投稿近2000,NAACL 2019接收率仅为22.6%|附录取论文名单

3 月 2 日 AI100


整理 | 若名

出品 | AI科技大本营(ID:rgznai100)


最近真是学术界公布论文产出结果的火热时期,距离计算机视觉领域的顶级盛会 CVPR 2019 刚公布论文接收结果不久,NLP 领域又迎来了丰收之时。


毫无疑问,NLP 领域的四大顶会分别是 ACL、EMNLP、NAACL - HLT、COLING 。NAACL - HLT,全称 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,AACL-HLT 即是 ACL 北美分会,一般简称 NAACL。虽然作为分会,但 NAACL 在自然语言处理领域是当之无愧的顶级会议,HLT 即是强调对人类语言技术的专注和重视, NAACL 每年都会选择在一个北美城市召开会议。


美国当地时间 2 月 28 日,NLP 领域的顶会 NAACL - HLT  2019 公布了目前已录取的全部论文目录(见文末),接下来 NAACL 正式会议将于今年 6 月 2 日至 6 月 7 日在美国明尼阿波利斯市举行。


那么,你的论文被录取了吗?


随着 AI 学术会议的论文投稿数量连年暴增,其中 NLP 领域也不例外。据官方统计,此次 NAACL 2019 共收到论文 1955 篇论文,共接收论文 424 篇,录取率仅为 22.6%。其中收到长论文投稿 1198 篇,短论文 757 篇。


今年的论文投稿数量以及接受数量意味着什么?



这就不得不拿往年的数字进行对比,就拿去年 NAACL 论文接收情况来看:共收到投稿 1072 篇,接收论文 332 篇,录取率为 31 %。长论文 647 篇,其中接收 207 篇,录取率 32%。短论文 425 篇,接收 125 篇,录取率为 29%。


也就是说,今年总论文投稿的数量多了近 1 倍,但在录取论文数量上却只增加了大约 100 篇,整体的论文录取率不增反降了,录取率降低的背后意味着对论文质量的标准更高,审稿也更加严苛。


这种操作让很多投稿作者猝不及防,叫苦不迭,但也早有预兆。


去年年底,有投稿作者因为一篇分数为 5-5-5(分数范围是 1-6)的论文被 NAACL 拒了,在 Twitter 表达了质疑。不过程序主席后来回复称,论文是否被接收,除了审稿意见,还受到多样性以及领域主席意见等多方面的影响。类似这样高分被拒的论文不是个例,被拒的还有 6-5-4,5-4-4,5-5-3 这样分数的论文。



NACCL 2019 最终极低的论文录取率证明了这一点,今年 NACCL 的竞争确实“惨烈”,一些论文投稿作者也在微博上表达了出乎意料之感。


眼看高分被拒,网友@JYGRTFD 发微博对此称,“NACCL 的风格是不是:不管你分数多高都有可能被拒,分数不是最后做出 decision 的唯一依据。”另有网友对此表示“瑟瑟发抖”。


以下是 UC Santa Barbra 计算机系助理教授王威廉对这届 NACCL 论文接收情况的评论:



目前, NAACL 暂未公布杰出论文,AI科技大本营(ID: rgznai100)将继续保持关注。


最后附上部分刚刚公布不久还很热乎的全部录取论文目录,供参考学习:)全部录取论文目录见链接(无需外网,点击即可查看):


https://naacl2019.org/program/accepted/



你怎么看这届 NAACL 论文评选?你的论文被接(拒)收(绝)了吗?欢迎评论。


(本文为 AI科技大本营整理文章,转载请微信联系 1092722531)


群招募


扫码添加小助手微信,回复:公司+研究方向(学校+研究方向),邀你加入技术交流群。技术群审核较严,敬请谅解。

推荐阅读:

                         

点击“阅读原文”,查看历史精彩文章。

点赞 0

Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a critical challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document time-stamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy and semantic change, and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts' genre information to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, we show that our model achieves improved predictive performance compared to the state of the art.

点赞 0
阅读1+

We use the persistent homology method of topological data analysis and dimensional analysis techniques to study data of syntactic structures of world languages. We analyze relations between syntactic parameters in terms of dimensionality, of hierarchical clustering structures, and of non-trivial loops. We show there are relations that hold across language families and additional relations that are family-specific. We then analyze the trees describing the merging structure of persistent connected components for languages in different language families and we show that they partly correlate to historical phylogenetic trees but with significant differences. We also show the existence of interesting non-trivial persistent first homology groups in various language families. We give examples where explicit generators for the persistent first homology can be identified, some of which appear to correspond to homoplasy phenomena, while others may have an explanation in terms of historical linguistics, corresponding to known cases of syntactic borrowing across different language subfamilies.

点赞 0
阅读1+

The main goal of this paper is to explore latent topic analysis (LTA), in the context of quantum information retrieval. LTA is a valuable technique for document analysis and representation, which has been extensively used in information retrieval and machine learning. Different LTA techniques have been proposed, some based on geometrical modeling (such as latent semantic analysis, LSA) and others based on a strong statistical foundation. However, these two different approaches are not usually mixed. Quantum information retrieval has the remarkable virtue of combining both geometry and probability in a common principled framework. We built on this quantum framework to propose a new LTA method, which has a clear geometrical motivation but also supports a well-founded probabilistic interpretation. An initial exploratory experimentation was performed on three standard data sets. The results show that the proposed method outperforms LSA on two of the three datasets. These results suggests that the quantum-motivated representation is an alternative for geometrical latent topic modeling worthy of further exploration.

点赞 0
阅读1+
Top