In this paper, we investigate the Domain Generalization (DG) problem for supervised Paraphrase Identification (PI). We observe that the performance of existing PI models deteriorates dramatically when tested in an out-of-distribution (OOD) domain. We
conjecture that it is caused by shortcut learning, i.e., these models tend to utilize the cue words that are unique for a particular dataset or domain. To alleviate this issue and enhance the DG ability, we propose a PI framework based on Optimal Transport (OT). Our method forces the network to learn the necessary features for all the words in the input, which alleviates the shortcut learning problem. Experimental results show that our method improves the DG ability for the PI models.
This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures. We pre-train our models on more than 340K of sentences, which is 50 times more than multilingual models th
at include Czech data. We outperform the multilingual models on 9 out of 11 datasets. In addition, we establish the new state-of-the-art results on nine datasets. At the end, we discuss properties of monolingual and multilingual models based upon our results. We publish all the pre-trained and fine-tuned models freely for the research community.
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on high-resource lang
uages so that it transfers well to the zero-shot languages is a non-trivial task. In this paper, we propose a novel meta-optimizer to soft-select which layers of the pre-trained model to freeze during fine-tuning. We train the meta-optimizer by simulating the zero-shot transfer scenario. Results on cross-lingual natural language inference show that our approach improves over the simple fine-tuning baseline and X-MAML (Nooralahzadeh et al., 2020).
New words are regularly introduced to communities, yet not all of these words persist in a community's lexicon. Among the many factors contributing to lexical change, we focus on the understudied effect of social networks. We conduct a large-scale an
alysis of over 80k neologisms in 4420 online communities across a decade. Using Poisson regression and survival analysis, our study demonstrates that the community's network structure plays a significant role in lexical change. Apart from overall size, properties including dense connections, the lack of local clusters, and more external contacts promote lexical innovation and retention. Unlike offline communities, these topic-based communities do not experience strong lexical leveling despite increased contact but accommodate more niche words. Our work provides support for the sociolinguistic hypothesis that lexical change is partially shaped by the structure of the underlying network but also uncovers findings specific to online communities.
With the increase in the number of published academic papers, growing expectations have been placed on research related to supporting the writing process of scientific papers. Recently, research has been conducted on various tasks such as citation wo
rthiness (judging whether a sentence requires citation), citation recommendation, and citation-text generation. However, since each task has been studied and evaluated using data that has been independently developed, it is currently impossible to verify whether such tasks can be successfully pipelined to effective use in scientific-document writing. In this paper, we first define a series of tasks related to scientific-document writing that can be pipelined. Then, we create a dataset of academic papers that can be used for the evaluation of each task as well as a series of these tasks. Finally, using the dataset, we evaluate the tasks of citation worthiness and citation recommendation as well as both of these tasks integrated. The results of our evaluations show that the proposed approach is promising.
In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word. Most existing methods take the source word as an indecomposable semantic unit. However, in parataxis languages
like Chinese, word meanings can be composed using the word formation process, where a word (桃花'', peach-blossom) is formed by formation components (桃'', peach; 花'', flower) using a formation rule (Modifier-Head). Inspired by this process, we propose to enhance DG with word formation features. We build a formation-informed dataset, and propose a model DeFT, which Decomposes words into formation features, dynamically Fuses different features through a gating mechanism, and generaTes word definitions. Experimental results show that our method is both effective and robust.
This research is considered a completion to many studies which dealt with nunnation
as a tool of namelessness as Arabic scientists were clearly interested in nunnation in their
artistic texts and books to control its origins and feel its effect in
the lingual context.
Research about nunnation origins has stopped in the semetic languages, generally
speaking, and in Arabic in particular.
After that its linguistic and conventional meaning was known by grammarians,
linguals and eloquent people. It also spotlighted all its kinds, the linguists disagreement
about its number and indication of each kind of it projecting its significance efficacy in
reference to namelessness as a tool that is opposite to the definite article ( alef and lam ) .
In addition to show the obstacles that faced grammarians as proper names nunnation
which is considered as a part of identifiers to know its omission places which were
identified by grammarians .
This research deals with a general professional book which is rarely studied nor
analyzed by researchers.It´s AL Koulliat by Abi ALbakáa ALkafawi. It tries tointroduce a
comprehensive description of this book.In the beginning, the research speaks a
bout the
biography of his writer and tries to know the purpose of its writing, examine its sources
and subject, and how to classify and explainit.In addition, the research examines the most
important characteristics of the book which is distinguished from other idiomatic books.
The research sumsup the most important results and commandments.
