Results 11 to 20 of about 1,392,663 (358)
Fine-Grained Human Evaluation of Neural Versus Phrase-Based Machine Translation [PDF]
We compare three approaches to statistical machine translation (pure phrase-based, factored phrase-based and neural) by performing a fine-grained manual evaluation via error annotation of the systems’ outputs.
Filip Klubicka+2 more
semanticscholar +10 more sources
UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining [PDF]
High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a context-free manner or rely on ...
Jiacheng Li+2 more
semanticscholar +1 more source
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration [PDF]
Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness.
Shufan Wang, Laure Thompson, Mohit Iyyer
semanticscholar +1 more source
Phrase Retrieval Learns Passage Retrieval, Too [PDF]
Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval—the most fine-grained retrieval unit—is appealing because phrases can be directly used as the output for ...
Jinhyuk Lee+2 more
semanticscholar +1 more source
Naming formed Anthroponyms of Sweets Names in Syntactic Aspect
The article characterizes the names of sweets, including anthroponyms, from the point of view of syntactic structure. Four groups of pragmatonyms are analyzed. The first group includes names that formally correspond to Russian anthroponymic formulas (one-
Natalia D. Osipova
doaj +1 more source
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation [PDF]
In this paper, we propose a novel neural network model called RNN Encoder‐ Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixedlength vector representation, and the other decodes the ...
Kyunghyun Cho+6 more
semanticscholar +1 more source
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models [PDF]
The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains, linking mentions of the same entities across
Bryan A. Plummer+5 more
semanticscholar +1 more source
Étude descriptive des différentes composantes d’une grammaire de texte
Dans l’enseignement de la langue étrangère le contexte linguistique où extralinguistique est primordial pour bien saisir le fonctionnement des énoncés.
Djamel BENDIHA, Mohamed MOKHENACHE
doaj +1 more source
Phrase-Based & Neural Unsupervised Machine Translation [PDF]
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs ...
Guillaume Lample+4 more
semanticscholar +1 more source
The development of software products for process automation is becoming more and more in demand. One of the main directions is the creation of software to automate the preparation of the client base to form the execution environment update, which allows ...
Marat R. Khamidullin+4 more
doaj +1 more source