언어 전공자의 NLP 로그

논문 읽기 : https://arxiv.org/abs/1707.01476 Convolutional 2D Knowledge Graph Embeddings Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressi arxiv.org 0. Abstract Link prediction은 지식 그래프 속 객체 사이의 비..

논문 읽기 : https://aclanthology.org/P19-1569/ Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation Daniel Loureiro, Alípio Jorge. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019. aclanthology.org 0. Abstract 본 연구에서 제시하는 맥락 임베딩으로 WSD 과제에서 전례 없는 성과를 이루어냈다. 외부 지식이나 특정 과제 모델링 없이 WordNet 전체를 ..

논문 출처 : https://arxiv.org/abs/1706.03762 Attention Is All You Need The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new arxiv.org 0. Abstract 당시 시퀀스 모델은 RNN 및 CNN 형태가 주도적이었고, 여기에 attention 메커니즘을 ..

논문 출처 : https://arxiv.org/abs/cs/0107019 Applying Natural Language Generation to Indicative Summarization The task of creating indicative summaries that help a searcher decide whether to read a particular document is a difficult task. This paper examines the indicative summarization task from a generation perspective, by first analyzing its required content vi arxiv.org 요약 태스크는 크게 정보 요약 (informa..

논문 출처 : https://arxiv.org/abs/1801.07243 Personalizing Dialogue Agents: I have a dog, do you have pets too? Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile informatio arxiv.org 잡담용 챗봇에 사용되는 LLM은 다양한 소..

논문 출처 : https://arxiv.org/abs/1808.06226 SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword units...

논문 출처 : https://www.semanticscholar.org/paper/Machine-Translation%3A-Interlingual-Methods-Dorr-Hovy/81466e7699334077dbd7948af109405bce22d581 https://www.semanticscholar.org/paper/Machine-Translation%3A-Interlingual-Methods-Dorr-Hovy/81466e7699334077dbd7948af109405bce22d581 www.semanticscholar.org 개요 만약 모든 언어로부터 의미 단위만 추출하여 일종의 국제적 언어를 만들어낼 수 있을까? 이것이 가능하다고 봤던 연구자들이 내세운 개념이 바로 Interlingua이다. 영어 사..

논문 출처 : https://dl.acm.org/doi/10.3115/1073083.1073135 BLEU | Proceedings of the 40th Annual Meeting on Association for Computational Linguistics We present the results of an experiment on extending the automatic method of Machine Translation evaluation BLUE with statistical weights for lexical items, such as tf.idf scores. We show that this extension gives additional information about evaluated..