Related papers: Zero-Shot Text Matching for Automated Auditing usi…

Machine based text comprehension has always been a significant research field in natural language processing. Once a full understanding of the text context and semantics is achieved, a deep learning model can be trained to solve a large…

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…

Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach…

While relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that cannot be observed at the training…

Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in zero-shot and…

We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on…

Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by…

Conversational agents such as Alexa and Google Assistant constantly need to increase their language understanding capabilities by adding new domains. A massive amount of labeled data is required for training each new domain. While domain…

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…

Turn-level user satisfaction is one of the most important performance metrics for conversational agents. It can be used to monitor the agent's performance and provide insights about defective user experiences. Moreover, a powerful…

For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language similarity in this…

There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs). In this paper, we study a flexible and efficient zero-short learning method, \textsc{ZeroGen}.…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare…

Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neural language models to…

Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the…

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…

Pretrained Masked Language Models (MLMs) have revolutionised NLP in recent years. However, previous work has indicated that off-the-shelf MLMs are not effective as universal lexical or sentence encoders without further task-specific…