This paper presents a joint model for performing unsupervised morphological
analysis on words, and learning a character-level composition function from
morphemes to word embeddings. Our model splits individual words into segments,
and weights each segment according to its ability to predict context words. Our
morphological analysis is comparable to dedicated morphological analyzers at
the task of morpheme boundary recovery, and also performs better than
word-based embedding models at the task of syntactic analogy answering.
Finally, we show that incorporating morphology explicitly into character-level
models help them produce embeddings for unseen words which correlate better
with human judgments.

本文介绍了一种联合模型，能够对单词进行无监督的形态分析，并学习从形态素到单词嵌入的字符级组成函数。该模型对单词进行分割，并根据其预测上下文单词的能力对每个分割部分进行加权。我们的形态分析与专门的形态分析器相当，并且在语法类比回答任务中表现优异。最后，我们表明，将形态学明确纳入字符级模型有助于它们生成与人类判断更相关的未知单词的嵌入。

词嵌入和词形态的联合模型

A Joint Model for Word Embedding and Word Morphology

Most state-of-the-art systems today produce morphological analysis based only
on orthographic patterns. In contrast, we propose a model for unsupervised
morphological analysis that integrates orthographic and semantic views of
words. We model word formation in terms of morphological chains, from base
words to the observed words, breaking the chains into parent-child relations.
We use log-linear models with morpheme and word-level features to predict
possible parents, including their modifications, for each word. The limited set
of candidate parents for each word render contrastive estimation feasible. Our
model consistently matches or outperforms five state-of-the-art systems on
Arabic, English and Turkish.

通过将词汇的正字法和语义视图相结合，采用基于形态学链的无监督形态学分析模型，使用形态素和单词级别特征的对数线性模型预测可能的父节点来分析阿拉伯语、英语和土耳其语的单词。