Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

By Alexandra Birch, Miles Osborne. 2011

370 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.

In Natural Language Processing

Citations in the corpus

All in One: Exploring Unified Video-Language Pre-Training (2022, methodology): “The pre-train-and-then-fine-tune scheme has become a standard paradigm to learn transferable videolanguage representations for a wide range of downstream video-text tasks, for example, text-video retrieval [7, 42], video-question answering [15, 40], multiple choice [15, 40] and visual commonsense re”
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning (2023, methodology): “Video Question Answering (VideoQA) includes the iVQA (Yang et al., 2021), MVSD (Chen & Dolan, 2011), and NextQA (Xiao et al., 2021) Nonverbal Reasoning includes the Raven IQ test (Huang et al., 2023a).”
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding (2023, background): “, MovieQA [79], MVAD [81], MPII-MD [66], and MovieNet [32]) from different sources such as YouTube [14,58,105], Twitter [5–8], Flirck [5, 6], and internet [9].”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning by Adam Yala (2017, background): “Several slot-filling methods have experimented with query formulation over web-based corpora to populate knowledge bases [19, 12].”
Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models (2023, methodology): “These results suggest that on six widely used IE datasets, ChatIE improves performance by an average of 18.98% compared to the original ChatGPT without ChatIE, and outperforms the supervised models FCM and MultiR [21; 30] on the NYT11-HRL dataset.”
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP (2019, methodology): “For RQ1, we pretrain an LSTM sequence encoder E(6) with 1500 hidden units on WikiText-2 similarly to [23, 22, 16], and apply (RQ2) or fine-tune it (RQ3) on IMDB [18], so we can analyze its zero-shot and supervised transfer properties.”
A Survey of Machine Unlearning (2022, neutral): “IMDB Review [93] dataset is a binary sentiment analysis dataset consisting of 50,000 Internet Movie Database (IMDb) reviews that have been categorised as positive or negative.”
Bootstrapping language acquisition. (2017, methodology): “CCG has been extensively applied to parsing and interpretation of unrestricted text (Auli & Lopez, 2011; Clark & Curran, 2004; Hockenmaier, 2003; Lewis & Steedman, 2014), and has received considerable attention recently in the computational literature on semantic parser induction (e.g., Artzi, Das,…”
Recent advances in document summarization (2017, methodology): “1) Comparative [79], update [42,99], evolutionary [198], multilingual [119,183]”
Align and Prompt: Video-and-Language Pre-training with Entity Prompts (2021, methodology): “(i) MSVD-QA [51] is built upon videos and text descriptions from MSVD [6].”
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment (2023, methodology): “On the MSVD dataset, LanguageBind achieves a notable R@1 score of 42.7%, surpassing the previous state-of-the-art model, CLIP4Clip (Luo et al., 2022), with an improvement of 4.2%.”
Sentiment analysis: A review and comparative analysis of web services (2015, background): “It seems a simple task; however, it is a really complex task, especially when opinions come from multiple domains or languages [76,30,10].”
Text: now in 2D! A framework for lexical expansion with contextual similarity (2013, background): “for user-generated content (Gimpel et al., 2011) or for domain-specific texts (e.”
Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models (2023, methodology): “These results suggest that on six widely used IE datasets, ChatIE improves performance by an average of 18.98% compared to the original ChatGPT without ChatIE, and out-performs the supervised models FCM and MultiR [20, 28] on the NYT11-HRL dataset.”