Figurative language (e.g., "he flew like the wind") is challenging to
understand, as it is hard to tell what implicit information is being conveyed
from the surface form alone. We hypothesize that to perform this task well, the
reader needs to mentally elaborate the scene being described to identify a
sensible meaning of the language. We present DREAM-FLUTE, a figurative language
understanding system that does this, first forming a "mental model" of
situations described in a premise and hypothesis before making an
entailment/contradiction decision and generating an explanation. DREAM-FLUTE
uses an existing scene elaboration model, DREAM, for constructing its "mental
model." In the FigLang2022 Shared Task evaluation, DREAM-FLUTE achieved (joint)
first place (Acc@60=63.3%), and can perform even better with ensemble
techniques, demonstrating the effectiveness of this approach. More generally,
this work suggests that adding a reflective component to pretrained language
models can improve their performance beyond standard fine-tuning (3.3%
improvement in Acc@60).

提出了一种名为 DREAM-FLUTE 的比喻语言理解系统，它通过构建 “mental model” 来实现理解，将场景描绘成意义明确的语言，以此来实现事件推理，并取得了非常好的结果。

DREAM-FLUTE：借助梦幻长笛理解比喻语言

Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE

In this paper, we propose the TBCNN-pair model to recognize entailment and
contradiction between two sentences. In our model, a tree-based convolutional
neural network (TBCNN) captures sentence-level semantics; then heuristic
matching layers like concatenation, element-wise product/difference combine the
information in individual sentences. Experimental results show that our model
outperforms existing sentence encoding-based approaches by a large margin.

本文提出了 TBCNN-Pair 模型，通过树形卷积神经网络 (TBCNN) 和启发式匹配层，能更好地识别两个句子之间的蕴含和矛盾关系。实验结果表明，该模型在句子编码方面优于现有方法。

基于树形卷积和启发式匹配的自然语言推理

Natural Language Inference by Tree-Based Convolution and Heuristic  Matching

Understanding entailment and contradiction is fundamental to understanding
natural language, and inference about entailment and contradiction is a
valuable testing ground for the development of semantic representations.
However, machine learning research in this area has been dramatically limited
by the lack of large-scale resources. To address this, we introduce the
Stanford Natural Language Inference corpus, a new, freely available collection
of labeled sentence pairs, written by humans doing a novel grounded task based
on image captioning. At 570K pairs, it is two orders of magnitude larger than
all other resources of its type. This increase in scale allows lexicalized
classifiers to outperform some sophisticated existing entailment models, and it
allows a neural network-based model to perform competitively on natural
language inference benchmarks for the first time.

通过引入 Stanford 自然语言推理语料库，我们成功解决了机器学习研究在自然语言推理方面的巨大缺乏，该语料库是由人类按照基于图像字幕的新颖本体任务撰写的标记句子对，包含 570k 个句子对，是同类资源的两个量级以上，在规模方面取得了重大进展，这使得词汇分类器优于一些复杂的现有蕴含模型，并且让一种基于神经网络的模型在自然语言推理基准测试中首次表现亮眼。