October 15, 2019

1417 words 7 mins read

Paper Group NANR 66

Paper Group NANR 66

Carcinologic Speech Severity Index Project: A Database of Speech Disorder Productions to Assess Quality of Life Related to Speech After Cancer. The GermaParl Corpus of Parliamentary Protocols. Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media. Exploring Named Entity Recognition As an Auxiliary Task for …

Title Carcinologic Speech Severity Index Project: A Database of Speech Disorder Productions to Assess Quality of Life Related to Speech After Cancer
Authors Corine Ast{'e}sano, Mathieu Balaguer, J{'e}r{^o}me Farinas, Corinne Fredouille, Pascal Gaillard, Alain Ghio, Imed Laaridh, Muriel Lalain, Beno{^\i}t Lepage, Julie Mauclair, Olivier Nocaudie, Julien Pinquier, Oriol Pont, Gilles Pouchoulin, Mich{`e}le Puech, Dani{`e}le Robert, Etienne Sicard, Virginie Woisard
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1673/
PDF https://www.aclweb.org/anthology/L18-1673
PWC https://paperswithcode.com/paper/carcinologic-speech-severity-index-project-a
Repo
Framework

The GermaParl Corpus of Parliamentary Protocols

Title The GermaParl Corpus of Parliamentary Protocols
Authors Andreas Bl{"a}tte, Andre Blessing
Abstract
Tasks Decision Making, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1130/
PDF https://www.aclweb.org/anthology/L18-1130
PWC https://paperswithcode.com/paper/the-germaparl-corpus-of-parliamentary
Repo
Framework

Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media

Title Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media
Authors
Abstract
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3500/
PDF https://www.aclweb.org/anthology/W18-3500
PWC https://paperswithcode.com/paper/proceedings-of-the-sixth-international
Repo
Framework

Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding

Title Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding
Authors Samuel Louvan, Bernardo Magnini
Abstract Slot filling is a crucial task in the Natural Language Understanding (NLU) component of a dialogue system. Most approaches for this task rely solely on the domain-specific datasets for training. We propose a joint model of slot filling and Named Entity Recognition (NER) in a multi-task learning (MTL) setup. Our experiments on three slot filling datasets show that using NER as an auxiliary task improves slot filling performance and achieve competitive performance compared with state-of-the-art. In particular, NER is effective when supervised at the lower layer of the model. For low-resource scenarios, we found that MTL is effective for one dataset.
Tasks Domain Adaptation, Multi-Task Learning, Named Entity Recognition, Slot Filling, Transfer Learning
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5711/
PDF https://www.aclweb.org/anthology/W18-5711
PWC https://paperswithcode.com/paper/exploring-named-entity-recognition-as-an
Repo
Framework

The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task

Title The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task
Authors Nick Rossenbach, Jan Rosendahl, Yunsu Kim, Miguel Gra{\c{c}}a, Aman Gokrani, Hermann Ney
Abstract This paper describes the submission of RWTH Aachen University for the De→En parallel corpus filtering task of the \textit{EMNLP 2018 Third Conference on Machine Translation} (WMT 2018). We use several rule-based, heuristic methods to preselect sentence pairs. These sentence pairs are scored with count-based and neural systems as language and translation models. In addition to single sentence-pair scoring, we further implement a simple redundancy removing heuristic. Our best performing corpus filtering system relies on recurrent neural language models and translation models based on the transformer architecture. A model trained on 10M randomly sampled tokens reaches a performance of 9.2{%} BLEU on newstest2018. Using our filtering and ranking techniques we achieve 34.8{%} BLEU.
Tasks Machine Translation, Tokenization
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6487/
PDF https://www.aclweb.org/anthology/W18-6487
PWC https://paperswithcode.com/paper/the-rwth-aachen-university-filtering-system
Repo
Framework

Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition

Title Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition
Authors Tao Ge, Qing Dou, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou
Abstract This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm. We use Burst Information Networks as media to represent text streams and present a simple yet effective network decipherment algorithm with diverse clues to decipher the networks for accurate text stream alignment. Experiments on Chinese-English news streams show our approach not only outperforms previous approaches on bilingual lexicon extraction from coordinated text streams but also can harvest high-quality alignments from large amounts of streaming data for endless language knowledge mining, which makes it promising to be a new paradigm for automatic language knowledge acquisition.
Tasks Information Retrieval
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1271/
PDF https://www.aclweb.org/anthology/D18-1271
PWC https://paperswithcode.com/paper/fine-grained-coordinated-cross-lingual-text
Repo
Framework

Completing State Representations using Spectral Learning

Title Completing State Representations using Spectral Learning
Authors Nan Jiang, Alex Kulesza, Satinder Singh
Abstract A central problem in dynamical system modeling is state discovery—that is, finding a compact summary of the past that captures the information needed to predict the future. Predictive State Representations (PSRs) enable clever spectral methods for state discovery; however, while consistent in the limit of infinite data, these methods often suffer from poor performance in the low data regime. In this paper we develop a novel algorithm for incorporating domain knowledge, in the form of an imperfect state representation, as side information to speed spectral learning for PSRs. We prove theoretical results characterizing the relevance of a user-provided state representation, and design spectral algorithms that can take advantage of a relevant representation. Our algorithm utilizes principal angles to extract the relevant components of the representation, and is robust to misspecification. Empirical evaluation on synthetic HMMs, an aircraft identification domain, and a gene splice dataset shows that, even with weak domain knowledge, the algorithm can significantly outperform standard PSR learning.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7686-completing-state-representations-using-spectral-learning
PDF http://papers.nips.cc/paper/7686-completing-state-representations-using-spectral-learning.pdf
PWC https://paperswithcode.com/paper/completing-state-representations-using
Repo
Framework

Proceedings of the Workshop on Linguistic Complexity and Natural Language Processing

Title Proceedings of the Workshop on Linguistic Complexity and Natural Language Processing
Authors
Abstract
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4600/
PDF https://www.aclweb.org/anthology/W18-4600
PWC https://paperswithcode.com/paper/proceedings-of-the-workshop-on-linguistic
Repo
Framework

Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations

Title Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations
Authors Erik-Lân Do Dinh, Hannah Wieland, Iryna Gurevych
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/papers/D18-1171/d18-1171
PDF https://www.aclweb.org/anthology/D18-1171
PWC https://paperswithcode.com/paper/weeding-out-conventionalized-metaphors-a
Repo
Framework

DialEdit: Annotations for Spoken Conversational Image Editing

Title DialEdit: Annotations for Spoken Conversational Image Editing
Authors Ramesh Manuvirakurike, Jacqueline Brixey, Trung Bui, Walter Chang, Ron Artstein, Kallirroi Georgila
Abstract
Tasks Dialogue State Tracking
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4701/
PDF https://www.aclweb.org/anthology/W18-4701
PWC https://paperswithcode.com/paper/dialedit-annotations-for-spoken
Repo
Framework

Downward Compatible Revision of Dialogue Annotation

Title Downward Compatible Revision of Dialogue Annotation
Authors Harry Bunt, Emer Gilmartin, Simon Keizer, Catherine Pelachaud, Volha Petukhova, Laurent Pr{'e}vot, Mari{"e}t Theune
Abstract
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4703/
PDF https://www.aclweb.org/anthology/W18-4703
PWC https://paperswithcode.com/paper/downward-compatible-revision-of-dialogue
Repo
Framework

Contextual Dependencies in Time-Continuous Multidimensional Affect Recognition

Title Contextual Dependencies in Time-Continuous Multidimensional Affect Recognition
Authors Dmitrii Fedotov, Denis Ivanko, Maxim Sidorov, Wolfgang Minker
Abstract
Tasks Emotion Recognition, Multimodal Emotion Recognition, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1196/
PDF https://www.aclweb.org/anthology/L18-1196
PWC https://paperswithcode.com/paper/contextual-dependencies-in-time-continuous
Repo
Framework

Universal Morphologies for the Caucasus region

Title Universal Morphologies for the Caucasus region
Authors Christian Chiarcos, Don, Kathrin t, Maxim Ionov, Monika Rind-Pawlowski, Hasmik Sargsian, Jesse Wichers Schreur, Frank Abromeit, Christian F{"a}th
Abstract
Tasks Lemmatization
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1417/
PDF https://www.aclweb.org/anthology/L18-1417
PWC https://paperswithcode.com/paper/universal-morphologies-for-the-caucasus
Repo
Framework

Discourse Annotation in the PDTB: The Next Generation

Title Discourse Annotation in the PDTB: The Next Generation
Authors Rashmi Prasad, Bonnie Webber, Alan Lee
Abstract
Tasks Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4710/
PDF https://www.aclweb.org/anthology/W18-4710
PWC https://paperswithcode.com/paper/discourse-annotation-in-the-pdtb-the-next
Repo
Framework

Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization

Title Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization
Authors Yuanxiang Gao, Li Chen, Baochun Li
Abstract Training deep neural networks requires an exorbitant amount of computation resources, including a heterogeneous mix of GPU and CPU devices. It is critical to place operations in a neural network on these devices in an optimal way, so that the training process can complete within the shortest amount of time. The state-of-the-art uses reinforcement learning to learn placement skills by repeatedly performing Monte-Carlo experiments. However, due to its equal treatment of placement samples, we argue that there remains ample room for significant improvements. In this paper, we propose a new joint learning algorithm, called Post, that integrates cross-entropy minimization and proximal policy optimization to achieve theoretically guaranteed optimal efficiency. In order to incorporate the cross-entropy method as a sampling technique, we propose to represent placements using discrete probability distributions, which allows us to estimate an optimal probability mass by maximal likelihood estimation, a powerful tool with the best possible efficiency. We have implemented Post in the Google Cloud platform, and our extensive experiments with several popular neural network training benchmarks have demonstrated clear evidence of superior performance: with the same amount of learning time, it leads to placements that have training times up to 63.7% shorter over the state-of-the-art.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8202-post-device-placement-with-cross-entropy-minimization-and-proximal-policy-optimization
PDF http://papers.nips.cc/paper/8202-post-device-placement-with-cross-entropy-minimization-and-proximal-policy-optimization.pdf
PWC https://paperswithcode.com/paper/post-device-placement-with-cross-entropy
Repo
Framework
comments powered by Disqus