Proceedings of ACL

By Shay B. Cohen, Melanie Johnson. 2013

75 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.

1. Zequn Sun
2. Zhiyuan Liu
3. Maosong Sun
4. Xipeng Qiu
5. Wei Hu
6. Ruobing Xie
7. Pengfei Liu
8. Xuanjing Huang

Citations in the corpus

• Recurrent Neural Network for Text Classification with Multi-Task Learning (2016, background): “[Pang and Lee, 2004] • IMDB The IMDB dataset2 consists of 100,000 movie reviews with binary classes [Maas et al., 2011].”
• Answer Extraction from Passage Graph for Question Answering (2013, unknown): “Without manual effort, [Ravichandran and Hovy, 2002] automatically learn such pattern sets and their scores.”
• Bootstrapping Entity Alignment with Knowledge Graph Embedding (2018, methodology): “• IPTransE [Zhu et al., 2017] is an iterative approach.”
• Max-Margin DeepWalk: Discriminative Learning of Network Representation (2016, background): “Besides, max-margin also benefits many NLP tasks, such as semantic parsing [Taskar et al., 2004] and word segmentation [Pei et al., 2014].”
• Knowledge Representation Learning with Entities, Attributes and Relations (2016, methodology): “In fact, other KR models such as TransD [Ji et al., 2015], TranSparse [Ji et al.”
• Text Transformations in Contrastive Self-Supervised Learning: A Review (2022, methodology): “Prior to that, Batmanghelich et al. [Batmanghelich et al., 2016] applied von Mises-Fisher distribution to model the density of the words over a unit sphere as well as discovering the number of topics in the data.”
• Image-embodied Knowledge Representation Learning (2016, methodology): “TransD [Ji et al., 2015] further considers the diversities of both entities and relations, using dynamic mapping matrix for the multiple representations of entities.”
• Representation Learning of Knowledge Graphs with Hierarchical Types (2016, background): “TransD [Ji et al., 2015] proposes dynamic mapping matrix constructed via both entity and relation, considering the diversity of entities as well as relations simultaneously.”
• PhoBERT: Pre-trained language models for Vietnamese (2020, methodology): “Different from RoBERTa, we then apply fastBPE [Sennrich et al., 2016] to segment these sentences with subword units, using a vocabulary size of 64K subword types.”
• FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining (2020, methodology): “combine multiple common unsupervised pre-training tasks [Joshi et al., 2019; Dong et al., 2019; Liu et al., 2019a; Lan et al., 2020; Devlin et al., 2019; Liu et al., 2019b; Raffel et al., 2019; Sun et al., 2019b] fit our framework.”
• Joint Learning of Character and Word Embeddings (2015, background): “[Lazaridou et al., 2013] explored the application of compositional distributional semantic models, originally designed to learn phrase meanings, for derivational morphology.”
• Joint Models for Extracting Adverse Drug Events from Biomedical Text (2016, methodology): “Joint models, which process all subtasks simultaneously, have been proposed to avoid error propagation in similar situations, such as word segmentation and part-of-speech (POS) tagging [Zhang and Clark, 2008], NER and parsing [Finkel and Manning, 2009], POS tagging and parsing [Bohnet and Nivre, 201”