Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics

By Kevin Gimpel, Nathan Schneider, Brendan T. O'Connor, Dipanjan Das, Daniel Mills, Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, Noah A. Smith. 2011

242 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Big Bird: Transformers for Longer Sequences (2020, neutral): “Note that this performance gain is not seen for much smaller IMDb dataset.”
Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization (2022, background): “IMDB (Maas et al., 2011) Text Continuation Partial Movie Review A positive completion of the movie review.”
Progressive Prompts: Continual Learning for Language Models (2023, methodology): “, 2019) (WiC, CB, COPA, MultiRC, BoolQ), and IMDB movie reviews dataset (Maas et al., 2011).”
Entailment as Few-Shot Learner (2021, positive): “Our benchmark includes 8 datasets from GLUE (Wang et al., 2018): CoLA (Warstadt et al., 2019), SST-2 (Socher et al., 2013), MPRC (Dolan & Brockett, 2005), QQP4, STS-B (Cer et al., 2017), MNLI (Williams et al., 2017), QNLI (Rajpurkar et al., 2016), RTE (Dagan et al., 2005; Haim et al., 2006; Giampicc”
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization (2021, methodology): “In addition, we evaluate on tasks that require dealing with long documents, both for sentiment analysis (IMDb; Maas et al., 2011) and news classification (AGNews; Zhang et al.”
Luna: Linear Unified Nested Attention (2021, methodology): “They collect five tasks in this benchmark which are ListOps (Nangia and Bowman, 2018), byte-level text classification (Text; Maas et al., 2011), byte-level document retrieval (Retrieval; Radev et al.”
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond (2023, methodology): “For sentiment analysis, such as on IMDB [81] and SST [104], fine-tuned models and LLMs perform equally well.”
Generating Natural-Language Video Descriptions Using Text-Mined Knowledge (2013, unknown): “In a second approach to estimating SVO probabilities, we used BerkeleyLM (Pauls and Klein, 2011) to train an n-gram language model on the GoogleNgram corpus (Lin et al., 2012).”
Discovering Latent Knowledge in Language Models Without Supervision (2022, methodology): “We test models on 10 datasets: sentiment classification (IMDB (Maas et al., 2011) and Amazon (McAuley & Leskovec, 2013)), topic classification (AG-News (Zhang et al., 2015) and DBpedia-14 (Lehmann et al., 2015)), NLI (RTE (Wang et al., 2018) and QNLI (Rajpurkar et al., 2016)), story completion…”
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation (2021, methodology): “We used ListOps [46], byte-level IMDb reviews text classification [44], byte-level document retrieval [48], image classification on sequences of pixels [37] and Pathfinder [40].”
Graph based anomaly detection and description: a survey (2014, background): “…al., 2012b, Jindal and Liu, 2008, Jindal et al., 2010, Xie et al., 2012], (ii) language stylometry analysis to spot deception [Feng et al., 2012a, Ott et al., 2011], and (iii) relational analysis and network effects to exploit connections among fraudulent reviewers [Akoglu et al., 2013a, Wang et…”
Escaping the Big Data Paradigm with Compact Transformers (2021, methodology): “Within this section, we present our text classification results on 5 datasets: AGNews [52], TREC [24], SST [37], IMDb [29], DBpedia [1].”
cosFormer: Rethinking Softmax in Attention (2022, methodology): “We use the pre-trained bidirectional model and ﬁne-tune it on three downstream text classiﬁcation tasks: GLUE (QQP, SST-2, MNLi) (Wang et al., 2018), IMDB (Maas et al., 2011) and AMAZON (Ni et al., 2019).”
Open Information Extraction: The Second Generation (2011, background): “parse WOE pos TEXTRUNNER Figure 2 : REVERB identifies correct relation phrases with substantially higher precision and recall than state-of-the-art open extractors , including WOE parse that uses patterns learned over dependency parse paths.”