Synthetic Data

We present a nonparametric Bayesian model of tree structures based on the hierarchical Dirichlet process (HDP). Our HDP-PCFG model allows the complexity of the grammar to grow as more training …...

We propose an algorithm to find the best path through an intersection of arbitrarily many weighted automata, without actually perform- ing the intersection. The algorithm is based on dual decomposition: …...

To overcome the shortage of labeled data for implicit discourse relation recogni- tion, previous works attempted to auto- matically generate training data by remov- ing explicit discourse connectives from sentences …...

Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models. This paper introduces two probabilistic topic models, Correlated LDA …...

This paper describes the neural and phrase-based machine translation systems submitted by CUNI to English-Czech News Translation Task of WMT17. We experiment with synthetic data for training and try several …...

AbstractIn this paper, we introduce a novel approach to generate synthetic data for training Neural Machine Translation systems. The proposed approach supports language variants and dialects with very limited parallel …...

AbstractImplicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. …...

AbstractIn this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign. Basque is a low-resourced, morphologically-rich language. This poses a challenge for …...

AbstractNeural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. …...

AbstractData-driven models have demonstrated state-of-the-art performance in inferring the temporal ordering of events in text. However, these models often overlook explicit temporal signals, such as dates and time windows. Rule-based …...

There is a need for real-time communica- tion between the deaf and hearing with- out the aid of an interpreter. Develop- ing a machine translation (MT) system be- tween sign …...

AbstractIn this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be …...

AbstractBeam search optimization (Wiseman and Rush, 2016) resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, …...

AbstractQuery translation (QT) serves as a critical factor in successful cross-lingual information retrieval (CLIR). Due to the lack of parallel query samples, neural-based QT models are usually optimized with synthetic …...

AbstractThe Surface Realization Shared Tasks of 2018 and 2019 were Natural Language Generation shared tasks with the goal of exploring approaches to surface realization from Universal-Dependency-like trees to surface strings …...

AbstractWe propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches. An NLG …...

AbstractThe paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach …...

AbstractKnowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original …...

AbstractFeature attribution a.k.a. input salience methods which assign an importance score to a feature are abundant but may produce surprisingly different results for the same model on the same input. …...

AbstractWhile there has been substantial progress in text comprehension through simple factoid question answering, more holistic comprehension of a discourse still presents a major challenge (Dunietz et al., 2020). Someone …...

AbstractCurrent approaches for fixing systematic problems in NLP models (e.g., regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide …...

AbstractThis paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks. We propose Prompt-based Data Augmentation model (PromDA) which only trains small-scale Soft Prompt (i.e., a set …...

AbstractIn this work, we take the named entity recognition task in the English language as a case study and explore style transfer as a data augmentation method to increase the …...

AbstractDeep learning models have significantly advanced the state of the art of question answering systems. However, the majority of datasets available for training such models have been annotated by humans, …...

AbstractRecent research shows synthetic data as a source of supervision helps pretrained language models (PLM) transfer learning to new target tasks/domains. However, this idea is less explored for spatial language. …...

AbstractControlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. …...

AbstractIn this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with …...

AbstractAutoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P – that is, minimizing the forward cross-entropy, which is equivalent …...

AbstractThe wide accessibility of social media has provided linguistically under-represented communities with an extraordinary opportunity to create content in their native languages. This, however, comes with certain challenges in script …...

AbstractPrivacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a …...

AbstractThis paper describes the submission of UZH_CLyp for the SemEval 2023 Task 9 “Multilingual Tweet Intimacy Analysis. We achieved second-best results in all 10 languages according to the official Pearson’s …...