Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains creating a need to adapt to new domains with small memory and deployment overhead. In this work, we introduce domain-prompts, a methodology that involves training a small number of domain embedding parameters to prime a Transformer-based Language Model (LM) to a particular domain. Using this domain-adapted LM for rescoring ASR hypotheses can achieve 7-13% WER reduction for a new domain with just 1000 unlabeled textual domain-specific sentences. This improvement is comparable or even better than fully fine-tuned models even though just 0.02% of the parameters of the base LM are updated. Additionally, our method is deployment-friendly as the learnt domain embeddings are prefixed to the input to the model rather than changing the base model architecture. Therefore, our method is an ideal choice for on-the-fly adaptation of LMs used in ASR systems to progressively scale it to new domains.

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks. DSE learns from dialogues by taking consecutive utterances of the same dialogue as positive pairs for contrastive learning. Despite its simplicity, DSE achieves significantly better representation capability than other dialogue representation and universal sentence representation models. We evaluate DSE on five downstream dialogue tasks that examine dialogue representation at different semantic granularities. Experiments in few-shot and zero-shot settings show that DSE outperforms baselines by a large margin. For example, it achieves 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets. We also provide analyses on the benefits and limitations of our model.

IN EARLY June, a Google engineer named Blake Lemoine dropped a bombshell. He told Washington Post reporter Nitasha Tiku that his employer had secretly developed a sentient artificial intelligence, and that it wanted to be free. The AI in question is called LaMDA (Language Model for Dialogue Applications). It is a large language model, or LLM, a type of algorithm that chats with people by drawing on a huge body of text – often from the internet – and predicting which words and phrases are most likely to follow each other.

This article is part of our coverage of the latest in AI research. Even before the recent craze about sentient chatbots, large language models (LLM) had been the source of much excitement and concern. In recent years, LLMs, deep learning models that have been trained on vast amounts of text, have shown remarkable performance on several benchmarks that are meant to measure language understanding. Large language models such as GPT-3 and LaMDA manage to maintain coherence over long stretches of text. They seem to be knowledgeable about different topics.

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. With full access to the data and to the model parameters as they change during every step while training, we can map in detail how the representation of gender develops, what patterns in the dataset drive this, and how the model's internal state relates to the bias in a downstream task (semantic textual similarity). We find that the representation of gender is dynamic and identify different phases during training. Furthermore, we show that gender information is represented increasingly locally in the input embeddings of the model and that, as a consequence, debias-ing these can be effective in reducing the downstream bias. Monitoring the training dynamics, allows us to detect an asymmetry in how the female and male gender are represented in the input embeddings. This is important, as it may cause naive mitigation strategies to introduce new undesirable biases. We discuss the relevance of the findings for mitigation strategies more generally and the prospects of generalizing our methods to larger language models, the Transformer architecture, other languages and other undesirable biases.

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding explicit linguistic knowledge into neural models. This has led many to question the relevance of linguistics for modern natural language processing. In this dissertation, I present several case studies to illustrate how theoretical linguistics and neural language models are still relevant to each other. First, language models are useful to linguists by providing an objective tool to measure semantic distance, which is difficult to do using traditional methods. On the other hand, linguistic theory contributes to language modelling research by providing frameworks and sources of data to probe our language models for specific aspects of language understanding. This thesis contributes three studies that explore different aspects of the syntax-semantics interface in language models. In the first part of my thesis, I apply language models to the problem of word class flexibility. Using mBERT as a source of semantic distance measurements, I present evidence in favour of analyzing word class flexibility as a directional process. In the second part of my thesis, I propose a method to measure surprisal at intermediate layers of language models. My experiments show that sentences containing morphosyntactic anomalies trigger surprisals earlier in language models than semantic and commonsense anomalies. Finally, in the third part of my thesis, I adapt several psycholinguistic studies to show that language models contain knowledge of argument structure constructions. In summary, my thesis develops new connections between natural language processing, linguistic theory, and psycholinguistics to provide fresh perspectives for the interpretation of language models.

Recently, for few-shot or even zero-shot learning, the new paradigm "pre-train, prompt, and predict" has achieved remarkable achievements compared with the "pre-train, fine-tune" paradigm. After the success of prompt-based GPT-3, a series of masked language model (MLM)-based (e.g., BERT, RoBERTa) prompt learning methods became popular and widely used. However, another efficient pre-trained discriminative model, ELECTRA, has probably been neglected. In this paper, we attempt to accomplish several NLP tasks in the zero-shot scenario using a novel our proposed replaced token detection (RTD)-based prompt learning method. Experimental results show that ELECTRA model based on RTD-prompt learning achieves surprisingly state-of-the-art zero-shot performance. Numerically, compared to MLM-RoBERTa-large and MLM-BERT-large, our RTD-ELECTRA-large has an average of about 8.4% and 13.7% improvement on all 15 tasks. Especially on the SST-2 task, our RTD-ELECTRA-large achieves an astonishing 90.1% accuracy without any training data. Overall, compared to the pre-trained masked language models, the pre-trained replaced token detection model performs better in zero-shot learning. The source code is available at: https://github.com/nishiwen1214/RTD-ELECTRA.

Artificial Intelligence and Machine Learning Market SWOT Analysis. AIBrain, Amazon, Anki, CloudMinds, Deepmind, Google, Facebook, IBM, Iris AI, Apple, …

The tech industry's latest artificial intelligence constructs can be pretty convincing if you ask them what it feels like to be a sentient computer, or maybe just a dinosaur or squirrel. Take, for instance, GPT-3, a Microsoft-controlled system that can generate paragraphs of human-like text based on what it's learned from a vast database of digital books and online writings. It's considered one of the most advanced of a new generation of AI algorithms that can converse, generate readable text on demand and even produce novel images and video. Among other things, GPT-3 can write up most any text you ask for -- a cover letter for a zookeeping job, say, or a Shakespearean-style sonnet set on Mars. But when Pomona College professor Gary Smith asked it a simple but nonsensical question about walking upstairs, GPT-3 muffed it.

It covers what Transformers are (Section 3 Transformers and Typical Tasks 3 6), how they are trained (Section 7), what 4 Tokenization: How Text is Represented 4 they're used for (Section 3), their key architectural 5 Architectural Components 4 components (Section 5), tokenization (Section 6 Transformer Architectures 7 4), and a preview of practical considerations 7 Transformer Training and Inference 8 8 Practical Considerations 9 (Section 8) and the most prominent models.