Gated-Attention Readers for Text Comprehension

Dhingra, Bhuwan; Liu, Hanxiao; Yang, Zhilin; Cohen, William W.; Salakhutdinov, Ruslan

doi:10.18653/v1/p17-1168

Cited by 305 publications

(353 citation statements)

References 22 publications

Supporting

Mentioning

352

Contrasting

Order By: Relevance

“…This would allow us to tackle the problem of the emote detection as a sequence modeling task, and this will be more natural as it is not easy to predict an emote of a message with no context. Finally, as Barbieri et al (2017) we plan to investigate character-based approaches to represent words and/or messages (Dhingra et al, 2016) For brands, gaining new customer is more expensive than keeping an existing one. Therefore, the ability to keep customers in a brand is becoming more challenging these days.…”

Section: Discussionmentioning

confidence: 99%

“…Given the proven effectiveness of recurrent neural networks in different tasks (Chung et al, 2014;Vinyals et al, 2015;Bahdanau et al, 2014, interalia), which also includes modeling of tweets (Dhingra et al, 2016;Barbieri et al, 2017), our Emote prediction model is based on RNNs, which are modeled to learn sequential data. We use the word based B-LSTM architecture by Barbieri et al (2017), designed to model emojis in Twitter.…”

Section: Bi-directional Lstmsmentioning

confidence: 99%

“…The CLC is not publicly available, which has inspired the use of automatically generated data with neural models. Liu and Liu (2016) have done exactly this with 16 different types of errors. Their success, although small compared to using manually annotated supervised revision data, has inspired our investigation into the particular effects of combining error types in an artificial corpus.…”

Section: Related Workmentioning

confidence: 99%

“…Currently, there is research into generating artificial data for training neural models, specifically data that resembles learner English (Cahill et al, 2013;Rozovskaya and Roth, 2010;Felice, 2016;Liu and Liu, 2016). The artificial data is generated from monolingual sentences of grammatical English by systematically introducing noise into it.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Proceedings of the 3rd Workshop on Noisy User-generated Text

Derczynski¹,

Xu²,

Ritter³

et al. 2017

View full text Add to dashboard Cite

ii Introduction The W-NUT 2017 workshop focuses on a core set of natural language processing tasks on top of noisy user-generated text, such as that found on social media, web forums and online reviews. Recent years have seen a significant increase of interest in these areas. The internet has democratized content creation leading to an explosion of informal user-generated text, publicly available in electronic format, motivating the need for NLP on noisy text to enable new data analytics applications. The workshop is an opportunity to bring together researchers interested in noisy text with different backgrounds and encourage crossover. The workshop this year features a shared task on Emerging and Rare entity recognition.The workshop received 27 main track submissions, 17 of which were accepted, in addition to 6 system description papers for the shared task and a task overview paper. There are 3 invited speakers, Bill Dolan, Dirk Hovy and Miles Osborne with each of their talks covering a different aspect of NLP for user-generated text. We would like to thank the Program Committee members who reviewed the papers this year. We would also like to thank the workshop participants. AbstractThis work presents a fine-grained, textchunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the handling of colloquial language. This algorithm's core novelty is its use of non-word tokens, i.e., boundaries, in a bottom-up strategy. Leveraging boundaries refines token-level information, forging highlevel performance from relatively basic data. The generality of this model's feature space allows for its application across languages and domains. Experiments spanning 19 different languages exhibit a broadly-applicable, stateof-the-art model. Evaluation against recent shared-task data places text partitioning as the overall, best performing MWE segmentation algorithm, covering all MWE classes and multiple English domains (including usergenerated text). This performance, coupled with a non-combinatorial, fast-running design, produces an ideal combination for implementations at scale, which are facilitated through the release of open-source software.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Bi-directional Lstmsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Proceedings of the 3rd Workshop on Noisy User-generated Text

Derczynski¹,

Xu²,

Ritter³

et al. 2017

View full text Add to dashboard Cite

show abstract

“…They implement a multi-hop attention mechanism from question to text (a Gated Attention Reader (Dhingra et al, 2017)). …”

Section: Ynu Deepmentioning

confidence: 99%

SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge

Ostermann¹,

Roth²,

Modi³

et al. 2018

Proceedings of the 12th International Workshop on Semantic Evaluation

110

101

View full text Add to dashboard Cite

This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge. For this machine comprehension task, we created a new corpus, MCScript. It contains a high number of questions that require commonsense knowledge for finding the correct answer. 11 teams from 4 different countries participated in this shared task, most of them used neural approaches. The best performing system achieves an accuracy of 83.95%, outperforming the baselines by a large margin, but still far from the human upper bound, which was found to be at 98%.

show abstract

Hippocampus segmentation on noncontrast CT using deep learning

et al. 2020

View full text Add to dashboard Cite

Purpose: Accurate segmentation of the hippocampus for hippocampal avoidance whole-brain radiotherapy currently requires high-resolution magnetic resonance imaging (MRI) in addition to neuroanatomic expertise for manual segmentation. Removing the need for MR images to identify the hippocampus would reduce planning complexity, the need for a treatment planning MR imaging session, potential uncertainties associated with MRI-computed tomography (CT) image registration, and cost. Three-dimensional (3D) deep convolutional network models have the potential to automate hippocampal segmentation. In this study, we investigate the accuracy and reliability of hippocampal segmentation by automated deep learning models from CT alone and compare the accuracy to experts using MRI fusion. Methods: Retrospectively, 390 Gamma Knife patients with high-resolution CT and MR images were collected. Following the RTOG 0933 guidelines, images were rigidly fused, and a neuroanatomic expert contoured the hippocampus on the MR, then transferred the contours to CT. Using a calculated cranial centroid, the image volumes were cropped to 200 9 200 9 35 voxels, which were used to train four models, including our proposed Attention-Gated 3D ResNet (AG-3D ResNet). These models were then compared with results from a nested tenfold validation. From the predicted test set volumes, we calculated the 100% Hausdorff distance (HD). Acceptability was assessed using the RTOG 0933 protocol criteria, and contours were considered passing with HD ≤ 7 mm. Results: The bilateral hippocampus passing rate across all 90 models trained in the nested cross-fold validation was 80.2% for AG-3D ResNet, which performs with a comparable pass rate (P = 0.3345) to physicians during centralized review for the RTOG 0933 Phase II clinical trial. Conclusions: Our proposed AG-3D ResNet's segmentation of the hippocampus from noncontrast CT images alone are comparable to those obtained by participating physicians from the RTOG 0933 Phase II clinical trial.

show abstract

Gated-Attention Readers for Text Comprehension

Cited by 305 publications

References 22 publications

Proceedings of the 3rd Workshop on Noisy User-generated Text

Proceedings of the 3rd Workshop on Noisy User-generated Text

SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge

Hippocampus segmentation on noncontrast CT using deep learning

Contact Info

Product

Resources

About