Results 21 to 30 of about 3,774,624 (287)
Deutsch als lingua franca: Bericht über ein forschungsbasiertes Lehrprojekt der 4EU+Allianz [PDF]
Beiträge zur Allgemeinen und Vergleichenden Sprachwissenschaft, 2023 This paper presents an overview of the activities and results of the European Network of German and Contrastive Linguistics (GerCoLiNet), which was part of the European University Alliance 4EU+ (May 2021 – June 2022).
Hélène Vinckel-Roisin
doaj +1 more source
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such as clustering ...
John Giorgi +3 more
semanticscholar +1 more source
The Contrastive Study of the Conjunction ‘and’ in English and Armenian
Translation Studies: Theory and Practice, 2021 In linguistics the structuring role of conjunctions is emphasized, whereas its pragmatic and contrastive study is often foregrounded. Conjunction may be prerequisite for contrastive study. The present research is mainly aimed at establishing semantic
Anahit Hovhannisyan
doaj +1 more source
Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great potential to ...
Yibin Lei +5 more
semanticscholar +1 more source
ConFEDE: Contrastive Feature Decomposition for Multimodal Sentiment Analysis
Annual Meeting of the Association for Computational Linguistics, 2023 Multimodal Sentiment Analysis aims to predict the sentiment of video content. Recent research suggests that multimodal sentiment analysis critically depends on learning a good representation of multimodal information, which should contain both modality ...
Jiuding Yang +4 more
semanticscholar +1 more source
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e., text or image) or limited multi-modal data (i.e., image-text pairs).
Wei Li +7 more
semanticscholar +1 more source
Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2023 Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding ...
Rico Sennrich +2 more
semanticscholar +1 more source
Improving Contrastive Learning of Sentence Embeddings from AI Feedback [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive and negative ...
Qinyuan Cheng +4 more
semanticscholar +1 more source
Chackelis Lemchenas, a contrastive linguist before contrastive linguistics
Philologia Estonica Tallinnensis, 2023 The article explores the views of Chackelis Lemchenas (1904– 2001) on teaching Lithuanian to speakers of other languages. As a prominent linguist, experienced practitioner, and a multilingual person, he proposed ideas that are compatible with the principles of contrastive linguistics already in the 1920s.
openaire +1 more source
Supporting Clustering with Contrastive Learning [PDF]
North American Chapter of the Association for Computational Linguistics, 2021 Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the beginning of the ...
Dejiao Zhang +8 more
semanticscholar +1 more source