ai模型

We at Zetane are all about democratizing AI, but getting to the laudable goal of empowering more people within AI innovation requires many steps along the way. One beginner’s step on our journey involves peeling away the abstract nature of AI like the skins of an onion. We peel these layers of abstraction away by presenting fundamental components of machine learning in ways technical and non-technical professionals can appreciate. This will be a repeated theme of ours on the Zetane blog, which we call:

我們在Zetane都是關于民主化AI，但得到授權向AI創新中更多的人值得稱道的目標要求沿途許多步驟。 初學者邁出的第一步包括剝開AI的抽象本質，例如洋蔥皮。 通過以技術人員和非技術人員可以欣賞的方式展示機器學習的基本組成部分，我們將這些抽象層剝離掉了。 這將是Zetane博客上我們主題的重復主題，我們稱之為：

This is what AI looks like.

這就是AI的樣子。

To start us off we present here the Bidirectional Attention Flow model, or BiDAF.

首先，我們在這里介紹雙向注意力流模型或BiDAF 。

At first glance, this model looks to be a practical attempt to understand elements of unstructured text. Its development in 2016 marked a major step forward in Natural Language Processing (NLP) for Question and Answer tasks. That may at first sound straightforward. This basic task, however, has huge implications in business as a tool to automate important tasks like customer support inquiries or common requests for information. It thus comes as no surprise that this model attracts fervent investment and research. Aside from the model’s commercial applications, BiDAF marks an important milestone in opening the doors to a not-too-distant future of appreciable Machine Comprehension. Building on knowledge gained from BiDAF, the machine learning community has since brought forth the superior NLP models of BERT and ELMo.

乍一看，該模型似乎是理解非結構化文本元素的實際嘗試。 它在2016年的發展標志著自然語言處理(NLP)在問答任務方面邁出了重要的一步。 乍一看聽起來很簡單。 但是，此基本任務作為使重要任務(例如客戶支持查詢或常見的信息請求)自動化的工具在業務中具有重大意義。 因此，這種模式吸引了無數的投資和研究也就不足為奇了。 除了該模型的商業應用之外，BiDAF還標志著一個重要的里程碑，它為不久的將來可觀的機器理解打開了大門。 機器學習社區以從BiDAF獲得的知識為基礎，提出了BERT和ELMo的高級NLP模型。

For the time being, let’s take a closer look at BiDAF and some of its complexities, beginning with an image of the full neural network.

目前，讓我們從完整的神經網絡的圖像開始，仔細研究BiDAF及其一些復雜性。

A display of the BiDAF model in Zetane zoomed out to show the extent of the full neural network. It is complex!Zetane中BiDAF模型的顯示被縮小以顯示整個神經網絡的范圍。 這很復雜！

The dimensions of the BiDAF model should grab one’s attention. When viewing the model end-to-end, it is difficult to make out the appreciable complexity of the neural network. Let’s zoom in for a closer look, focusing on the left-side input layers of the network.

BiDAF模型的尺寸應引起人們的注意。 端到端查看模型時，很難確定神經網絡的明顯復雜性。 讓我們放大一下以集中查看網絡的左側輸入層。

SQuAD. The mid-green squares on the far left and far right represent four distinct input layers.的陣容 。 最左側和最右側的中間綠色方塊代表四個不同的輸入層。

The above image shows a typical ‘source’, being text with a jumble of information. Upon querying the basic question ‘What color is the fox?’, the model predicts the best answer is ‘brown’, being spot-on. Of particular interest here are the four input layers of the neural network, represented by the mid-green squares. Machine-learning models often have one input, but the specifics of the question-and-answer task requires a bit more work in terms of structuring and analysing the data as text. Let’s inspect further to better understand why that is the case.

上圖顯示了一個典型的“來源”，即帶有混雜信息的文本。 在詢問基本問題“狐貍是什么顏色？”時，該模型預測最佳答案是“棕色”，即亮點。 這里特別有趣的是神經網絡的四個輸入層，由中間的綠色方塊表示。 機器學習模型通常只有一個輸入，但是問答結構的細節在以文本形式構造和分析數據方面需要更多的工作。 讓我們進一步檢查以更好地理解為什么會這樣。

Left: the first two input layers of BiDAF. Right: the latter two input layers of BiDAF左：BiDAF的前兩個輸入層。 右：BiDAF的后兩個輸入層

The first input layers are the context_char and query_char, being abbreviations for the inputs of character-level representations of the text and the question (“query”). The latter two inputs of contex_word and query_word are where word-level representations of the text and question become incorporated in the analysis by the neural network. This architecture shows there is an initial processing of the text and then a subsequent assessment of the words in order to achieve an appreciable level of language comprehension. Overall, the BiDAF model aims to identify a context and then keywords integral to the context, where the layered design of the neural network makes it easier for the model to tease out the answer keyword from the general context. It’s interesting to note that the model does this by converting all text into math, namely vectors, meaning its ability to understand text has little to do with text per se and is in fact a probability-based prediction of pairing words.

第一個輸入層是context_char和query_char，它們是文本和問題(“查詢”)的字符級表示的輸入的縮寫。 contex_word和query_word的后兩個輸入是文本和問題的單詞級表示形式在神經網絡分析中的合并位置。 此體系結構顯示了對文本的初始處理，然后對單詞進行了后續評估，以實現可理解的語言理解水平。 總體而言，BiDAF模型旨在識別上下文，然后識別上下文中不可或缺的關鍵字，其中神經網絡的分層設計使該模型更容易從通用上下文中挑出答案關鍵字。 有趣的是，該模型通過將所有文本轉換為數學(即向量)來實現此目的，這意味著其理解文本的能力與文本本身無關，實際上是基于概率的配對詞預測。

To conclude our overview of BiDAF we present a short video capture of the model in our environment for machine learning projects. Here is a display of the breakdown and analysis of the vectorized text information as it passes through nodes of the neural network. We intermittently show the internal metrics of the information at the nodes, called tensors. The take-home message here is that whether data is in the form of text, images, video or whatnot, a neural network transforms that information into a universal language of advanced — and arguably aesthetic — statistics.

總結我們對BiDAF的概述，我們將在我們的環境中為機器學習項目展示該模型的簡短視頻。 這是矢量化文本信息通過神經網絡節點時的細目分類和分析的顯示。 我們間歇地顯示節點上信息的內部度量，稱為張量。 這里要傳達的信息是，無論數據是文本，圖像，視頻還是其他形式，神經網絡都會將該信息轉換為高級的統計數據(可以說是美學)。

This is what AI looks like.

這就是AI的樣子。

You can read more about the foundational research for BiDAF right below (or follow links to the .pdf articles here & here).

您可以在下面閱讀有關BiDAF基礎研究的更多信息(或在此處和此處，鏈接到.pdf文章)。

補充閱讀 (Additional reading)

We appreciate this article by Meraldo Antonio that also provides a visual representation of the BiDAF model.

我們贊賞Meraldo Antonio的這篇文章，該文章還提供了BiDAF模型的直觀表示。

致謝 (Acknowledgement)

We thank Semih Cantürk for providing the images and video for this post.

我們感謝SemihCantürk為這篇文章提供的圖像和視頻。

翻譯自: https://medium.com/zetane-blog/this-is-what-ai-looks-like-bidaf-model-for-question-answering-8a0a69bcb045

ai模型

總結

以上是生活随笔為你收集整理的ai模型_这就是AI的样子：用于回答问题的BiDAF模型的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。