The compositionality degree of multiword expressions indicates to what extent
the meaning of a phrase can be derived from the meaning of its constituents and
their grammatical relations. Prediction of (non)-compositionality is a task
that has been frequently addressed with distributional semantic models. We
introduce a novel technique to blend hierarchical information with
distributional information for predicting compositionality. In particular, we
use hypernymy information of the multiword and its constituents encoded in the
form of the recently introduced Poincar\'e embeddings in addition to the
distributional information to detect compositionality for noun phrases. Using a
weighted average of the distributional similarity and a Poincar\'e similarity
function, we obtain consistent and substantial, statistically significant
improvement across three gold standard datasets over state-of-the-art models
based on distributional information only. Unlike traditional approaches that
solely use an unsupervised setting, we have also framed the problem as a
supervised task, obtaining comparable improvements. Further, we publicly
release our Poincar\'e embeddings, which are trained on the output of
handcrafted lexical-syntactic patterns on a large corpus.

论文介绍了一种利用多层次信息和分布式信息的新技术，以检测名词短语的组合度，同时采用有监督的方法，并且使用了 Poincaré 嵌入，可以获得显著的效果提升。

使用 Poincaré 嵌入预测名词词组的组合性

On the Compositionality Prediction of Noun Phrases using Poincaré  Embeddings

We introduce the use of Poincar\'e embeddings to improve existing
state-of-the-art approaches to domain-specific taxonomy induction from text as
a signal for both relocating wrong hyponym terms within a (pre-induced)
taxonomy as well as for attaching disconnected terms in a taxonomy. This method
substantially improves previous state-of-the-art results on the SemEval-2016
Task 13 on taxonomy extraction. We demonstrate the superiority of Poincar\'e
embeddings over distributional semantic representations, supporting the
hypothesis that they can better capture hierarchical lexical-semantic
relationships than embeddings in the Euclidean space.

本文提出了使用 Poincaré 嵌入来改善领域特定分类法诱导的现有最先进方法，该方法可用作重新定位（预先诱导的）分类法中的错误下位词术语的信号，以及用于将断开的词术语附加到分类法中。本方法在 SemEval-2016 任务 13 的分类法提取上大大改进了以前的最先进结果，支持 Poincaré 嵌入优于分布语义表示的假设，因为它们可以更好地捕捉层次词汇语义关系。