Results 41 to 50 of about 8,669 (85)
Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition
Transactions of the Association for Computational Linguistics, 2019 Building meaningful phrase representations is challenging because phrase meanings are not simply the sum of their constituent meanings. Lexical composition can shift the meanings of the constituent words and introduce implicit information.
Shwartz, Vered, Dagan, Ido
doaj +1 more source
Aspect-based sentiment classification with BERT and AI feedback
Natural Language Processing JournalData augmentation has been widely employed in low-resource aspect-based sentiment classification (ABSC) tasks to alleviate the issue of data sparsity and enhance the performance of the model. Unlike previous data augmentation approaches that rely on back
Lingling Xu, Weiming Wang
doaj +1 more source
Jurnal Linguistik Komputasional, 2019 Kalibrasi LR merupakan tahapan yang sangat penting saat akan mengaplikasikan sistem rekognisi pengucap otomatis pada bidang forensik. Artikel ini memuat tahapan dan evaluasi terhadap sistem rekognisi pengucap yang dibangun menggunakan basis data suara ...
Miranti Indar Mandasari +2 more
doaj +1 more source
Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach
Transactions of the Association for Computational Linguistics, 2019 We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples the source-to-target language transformation into (a) language-specific rotations on the original ...
Jawanpuria, Pratik +3 more
doaj +1 more source
Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs
Transactions of the Association for Computational Linguistics, 2019 Recent years have seen increasingly complex question-answering on knowledge bases (KBQA) involving logical, quantitative, and comparative reasoning over KB subgraphs.
Saha, Amrita +4 more
doaj +1 more source
Efficient Contextual Representation Learning With Continuous Outputs
Transactions of the Association for Computational Linguistics, 2019 Contextual representation models have achieved great success in improving various downstream natural language processing tasks. However, these language-model-based encoders are difficult to train due to their large parameter size and high computational ...
Li, Liunian Harold +3 more
doaj +1 more source
Morphological Analysis Using a Sequence Decoder
Transactions of the Association for Computational Linguistics, 2019 We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the decoder ...
Akyürek, Ekin +2 more
doaj +1 more source
Design, Green Synthesis and Tailoring of Vitamin E TPGS Augmented Niosomal Nano-Carrier of Pyrazolopyrimidines as Potential Anti-Liver and Breast Cancer Agents with Accentuated Oral Bioavailability. [PDF]
Pharmaceuticals (Basel), 2022 Anwer KE +4 more
europepmc +1 more source
Synchronous Bidirectional Neural Machine Translation
Transactions of the Association for Computational Linguistics, 2019 Existing approaches to neural machine translation (NMT) generate the target language sequence token-by-token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be ...
Zhou, Long +2 more
doaj +1 more source
Measuring Online Debaters’ Persuasive Skill from Text over Time
Transactions of the Association for Computational Linguistics, 2019 Online debates allow people to express their persuasive abilities and provide exciting opportunities for understanding persuasion. Prior studies have focused on studying persuasion in debate content, but without accounting for each debater’s history or ...
Luu, Kelvin +2 more
doaj +1 more source