Results 11 to 20 of about 22,610 (167)
Linguistically Regularized LSTM for Sentiment Classification [PDF]
Proceedings of the 55th Annual Meeting of the Association for
Computational Linguistics (Volume 1: Long Papers), 2017 Sentiment understanding has been a long-term goal of AI in the past decades. This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed very recently, however, previous models either depend on expensive phrase-level annotation, whose performance drops substantially when trained with only ...
Qiao Qian +3 more
openaire +3 more sources
Linguistic Regularities of LOLspeak [PDF]
Sino-US English Teaching, 2017 The influence of the Internet on language is an unprecedented phenomenon. Maybe only the emergence of the systems of writing and the invention of printing can be claimed to have contributed more to the way language is used and perceived. Numerous publications have been devoted to the new forms of language thriving in the cyberspace.
Bury, Beata, Wojtaszek, Adam
openaire +3 more sources
Sentence Analogies: Linguistic Regularities in Sentence Embeddings [PDF]
Proceedings of the 28th International Conference on Computational Linguistics, 2020 While important properties of word vector representations have been studied extensively, far less is known about the properties of sentence vector representations. Word vectors are often evaluated by assessing to what degree they exhibit regularities with regard to relationships of the sort considered in word analogies. In this paper, we investigate to
Xunjie Zhu, Gerard de Melo
openaire +1 more source
Improving statistical parsing by linguistic regularization [PDF]
2010 10th International Conference on Intelligent Systems Design and Applications, 2010 Statistically-based parsers for large corpora, in particular the Penn Tree Bank (PTB), typically have not used all the linguistic information encoded in the annotated trees on which they are trained. In particular, they have not in general used information that records the effects of derivations, such as empty categories and the representation of ...
Berwick, Robert C. +1 more
openaire +2 more sources
Robust Reading Comprehension With Linguistic Constraints via Posterior Regularization [PDF]
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020 In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic different adversarial examples, while over-sensitively predict wrong answers to semantic equivalent adversarial examples.
Mantong Zhou +2 more
openaire +2 more sources
Linguistic Regularities in Sparse and Explicit Word Representations [PDF]
Proceedings of the Eighteenth Conference on Computational Natural Language Learning, 2014 Recent work has shown that neuralembedded word representations capture many relational similarities, which can be recovered by means of vector arithmetic in the embedded space. We show that Mikolov et al.’s method of first adding and subtracting word vectors, and then searching for a word similar to the result, is equivalent to searching for a word ...
Omer Levy, Yoav Goldberg
openaire +1 more source
The effect of regular rhythm on the perception of linguistic and non‐linguistic auditory input
European Journal of Neuroscience, 2020 Abstract Regular distribution of auditory stimuli over time can facilitate perception and attention. However, such effects have to date only been observed in separate studies using either linguistic or non‐linguistic materials.
Rassili, Outhmane, Ordin, Mikhail
openaire +4 more sources
Implicit learning of non-linguistic and linguistic regularities in children with dyslexia
Annals of Dyslexia, 2015 One of the hallmarks of dyslexia is the failure to automatise written patterns despite repeated exposure to print. Although many explanations have been proposed to explain this problem, researchers have recently begun to explore the possibility that an underlying implicit learning deficit may play a role in dyslexia.
Nigro, Lucíana +3 more
openaire +4 more sources
Detecting Regular Sound Changes in Linguistics as Events of Concerted Evolution [PDF]
Current Biology, 2015 Concerted evolution is normally used to describe parallel changes at different sites in a genome, but it is also observed in languages where a specific phoneme changes to the same other phoneme in many words in the lexicon—a phenomenon known as regular sound change.
Daniel J. Hruschka +6 more
openaire +3 more sources
Limited-Resource Adapters Are Regularizers, Not Linguists
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show promise for, e.g., improving low-resource machine translation (MT). In this work, we investigate an adapter souping method combined with cross-attention fine-tuning of a pre ...
Marcell Fekete +6 more
openaire +3 more sources