Paper Group NANR 19
DialSQL: Dialogue Based Structured Query Generation. Huge Automatically Extracted Training-Sets for Multilingual Word SenseDisambiguation. A Survey on Automatically-Constructed WordNets and their Evaluation: Lexical and Word Embedding-based Approaches. Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network. Porcupine Ne …
DialSQL: Dialogue Based Structured Query Generation
Title | DialSQL: Dialogue Based Structured Query Generation |
Authors | Izzeddin Gur, Semih Yavuz, Yu Su, Xifeng Yan |
Abstract | The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries. However, further improvement of the existing approaches turns out to be quite challenging. Rather than solely relying on algorithmic innovations, in this work, we introduce DialSQL, a dialogue-based structured query generation framework that leverages human intelligence to boost the performance of existing algorithms via user interaction. DialSQL is capable of identifying potential errors in a generated SQL query and asking users for validation via simple multi-choice questions. User feedback is then leveraged to revise the query. We design a generic simulator to bootstrap synthetic training dialogues and evaluate the performance of DialSQL on the WikiSQL dataset. Using SQLNet as a black box query generation tool, DialSQL improves its performance from 61.3{%} to 69.0{%} using only 2.4 validation questions per dialogue. |
Tasks | Semantic Parsing |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-1124/ |
https://www.aclweb.org/anthology/P18-1124 | |
PWC | https://paperswithcode.com/paper/dialsql-dialogue-based-structured-query |
Repo | |
Framework | |
Huge Automatically Extracted Training-Sets for Multilingual Word SenseDisambiguation
Title | Huge Automatically Extracted Training-Sets for Multilingual Word SenseDisambiguation |
Authors | Tommaso Pasini, Francesco Elia, Roberto Navigli |
Abstract | |
Tasks | Question Answering, Semantic Parsing, Word Sense Disambiguation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1268/ |
https://www.aclweb.org/anthology/L18-1268 | |
PWC | https://paperswithcode.com/paper/huge-automatically-extracted-training-sets |
Repo | |
Framework | |
A Survey on Automatically-Constructed WordNets and their Evaluation: Lexical and Word Embedding-based Approaches
Title | A Survey on Automatically-Constructed WordNets and their Evaluation: Lexical and Word Embedding-based Approaches |
Authors | Steven Neale |
Abstract | |
Tasks | Semantic Textual Similarity, Text Summarization, Word Embeddings, Word Sense Disambiguation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1270/ |
https://www.aclweb.org/anthology/L18-1270 | |
PWC | https://paperswithcode.com/paper/a-survey-on-automatically-constructed |
Repo | |
Framework | |
Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network
Title | Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network |
Authors | Fang Zhao, Jianshu Li, Jian Zhao, Jiashi Feng |
Abstract | In this paper, we propose a novel weakly supervised model, Multi-scale Anchored Transformer Network (MATN), to accurately localize free-form textual phrases with only image-level supervision. The proposed MATN takes region proposals as localization anchors, and learns a multi-scale correspondence network to continuously search for phrase regions referring to the anchors. In this way, MATN can exploit useful cues from these anchors to reliably reason about locations of the regions described by the phrases given only image-level supervision. Through differentiable sampling on image spatial feature maps, MATN introduces a novel training objective to simultaneously minimize a contrastive reconstruction loss between different phrases from a single image and a set of triplet losses among multiple images with similar phrases. Superior to existing region proposal based methods, MATN searches for the optimal bounding box over the entire feature map instead of selecting a sub-optimal one from discrete region proposals. We evaluate MATN on the Flickr30K Entities and ReferItGame datasets. The experimental results show that MATN significantly outperforms the state-of-the-art methods. |
Tasks | |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhao_Weakly_Supervised_Phrase_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Weakly_Supervised_Phrase_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/weakly-supervised-phrase-localization-with |
Repo | |
Framework | |
Porcupine Neural Networks: Approximating Neural Network Landscapes
Title | Porcupine Neural Networks: Approximating Neural Network Landscapes |
Authors | Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse |
Abstract | Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes analyzing their performance challenging. In this paper, we take another approach to this problem by constraining the network such that the corresponding optimization landscape has good theoretical properties without significantly compromising performance. In particular, for two-layer neural networks we introduce Porcupine Neural Networks (PNNs) whose weight vectors are constrained to lie over a finite set of lines. We show that most local optima of PNN optimizations are global while we have a characterization of regions where bad local optimizers may exist. Moreover, our theoretical and empirical results suggest that an unconstrained neural network can be approximated using a polynomially-large PNN. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7732-porcupine-neural-networks-approximating-neural-network-landscapes |
http://papers.nips.cc/paper/7732-porcupine-neural-networks-approximating-neural-network-landscapes.pdf | |
PWC | https://paperswithcode.com/paper/porcupine-neural-networks-approximating |
Repo | |
Framework | |
A Dataset for Inter-Sentence Relation Extraction using Distant Supervision
Title | A Dataset for Inter-Sentence Relation Extraction using Distant Supervision |
Authors | M, Angrosh ya, Danushka Bollegala, Frans Coenen, Katie Atkinson |
Abstract | |
Tasks | Information Retrieval, Relation Extraction |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1246/ |
https://www.aclweb.org/anthology/L18-1246 | |
PWC | https://paperswithcode.com/paper/a-dataset-for-inter-sentence-relation |
Repo | |
Framework | |
Event Detection via Gated Multilingual Attention Mechanism
Title | Event Detection via Gated Multilingual Attention Mechanism |
Authors | Jian Liu, Yubo Chen, Kang Liu, Jun Zhao |
Abstract | Identifying event instance in text plays a critical role in building NLP applications such as Information Extraction (IE) system. However, most existing methods for this task focus only on monolingual clues of a specific language and ignore the massive information provided by other languages. Data scarcity and monolingual ambiguity hinder the performance of these monolingual approaches. In this paper, we propose a novel multilingual approach — dubbed as Gated MultiLingual Attention (GMLATT) framework — to address the two issues simultaneously. In specific, to alleviate data scarcity problem, we exploit the consistent information in multilingual data via context attention mechanism. Which takes advantage of the consistent evidence in multilingual data other than learning only from monolingual data. To deal with monolingual ambiguity problem, we propose gated cross-lingual attention to exploit the complement information conveyed by multilingual data, which is helpful for the disambiguation. The cross-lingual attention gate serves as a sentinel modelling the confidence of the clues provided by other languages and controls the information integration of various languages. We have conducted extensive experiments on the ACE 2005 benchmark. Experimental results show that our approach significantly outperforms state-of-the-art methods. |
Tasks | |
Published | 2018-09-01 |
URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/16371 |
https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16371/16017 | |
PWC | https://paperswithcode.com/paper/event-detection-via-gated-multilingual |
Repo | |
Framework | |
Sequence Transfer Learning for Neural Decoding
Title | Sequence Transfer Learning for Neural Decoding |
Authors | Venkatesh Elango*, Aashish N Patel*, Kai J Miller, Vikash Gilja |
Abstract | A fundamental challenge in designing brain-computer interfaces (BCIs) is decoding behavior from time-varying neural oscillations. In typical applications, decoders are constructed for individual subjects and with limited data leading to restrictions on the types of models that can be utilized. Currently, the best performing decoders are typically linear models capable of utilizing rigid timing constraints with limited training data. Here we demonstrate the use of Long Short-Term Memory (LSTM) networks to take advantage of the temporal information present in sequential neural data collected from subjects implanted with electrocorticographic (ECoG) electrode arrays performing a finger flexion task. Our constructed models are capable of achieving accuracies that are comparable to existing techniques while also being robust to variation in sample data size. Moreover, we utilize the LSTM networks and an affine transformation layer to construct a novel architecture for transfer learning. We demonstrate that in scenarios where only the affine transform is learned for a new subject, it is possible to achieve results comparable to existing state-of-the-art techniques. The notable advantage is the increased stability of the model during training on novel subjects. Relaxing the constraint of only training the affine transformation, we establish our model as capable of exceeding performance of current models across all training data sizes. Overall, this work demonstrates that LSTMs are a versatile model that can accurately capture temporal patterns in neural data and can provide a foundation for transfer learning in neural decoding. |
Tasks | Transfer Learning |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rybDdHe0Z |
https://openreview.net/pdf?id=rybDdHe0Z | |
PWC | https://paperswithcode.com/paper/sequence-transfer-learning-for-neural |
Repo | |
Framework | |
Lightweight Grammatical Annotation in the TEI: New Perspectives
Title | Lightweight Grammatical Annotation in the TEI: New Perspectives |
Authors | Piotr Ba{'n}ski, Susanne Haaf, Martin Mueller |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1283/ |
https://www.aclweb.org/anthology/L18-1283 | |
PWC | https://paperswithcode.com/paper/lightweight-grammatical-annotation-in-the-tei |
Repo | |
Framework | |
Blind Deconvolutional Phase Retrieval via Convex Programming
Title | Blind Deconvolutional Phase Retrieval via Convex Programming |
Authors | Ali Ahmed, Alireza Aghasi, Paul Hand |
Abstract | We consider the task of recovering two real or complex $m$-vectors from phaseless Fourier measurements of their circular convolution. Our method is a novel convex relaxation that is based on a lifted matrix recovery formulation that allows a nontrivial convex relaxation of the bilinear measurements from convolution. We prove that if the two signals belong to known random subspaces of dimensions $k$ and $n$, then they can be recovered up to the inherent scaling ambiguity with $m » (k+n) \log^2 m$ phaseless measurements. Our method provides the first theoretical recovery guarantee for this problem by a computationally efficient algorithm and does not require a solution estimate to be computed for initialization. Our proof is based Rademacher complexity estimates. Additionally, we provide an ADMM implementation of the method and provide numerical experiments that verify the theory. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8207-blind-deconvolutional-phase-retrieval-via-convex-programming |
http://papers.nips.cc/paper/8207-blind-deconvolutional-phase-retrieval-via-convex-programming.pdf | |
PWC | https://paperswithcode.com/paper/blind-deconvolutional-phase-retrieval-via |
Repo | |
Framework | |
Twitter corpus of Resource-Scarce Languages for Sentiment Analysis and Multilingual Emoji Prediction
Title | Twitter corpus of Resource-Scarce Languages for Sentiment Analysis and Multilingual Emoji Prediction |
Authors | Nurendra Choudhary, Rajat Singh, Vijjini Anvesh Rao, Manish Shrivastava |
Abstract | In this paper, we leverage social media platforms such as twitter for developing corpus across multiple languages. The corpus creation methodology is applicable for resource-scarce languages provided the speakers of that particular language are active users on social media platforms. We present an approach to extract social media microblogs such as tweets (Twitter). In this paper, we create corpus for multilingual sentiment analysis and emoji prediction in Hindi, Bengali and Telugu. Further, we perform and analyze multiple NLP tasks utilizing the corpus to get interesting observations. |
Tasks | Sentiment Analysis |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1133/ |
https://www.aclweb.org/anthology/C18-1133 | |
PWC | https://paperswithcode.com/paper/twitter-corpus-of-resource-scarce-languages |
Repo | |
Framework | |
Fine-Grained Termhood Prediction for German Compound Terms Using Neural Networks
Title | Fine-Grained Termhood Prediction for German Compound Terms Using Neural Networks |
Authors | Anna H{"a}tty, Sabine Schulte im Walde |
Abstract | Automatic term identification and investigating the understandability of terms in a specialized domain are often treated as two separate lines of research. We propose a combined approach for this matter, by defining fine-grained classes of termhood and framing a classification task. The classes reflect tiers of a term{'}s association to a domain. The new setup is applied to German closed compounds as term candidates in the domain of cooking. For the prediction of the classes, we compare several neural network architectures and also take salient information about the compounds{'} components into account. We show that applying a similar class distinction to the compounds{'} components and propagating this information within the network improves the compound class prediction results. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4909/ |
https://www.aclweb.org/anthology/W18-4909 | |
PWC | https://paperswithcode.com/paper/fine-grained-termhood-prediction-for-german |
Repo | |
Framework | |
Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions
Title | Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions |
Authors | Kira Droganova, Daniel Zeman, Jenna Kanerva, Filip Ginter |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1290/ |
https://www.aclweb.org/anthology/L18-1290 | |
PWC | https://paperswithcode.com/paper/parse-me-if-you-can-artificial-treebanks-for |
Repo | |
Framework | |
Attention for Implicit Discourse Relation Recognition
Title | Attention for Implicit Discourse Relation Recognition |
Authors | Andre Cianflone, Leila Kosseim |
Abstract | |
Tasks | Coreference Resolution, Feature Engineering, Machine Translation, Reading Comprehension, Sentence Classification |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1306/ |
https://www.aclweb.org/anthology/L18-1306 | |
PWC | https://paperswithcode.com/paper/attention-for-implicit-discourse-relation |
Repo | |
Framework | |
Demonstrating the MUSTE Language Learning Environment
Title | Demonstrating the MUSTE Language Learning Environment |
Authors | Herbert Lange, Peter Ljungl{"o}f |
Abstract | |
Tasks | Machine Translation |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-7105/ |
https://www.aclweb.org/anthology/W18-7105 | |
PWC | https://paperswithcode.com/paper/demonstrating-the-muste-language-learning |
Repo | |
Framework | |