Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

By Alessandro Moschitti, Bo Pang, Walter Daelemans. 2014

884 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network (2018, background): “Although [32] said that GloVe and Word2Vec were equally effective for natural language processing problems, they originated from datasets irrelevant to the financial field which affects the overall performance when they are used for financial applications.”
Improving Distributional Similarity with Lessons Learned from Word Embeddings (2015, methodology): “3 Finally, an important novelty introduced in (Pennington et al., 2014) is that, assuming V C = V W , one could take the representation of a word w to be ~w + ~c w where ~c w is the row corresponding to w in C > .”
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize (2018, methodology): “Overall, we sampled 10 Million comments each for our sensitive and nonsensitive classes, which were then used to train a BiLSTM classifier in which word representations were initialized using GLoVE (Pennington et al., 2014) embeddings and then fine-tuned during training.”
Deep Text Classification Can be Fooled (2017, background): “, 2015] and the other is word-level [Kim, 2014].”
Information Retrieval: A Biomedical and Health Perspective (2020, background): “Sheldon expresses concern they may promote confusion, especially among journalists who may not be able to adequately explain their meaning to their readers [199].”
Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content? (2022, background): “Additionally, the definitions and datasets on such tasks as bias-and hate-speech identification become increasingly complex [Sap et al. 2020].”
Metaphoria: An Algorithmic Companion for Metaphor Creation (2019, methodology): “To rank suggestions we use GloVe word embeddings [32] trained on Wikipedia 2014 + Gigaword 5.”
Learning Deep on Cyberbullying is Always Better Than Brute Force (2017, methodology): “Although originally, CNN were designed for image recognition, their performance has been confirmed in many tasks, including NLP [Collobert and Weston, 2008] and sentence classification [Kim, 2014].”
Applications of deep learning in stock market prediction: recent progress (2020, methodology): “Different from other related works that cover more papers from the computer science community, Reschenhofer et al. (2019) reviews articles covered by the Social Sciences Citation Index in the category Business, Finance and gives more insight on economic significance.”
Membership Inference Attacks on Machine Learning: A Survey (2021, background): “and Raghunathan [91] investigate the membership risks on embedding models and demonstrate a simple threshold attack can achieve a 30% improvement in attack accuracy over random guessing on Word2Vec [67], Fast-Text [7], Glove [76], LSTM [35], and Transformer [106] models.”
Neural Generative Question Answering (2015, methodology): “Yang et al. [Yang et al. , 2014 ] propose a method that transforms natural questions into their corresponding logical forms using joint relational embeddings, and conducts question answering by leveraging semantic associations between lexical representations and KB properties in the latent space.”
Graph-Bert: Only Attention is Needed for Learning Graph Representations (2020, background): “, 2014] or convolutional neural networks [Kim, 2014].”