Journal Article•
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
About: This article is published in The Association for Computational Linguistics.The article was published on 2011-01-01 and is currently open access. It has received 324 citations till now. The article focuses on the topics: Computational linguistics.
Citations
More filters
01 Dec 2013
TL;DR: The ACL Anthology Network is introduced, a comprehensive manually curated networked database of citations, collaborations, and summaries in the field of Computational Linguistics and a number of statistics about the network including the most cited authors, the most central collaborators, as well as network statistics.
Abstract: We introduce the ACL Anthology Network (AAN), a comprehensive manually curated networked database of citations, collaborations, and summaries in the field of Computational Linguistics. We also present a number of statistics about the network including the most cited authors, the most central collaborators, as well as network statistics about the paper citation, author citation, and author collaboration networks.
332 citations
TL;DR: The authors identify argument components using sequence labeling at the token level and apply a new joint model for detecting argumentation structures, which is a novel approach for parsing argumentation structure, and apply it to the problem of argumentation parsing.
Abstract: In this article, we present a novel approach for parsing argumentation structures. We identify argument components using sequence labeling at the token level and apply a new joint model for detecti...
301 citations
TL;DR: It is argued that democracy itself is a contested concept and points to a variety of norms, so designers of diversity enhancing tools must thus be exposed to diverse conceptions of democracy.
Abstract: It has been argued that the Internet and social media increase the number of available viewpoints, perspectives, ideas and opinions available, leading to a very diverse pool of information. However, critics have argued that algorithms used by search engines, social networking platforms and other large online intermediaries actually decrease information diversity by forming so-called "filter bubbles". This may form a serious threat to our democracies. In response to this threat others have developed algorithms and digital tools to combat filter bubbles. This paper first provides examples of different software designs that try to break filter bubbles. Secondly, we show how norms required by two democracy models dominate the tools that are developed to fight the filter bubbles, while norms of other models are completely missing in the tools. The paper in conclusion argues that democracy itself is a contested concept and points to a variety of norms. Designers of diversity enhancing tools must thus be exposed to diverse conceptions of democracy.
219 citations
Cites background from "Proceedings of the 49th Annual Meet..."
...Newscube (Park et al. 2009, 2011) is a tool that detects different aspects of a news using keyword analysis, and displays users news items with different perspectives in order to decrease media bias....
[...]
01 Mar 2014
TL;DR: This article proposed a two-stage statistical model that takes lexical targets and predicts frame-semantic structures using latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time.
Abstract: Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets i.e., content words and phrases in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than nave local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software.
214 citations
01 Jul 2015
TL;DR: A semisupervised system that detects 10 types of named entities that achieved the fourth position in the final ranking, without using any kind of hand-crafted features such as lexical features or gazetteers.
Abstract: Due to the short and noisy nature of Twitter microposts, detecting named entities is often a cumbersome task. As part of the ACL2015 Named Entity Recognition (NER) shared task, we present a semisupervised system that detects 10 types of named entities. To that end, we leverage 400 million Twitter microposts to generate powerful word embeddings as input features and use a neural network to execute the classification. To further boost the performance, we employ dropout to train the network and leaky Rectified Linear Units (ReLUs). Our system achieved the fourth position in the final ranking, without using any kind of hand-crafted features such as lexical features or gazetteers.
205 citations
Cites background or methods from "Proceedings of the 49th Annual Meet..."
...For example, Liu et al. (2011) report a F1 score of 45.8% when applying the Stanford NER tagger to Twitter microposts and Ritter et al. (2011) even report a F1-score of 29% on their Twitter micropost dataset....
[...]
...1c) of Mikolov et al. (2013) on our preprocessed dataset of 400 million Twitter microposts to generate word embeddings....
[...]
References
More filters
01 Dec 2013
TL;DR: The ACL Anthology Network is introduced, a comprehensive manually curated networked database of citations, collaborations, and summaries in the field of Computational Linguistics and a number of statistics about the network including the most cited authors, the most central collaborators, as well as network statistics.
Abstract: We introduce the ACL Anthology Network (AAN), a comprehensive manually curated networked database of citations, collaborations, and summaries in the field of Computational Linguistics. We also present a number of statistics about the network including the most cited authors, the most central collaborators, as well as network statistics about the paper citation, author citation, and author collaboration networks.
332 citations
TL;DR: The authors identify argument components using sequence labeling at the token level and apply a new joint model for detecting argumentation structures, which is a novel approach for parsing argumentation structure, and apply it to the problem of argumentation parsing.
Abstract: In this article, we present a novel approach for parsing argumentation structures. We identify argument components using sequence labeling at the token level and apply a new joint model for detecti...
301 citations
TL;DR: It is argued that democracy itself is a contested concept and points to a variety of norms, so designers of diversity enhancing tools must thus be exposed to diverse conceptions of democracy.
Abstract: It has been argued that the Internet and social media increase the number of available viewpoints, perspectives, ideas and opinions available, leading to a very diverse pool of information. However, critics have argued that algorithms used by search engines, social networking platforms and other large online intermediaries actually decrease information diversity by forming so-called "filter bubbles". This may form a serious threat to our democracies. In response to this threat others have developed algorithms and digital tools to combat filter bubbles. This paper first provides examples of different software designs that try to break filter bubbles. Secondly, we show how norms required by two democracy models dominate the tools that are developed to fight the filter bubbles, while norms of other models are completely missing in the tools. The paper in conclusion argues that democracy itself is a contested concept and points to a variety of norms. Designers of diversity enhancing tools must thus be exposed to diverse conceptions of democracy.
219 citations
01 Mar 2014
TL;DR: This article proposed a two-stage statistical model that takes lexical targets and predicts frame-semantic structures using latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time.
Abstract: Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets i.e., content words and phrases in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than nave local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software.
214 citations
01 Jul 2015
TL;DR: A semisupervised system that detects 10 types of named entities that achieved the fourth position in the final ranking, without using any kind of hand-crafted features such as lexical features or gazetteers.
Abstract: Due to the short and noisy nature of Twitter microposts, detecting named entities is often a cumbersome task. As part of the ACL2015 Named Entity Recognition (NER) shared task, we present a semisupervised system that detects 10 types of named entities. To that end, we leverage 400 million Twitter microposts to generate powerful word embeddings as input features and use a neural network to execute the classification. To further boost the performance, we employ dropout to train the network and leaky Rectified Linear Units (ReLUs). Our system achieved the fourth position in the final ranking, without using any kind of hand-crafted features such as lexical features or gazetteers.
205 citations