Source A Survey of Large Language Models
Simple definition: Language Modeling is the task of predicting what word comes next.
"The dog is playing in the ..."
The main purpose of Language Models is to assign a probability to a sentence, to distinguish between the more likely and the less likely sentences.
For Speech Recognition, we use not only the acoustics model (the speech signal), but also a language model. Similarly, for Optical Character Recognition (OCR), we use both a vision model and a language model. Language models are very important for such recognition systems.
Sometimes, you hear or read a sentence that is not clear, but using your language model, you still can recognize it at a high accuracy despite the noisy vision/speech input.
The language model computes either of:
Language Modeling is a subcomponent of many NLP tasks, especially those involving generating text or estimating the probability of text.
The Chain Rule: $P(x_1, x_2, x_3, …, x_n) = P(x_1)P(x_2|x_1)P(x_3|x_1,x_2)…P(x_n|x_1,…,x_{n-1})$
$P(The, water, is, so, clear) = P(The) × P(water|The) × P(is|The, water) × P(so|The, water, is) × P(clear | The, water, is, so)$
What just happened? The Chain Rule is applied to compute the joint probability of words in a sentence.
Using a large amount of text (corpus such as Wikipedia), we collect statistics about how frequently different words are, and use these to predict the next word. For example, the probability that a word w comes after these three words students opened their can be estimated as follows:
The above example is a 4-gram model. And we may get:
We can conclude that the word “books” is more probable than “cars” in this context.
We ignored the previous context before "students opened their"
Accordingly, arbitrary text can be generated from a language model given starting word(s), by sampling from the output probability distribution of the next word, and so on.
We can train an LM on any kind of text, then generate text in that style (Harry Potter, etc.).
<!-- ### How to estimate these probabilities? Amusing we have a large text corpus (data set like Wikipedia), we can count and divide as follows: - $P(clear |The, water, is, so) = Count (The, water, is, so, clear) / Count (The, water, is, so)$ --> <!-- Sparsity: Sometimes we do not have enough data to estimate the following: - $P(clear |The, water, is, so) = Count (The, water, is, so, clear) / Count (The, water, is, so)$ Markov Assumption (Simplifying assumption): - $P(clear |The, water, is, so) ≈ P(clear | so)$ - Or $P(clear |The, water, is, so) ≈ P(clear | is, so)$ Formally: - $P(w_1 w_2 … w_n ) ≈ ∏i P(w_i | w_{i−k} … w_{i−1})$ - $P(w_i | w_1 w_2 … w_{i−1}) ≈ P(w_i | w_{i−k} … w_{i−1})$ - Unigram model: $P(w_1 w_2 … w_n ) ≈ ∏i P(w_i)$ - Bigram model: $P(w_i | w_1 w_2 … w{i−1}) ≈ P(w_i | w_{i−1})$ -->We can extend to trigrams, 4-grams, 5-grams, and N-grams.
In general, this is an insufficient model of language because the language has long-distance dependencies. However, in practice, these 3,4 grams work well for most of the applications.
<!--- ### Estimating bigram probabilities: The Maximum Likelihood Estimate (MLE): of all the times we saw the word wi-1, how many times it was followed by the word wi $P(w_i | w_{i−1}) = count(w_{i−1}, w_i) / count(w_{i−1})$ Practical Issue: We do everything in log space to avoid underflow $log(p1 × p2 × p3 × p4 ) = log p1 + log p2 + log p3 + log p4$ -->Google's N-gram Models Belong to You: Google Research has been using word n-gram models for a variety of R&D projects. Google N-Gram processed 1,024,908,267,229 words of running text and published the counts for all 1,176,470,663 five-word sequences that appear at least 40 times.
The counts of text from the Linguistics Data Consortium LDC are as follows:
File sizes: approx. 24 GB compressed (gzip'ed) text files
Number of tokens: 1,024,908,267,229
Number of sentences: 95,119,665,584
Number of unigrams: 13,588,391
Number of bigrams: 314,843,401
Number of trigrams: 977,069,902
Number of fourgrams: 1,313,818,354
Number of fivegrams: 1,176,470,663
The following is an example of the 4-gram data in this corpus:
serve as the incoming 92
serve as the incubator 99
serve as the independent 794
serve as the index 223
serve as the indication 72
serve as the indicator 120
serve as the indicators 45
serve as the indispensable 111
serve as the indispensible 40
For example, the sequence of the four words "serve as the indication" has been seen in the corpus 72 times.
<!--- Try some examples of your own using [Google Books Ngram Viewer](https://books.google.com/ngrams/) and see the frequency of likely and unlikely N-grams.  -->Sometimes we do not have enough data to estimate. Increasing n makes sparsity problems worse. Typically we can’t have n bigger than 5.
NLM usually (but not always) uses an RNN to learn sequences of words (sentences, paragraphs, … etc) and hence can predict the next word.
Advantages:
As depicted, At each step, we have a probability distribution of the next word over the vocabulary.
Training an NLM:
Example of long sequence learning:
Disadvantages:
LM can be used to generate text conditions on input (speech, image (OCR), text, etc.) across different applications such as: speech recognition, machine translation, summarization, etc.
Does our language model prefer good (likely) sentences to bad ones?
The standard evaluation metric for Language Models is perplexity Perplexity is the inverse probability of the test set, normalized by the number of words
Lower perplexity = Better model
Perplexity is related to branch factor: On average, how many things could occur next.
Instead of RNN, let's use attention Let's use large pre-trained models
What is the problem? One of the biggest challenges in natural language processing (NLP) is the shortage of training data for many distinct tasks. However, modern deep learning-based NLP models improve when trained on millions, or billions, of annotated training examples.
Pre-training is the solution: To help close this gap, a variety of techniques have been developed for training general-purpose language representation models using the enormous amount of unannotated text. The pre-trained model can then be fine-tuned on small data for different tasks like question answering and sentiment analysis, resulting in substantial accuracy improvements compared to training on these datasets from scratch.
The Transformer architecture was proposed in the paper Attention is All You Need, used for the Neural Machine Translation task (NMT), consisting of:
As mentioned in the paper:
"We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely"
The main idea of attention can be summarized as mentioned in the OpenAi's article:
"... every output element is connected to every input element, and the weightings between them are dynamically calculated based upon the circumstances, a process called attention."
Based on this architecture (the vanilla Transformers!), encoder or decoder components can be used alone to enable massive pre-trained generic models that can be fine-tuned for downstream tasks such as text classification, translation, summarization, question answering, etc. For Example:
These models, BERT and GPT for instance, can be considered as the NLP's ImageNET.
As shown, BERT is deeply bidirectional, OpenAI GPT is unidirectional, and ELMo is shallowly bidirectional.
Pre-trained representations can be:
Contextual Language models can be:
In this part, we are going to use different large language models
GPT2 (a successor to GPT) is a pre-trained model on English language using a causal language modeling (CLM) objective, trained simply to predict the next
字节跳动发布的AI编程神器IDE
Trae是一种自适应的集成开发环境(IDE),通过自动化和多元协作改变开发流程。利用Trae,团队能够更快速、精确地编写和部署代码,从 而提高编程效率和项目交付速度。Trae具备上下文感知和代码自动完成功能,是提升开发效率的理想工具。
全能AI智能助手,随时解答生活与工作的多样问题
问小白,由元石科技研发的AI智能助手,快速准确地解答各种生活和工作问题,包括但不限于搜索、规划和社交互动,帮助用户在日常生活中提高效率,轻松管理个人事务。
实时语音翻译/同声传译工具
Transly是一个多场景的AI大语言模型驱动的同声传译、专业翻译助手,它拥有超精准的音频识别翻译能力,几乎零延迟的使用体验和支持多国语言可以让你带它走遍全球,无论你是留学生、商务人士 、韩剧美剧爱好者,还是出国游玩、多国会议、跨国追星等等,都可以满足你所有需要同传的场景需求,线上线下通用,扫除语言障碍,让全世界的语言交流不再有国界。
一键生成PPT和Word,让学习生活更轻松
讯飞智文是一个利用 AI 技术的项目,能够帮助用户生成 PPT 以及各类文档。无论是商业领域的市场分析报告、年度目标制定,还是学生群体的职业生涯规划、实习避坑指南,亦或是活动策划、旅游攻略等内容,它都能提供支持,帮助用户精准表达,轻松呈现各种信息。
深度推理能力全新升级,全面对标OpenAI o1
科大讯飞的星火大模型,支持语言理解、知识问答和文本创作等多功能,适用于多种文件和业务场景,提升办公和日常生活的效率。讯飞星火是一 个提供丰富智能服务的平台,涵盖科技资讯、图像创作、写作辅助、编程解答、科研文献解读等功能,能为不同需求的用户提供便捷高效的帮助,助力用户轻松获取信息、解决问题,满足多样化使用场景。
一种基于大语言模型的高效单流解耦语音令牌文本到语音合成模型
Spark-TTS 是一个基于 PyTorch 的开源文本到语音合成项目,由多个知名机构联合参与。该项目提供了高效的 LLM(大语言模型)驱动的语音合成方案,支持语音克隆和语音创建功能,可通过命令行界面(CLI)和 Web UI 两种方式使用。用户可以根据需求调整语音的性别、音高、速度等参数,生成高质量的语音。该项目适用于多种场景,如有声读物制作、智能语音助手开发等。
AI助力,做PPT更简单!
咔片是一款轻量化在线演示设计工具,借助 AI 技术,实现从内容生成到智能设计的一站式 PPT 制作服务。支持多种文档格式导入生成 PPT,提供海量模板、智能美化、素材替换等功能,适用于销售、教师、学生等各类人群,能高效制作出高品质 PPT,满足不同场景演示需求。
选题、配图、成文,一站式创作,让内容运营更高效
讯飞绘文,一个AI集成平台,支持写作、选题、配图、排版和发布。高效生成适用于各类媒体的定制内容,加速品牌传播,提升内容营销效果。
专业的AI公文写作平台,公文写作神器
AI 材料星,专业的 AI 公文写作辅助平台,为体制内工作人员提供高效的公文写作解决方案。拥有海量公文文库、9 大核心 AI 功能,支持 30 + 文稿类型生成,助力快速完成领导讲话、工作总结、述职报告等材料,提升办公效率 ,是体制打工人的得力写作神器。
OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。
openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。