoder). TRACE is a differentiable approach that uses a convolutional recurrent neural network (CRNN) to infer temporal stroke information from long lines of offline handwritten text with many characters and dynamic time warping (DTW) to align predictions and ground truth points. TRACE is perhaps the first system to be trained end-to-end on entire lines of text of arbitrary width and does not require the use of dynamic exemplars. Moreover, the system does not require images to undergo any pre-processing, nor do the predictions require any post-processing. Consequently, the recovered trajectory is differentiable and can be used as a loss function for other tasks, including synthesizing offline handwritten text. We demonstrate that temporal stroke information recovered by TRACE from offline data can be used for handwriting synthesis and establish the first benchmarks for a stroke trajectory recovery system trained on the IAM online handwriting dataset.
Numerous events occur worldwide and are documented in the news, social media, and various online platforms in raw text. Extracting useful and succinct information about these events is crucial to various downstream applications. Event Argument Extraction (EAE) deals with the task of extracting event-specific information from natural language text. In order to cater to new events and domains in a realistic low-data setting, there is a growing urgency for EAE models to be generalizable. Consequentially, there is a necessity for benchmarking setups to evaluate the generalizability of EAE models. But most existing benchmarking datasets like ACE and ERE have limited coverage in terms of events and cannot adequately evaluate the generalizability of EAE models. To alleviate this issue, we introduce a new dataset GENEVA covering a diverse range of 115 events and 187 argument roles. Using this dataset, we create four benchmarking test suites to assess the model's generalization capability from different perspectives. We benchmark various representative models on these test suites and compare their generalizability relatively. Finally, we propose a new model SCAD that outperforms the previous models and serves as a strong benchmark for these test suites.
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently designed to incorporate useful external information. Grounded generation models appear to offer remedies, but their training typically relies on rarely-available parallel data where corresponding documents are provided for context. We propose a framework that alleviates this data constraint by jointly training a grounded generator and document retriever on the language model signal. The model learns to retrieve the documents with the highest utility in generation and attentively combines them in the output. We demonstrate that by taking advantage of external references our approach can produce more informative and interesting text in both prose and dialogue generation.
Hate speech is a form of online harassment that involves the use of abusive language, and it is commonly seen in social media posts. This sort of harassment mainly focuses on specific group characteristics such as religion, gender, ethnicity, etc and it has both societal and economic consequences nowadays. The automatic detection of abusive language in text postings has always been a difficult task, but it is lately receiving much interest from the scientific community. This paper addresses the important problem of discerning hateful content in social media. The model we propose in this work is an extension of an existing approach based on LSTM neural network architectures, which we appropriately enhanced and fine-tuned to detect certain forms of hatred language, such as racism or sexism, in a short text. The most significant enhancement is the conversion to a two-stage scheme consisting of Recurrent Neural Network (RNN) classifiers. The output of all One-vs-Rest (OvR) classifiers from the first stage are combined and used to train the second stage classifier, which finally determines the type of harassment. Our study includes a performance comparison of several proposed alternative methods for the second stage evaluated on a public corpus of 16k tweets, followed by a generalization study on another dataset. The reported results show the superior classification quality of the proposed scheme in the task of hate speech detection as compared to the current state-of-the-art.
Modern speech synthesis techniques can produce natural-sounding speech given sufficient high-quality data and compute resources. However, such data is not readily available for many languages. This paper focuses on speech synthesis for low-resourced African languages, from corpus creation to sharing and deploying the Text-to-Speech (TTS) systems. We first create a set of general-purpose instructions on building speech synthesis systems with minimum technological resources and subject-matter expertise. Next, we create new datasets and curate datasets from "found" data (existing recordings) through a participatory approach while considering accessibility, quality, and breadth. We demonstrate that we can develop synthesizers that generate intelligible speech with 25 minutes of created speech, even when recorded in suboptimal environments. Finally, we release the speech data, code, and trained voices for 12 African languages to support researchers and developers.
As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true capabilities. For a more informative evaluation than accuracy on text classification tasks can offer, we propose evaluating systems through a novel measure of prediction coherence. We apply our framework to two existing language understanding benchmarks with different properties to demonstrate its versatility. Our experimental results show that this evaluation framework, although simple in ideas and implementation, is a quick, effective, and versatile measure to provide insight into the coherence of machines' predictions.
Emotion recognition is involved in several real-world applications. With an increase in available modalities, automatic understanding of emotions is being performed more accurately. The success in Multimodal Emotion Recognition (MER), primarily relies on the supervised learning paradigm. However, data annotation is expensive, time-consuming, and as emotion expression and perception depends on several factors (e.g., age, gender, culture) obtaining labels with a high reliability is hard. Motivated by these, we focus on unsupervised feature learning for MER. We consider discrete emotions, and as modalities text, audio and vision are used. Our method, as being based on contrastive loss between pairwise modalities, is the first attempt in MER literature. Our end-to-end feature learning approach has several differences (and advantages) compared to existing MER methods: i) it is unsupervised, so the learning is lack of data labelling cost; ii) it does not require data spatial augmentation, modality alignment, large number of batch size or epochs; iii) it applies data fusion only at inference; and iv) it does not require backbones pre-trained on emotion recognition task. The experiments on benchmark datasets show that our method outperforms several baseline approaches and unsupervised learning methods applied in MER. Particularly, it even surpasses a few supervised MER state-of-the-art.
Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant gains across different NLP tasks. However, their applicability to data augmentation for text classification tasks in few-shot settings have not been fully explored, especially for specialised domains. In this paper, we leverage GPT-2 (Radford A et al, 2019) for generating artificial training instances in order to improve classification performance. Our aim is to analyse the impact the selection process of seed training examples have over the quality of GPT-generated samples and consequently the classifier performance. We perform experiments with several seed selection strategies that, among others, exploit class hierarchical structures and domain expert selection. Our results show that fine-tuning GPT-2 in a handful of label instances leads to consistent classification improvements and outperform competitive baselines. Finally, we show that guiding this process through domain expert selection can lead to further improvements, which opens up interesting research avenues for combining generative models and active learning.
We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A PreQuEL system predicts how well a given sentence will be translated, without recourse to the actual translation, thus eschewing unnecessary resource allocation when translation quality is bound to be low. PreQuEL can be defined relative to a given MT system (e.g., some industry service) or generally relative to the state-of-the-art. From a theoretical perspective, PreQuEL places the focus on the source text, tracing properties, possibly linguistic features, that make a sentence harder to machine translate. We develop a baseline model for the task and analyze its performance. We also develop a data augmentation method (from parallel corpora), that improves results substantially. We show that this augmentation method can improve the performance of the Quality-Estimation task as well. We investigate the properties of the input text that our model is sensitive to, by testing it on challenge sets and different languages. We conclude that it is aware of syntactic and semantic distinctions, and correlates and even over-emphasizes the importance of standard NLP features.
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.