Related papers: Error Detection in Large-Scale Natural Language Un…
High-quality automatic speech recognition (ASR) is essential for virtual assistants (VAs) to work well. However, ASR often performs poorly on VA requests containing named entities. In this work, we start from the observation that many ASR…
Despite speech recognition systems achieving low word error rates on standard benchmarks, they often fail on short, high-stakes utterances in real-world deployments. Here, we study this failure mode in a high-stakes task: the transcription…
State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…
Large Language Models (LLMs) are effective for data augmentation in classification tasks like intent detection. In some cases, they inadvertently produce examples that are ambiguous with regard to untargeted classes. We present DDAIR…
Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density…
Sentiment analysis focuses on identifying the emotional polarity expressed in textual data, typically categorized as positive, negative, or neutral. Hate speech detection, on the other hand, aims to recognize content that incites violence,…
Question Answering (QA) is a task in natural language processing that has seen considerable growth after the advent of transformers. There has been a surge in QA datasets that have been proposed to challenge natural language processing…
This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…
Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder the process of sentiment analysis including the lexical diversity…
Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…
E-commerce voice ordering systems need to recognize multiple product name entities from ordering utterances. Existing voice ordering systems such as Amazon Alexa can capture only a single product name entity. This restrains users from…
This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…
Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…
The development of large language models (LLMs) has successfully transformed knowledge-based systems such as open domain question nswering, which can automatically produce vast amounts of seemingly coherent information. Yet, those models…
While Large Language Models (LLMs) have achieved strong performance on general-purpose language tasks, their deployment in regulated and data-sensitive domains, including insurance, remains limited. Leveraging millions of historical…
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…
Textual data annotation, the process of labeling or tagging text with relevant information, is typically costly, time-consuming, and labor-intensive. While large language models (LLMs) have demonstrated their potential as direct…
Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…
Named entity recognition (NER) is a vital task in spoken language understanding, which aims to identify mentions of named entities in text e.g., from transcribed speech. Existing neural models for NER rely mostly on dedicated word-level…
Background: Cyber-attacks have evolved rapidly in recent years, many individuals and business owners have been affected by cyber-attacks in various ways. Cyber-attacks include various threats such as ransomware, malware, phishing, and…