Association for Computational Linguistics: Human Language Technologies

By H. Chinaei, M. Dreyer, J. Gillenwater, S. Hassan, Tom Kwiatkowski, M. Lehr, A. Levenberg, Ziheng Lin, P. Mannem, E. Morley and 3 more. 2011

612 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

All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text (2021, methodology): “Additionally, crowdsourcing literature has work on effectively using platforms like Amazon Mechanical Turk (e.g., Daniel et al., 2018; Oppenheimer et al., 2009; Weld et al., 2014; Mitra et al., 2015).”
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021, methodology): “It could also be keywords [112], relation triples [154] or even highlighted phrases or sentences [34, 78] to plan the content of generated texts.”
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation (2016, neutral): “We find that in almost all cases context provides enough language evidence to produce the correct translation.”
Towards Open Intent Discovery for Conversational Text (2019, methodology): “Supervised and semi-supervised learning models based on linguistic and sentiment features have been used to model racial intent on Tumblr [1], and purchase intent in social posts [14, 47] and in discussion forums [5].”
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search (2017, methodology): “We modify the experiments of Cheng et al. (2016) slightly, and assume that the user only provides sequences of up to three words which are missing from the hypothesis.4 To simulate user interaction, at each iteration we chose a phrase of up to three tokens from the reference translation which does…”
Abstract Syntax Networks for Code Generation and Semantic Parsing (2017, background): “This difference may be partially attributable to the use of typing information or rich lexicons in most previous semantic parsing approaches (Zettlemoyer and Collins, 2007; Kwiatkowski et al., 2013; Wang et al., 2014; Zhao and Huang, 2015).”
Do Neural Language Representations Learn Physical Commonsense? (2019, neutral): “Contextualized representations The other two representations are ELMo (Peters et al., 2018) and BERT (Devlin et al.”
Identifying Customer Needs from User-Generated Content (2019, background): “In NLP, CNNs demonstrate state-of-the-art performance with minimum tuning in such problems as relation extraction (Nguyen and Grishman, 2015), named entity recognition (Sun et al., 2015) and sentiment analysis (Santos and Gatti, 2014).”
Overview of Touché 2022: Argument Retrieval (2022, positive): “We then employed MACE [38] to identify images with high disagreement (confidence ≤ 0.55) and re-judged them ourselves (2,056 images).”
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, background): “This barrier has led to proposals that acquire multilingual lexicons from parallel text [42,39,70, inter alia], monolingual corpora [58,119,46] or machine readable dictionaries (MRDs) [25].”
A Survey of Multilingual Neural Machine Translation (2019, methodology): “In addition, it is not uncommon to write domain-specific sentences in different styles, and so multi-source approaches [168] are not applicable either.”
Detect & Describe: Deep Learning of Bank Stress in the News (2015, neutral): “C P] 2 5 Ju l 2 01 5”
Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks (2022, background): “The community’s understanding of the limitations of these approaches is evolving (Webson and Pavlick, 2022; Min et al., 2022a).”
Towards recency ranking in web search (2010, methodology): “The works that are most related to our approach include [8] and [22], which also directly improve ranking recency in web search.”
Directions in abusive language training data, a systematic review: Garbage in, garbage out (2020, background): “ACL Anthology A database of research in the fields of computational linguistics and natural language processing published by the Association for Computational Linguistics [35, 36].”