Paper Group NANR 48
Story Cloze Task: UW NLP System. NCTU-NTUT at IJCNLP-2017 Task 2: Deep Phrase Embedding using bi-LSTMs for Valence-Arousal Ratings Prediction of Chinese Phrases. Segment-Level Neural Conditional Random Fields for Named Entity Recognition. Action Languages and Question Answering. OnACID: Online Analysis of Calcium Imaging Data in Real Time. Inter-Pa …
Story Cloze Task: UW NLP System
| Title | Story Cloze Task: UW NLP System |
| Authors | Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi, Noah A. Smith |
| Abstract | This paper describes University of Washington NLP{'}s submission for the Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2017) shared task{—}the Story Cloze Task. Our system is a linear classifier with a variety of features, including both the scores of a neural language model and style features. We report 75.2{%} accuracy on the task. A further discussion of our results can be found in Schwartz et al. (2017). |
| Tasks | Language Modelling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0907/ |
| https://www.aclweb.org/anthology/W17-0907 | |
| PWC | https://paperswithcode.com/paper/story-cloze-task-uw-nlp-system |
| Repo | |
| Framework | |
NCTU-NTUT at IJCNLP-2017 Task 2: Deep Phrase Embedding using bi-LSTMs for Valence-Arousal Ratings Prediction of Chinese Phrases
| Title | NCTU-NTUT at IJCNLP-2017 Task 2: Deep Phrase Embedding using bi-LSTMs for Valence-Arousal Ratings Prediction of Chinese Phrases |
| Authors | Yen-Hsuan Lee, Han-Yun Yeh, Yih-Ru Wang, Yuan-Fu Liao |
| Abstract | In this paper, a deep phrase embedding approach using bi-directional long short-term memory (Bi-LSTM) is proposed to predict the valence-arousal ratings of Chinese words and phrases. It adopts a Chinese word segmentation frontend, a local order-aware word, a global phrase embedding representations and a deep regression neural network (DRNN) model. The performance of the proposed method was benchmarked by the IJCNLP 2017 shared task 2. According the official evaluation results, our best system achieved mean rank 6.5 among all 24 submissions. |
| Tasks | Chinese Word Segmentation, Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4020/ |
| https://www.aclweb.org/anthology/I17-4020 | |
| PWC | https://paperswithcode.com/paper/nctu-ntut-at-ijcnlp-2017-task-2-deep-phrase |
| Repo | |
| Framework | |
Segment-Level Neural Conditional Random Fields for Named Entity Recognition
| Title | Segment-Level Neural Conditional Random Fields for Named Entity Recognition |
| Authors | Motoki Sato, Hiroyuki Shindo, Ikuya Yamada, Yuji Matsumoto |
| Abstract | We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking. Our segment-level CRF can consider higher-order label dependencies compared with conventional word-level CRF. Since it is difficult to consider all possible variable length segments, our method uses segment lattice constructed from the word-level tagging model to reduce the search space. Performing experiments on NER and chunking, we demonstrate that our method outperforms conventional word-level CRF with neural networks. |
| Tasks | Chunking, Morphological Tagging, Named Entity Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2017/ |
| https://www.aclweb.org/anthology/I17-2017 | |
| PWC | https://paperswithcode.com/paper/segment-level-neural-conditional-random |
| Repo | |
| Framework | |
Action Languages and Question Answering
| Title | Action Languages and Question Answering |
| Authors | Yuliya Lierler, Daniela Inclezan, Michael Gelfond |
| Abstract | |
| Tasks | Question Answering |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6925/ |
| https://www.aclweb.org/anthology/W17-6925 | |
| PWC | https://paperswithcode.com/paper/action-languages-and-question-answering |
| Repo | |
| Framework | |
OnACID: Online Analysis of Calcium Imaging Data in Real Time
| Title | OnACID: Online Analysis of Calcium Imaging Data in Real Time |
| Authors | Andrea Giovannucci, Johannes Friedrich, Matt Kaufman, Anne Churchland, Dmitri Chklovskii, Liam Paninski, Eftychios A. Pnevmatikakis |
| Abstract | Optical imaging methods using calcium indicators are critical for monitoring the activity of large neuronal populations in vivo. Imaging experiments typically generate a large amount of data that needs to be processed to extract the activity of the imaged neuronal sources. While deriving such processing algorithms is an active area of research, most existing methods require the processing of large amounts of data at a time, rendering them vulnerable to the volume of the recorded data, and preventing real-time experimental interrogation. Here we introduce OnACID, an Online framework for the Analysis of streaming Calcium Imaging Data, including i) motion artifact correction, ii) neuronal source extraction, and iii) activity denoising and deconvolution. Our approach combines and extends previous work on online dictionary learning and calcium imaging data analysis, to deliver an automated pipeline that can discover and track the activity of hundreds of cells in real time, thereby enabling new types of closed-loop experiments. We apply our algorithm on two large scale experimental datasets, benchmark its performance on manually annotated data, and show that it outperforms a popular offline approach. |
| Tasks | Denoising, Dictionary Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6832-onacid-online-analysis-of-calcium-imaging-data-in-real-time |
| http://papers.nips.cc/paper/6832-onacid-online-analysis-of-calcium-imaging-data-in-real-time.pdf | |
| PWC | https://paperswithcode.com/paper/onacid-online-analysis-of-calcium-imaging |
| Repo | |
| Framework | |
Inter-Patient ECG Heartbeat Classification with Temporal VCG Optimized by PSO
| Title | Inter-Patient ECG Heartbeat Classification with Temporal VCG Optimized by PSO |
| Authors | Gabriel Garcia, Gladston Moreira, David Menotti, Eduardo Luz |
| Abstract | Classifying arrhythmias can be a tough task for a human being and automating this task is highly desirable. Nevertheless fully automatic arrhythmia classification through Electrocardiogram (ECG) signals is a challenging task when the inter-patient paradigm is considered. For the inter-patient paradigm, classifiers are evaluated on signals of unknown subjects, resembling the real world scenario. In this work, we explore a novel ECG representation based on vectorcardiogram (VCG), called temporal vectorcardiogram (TVCG), along with a complex network for feature extraction. We also fine-tune the SVM classifier and perform feature selection with a particle swarm optimization (PSO) algorithm. Results for the inter-patient paradigm show that the proposed method achieves the results comparable to state-of-the-art in MIT-BIH database (53% of Positive predictive (+P) for the Supraventricular ectopic beat (S) class and 87.3% of Sensitivity (Se) for the Ventricular ectopic beat (V) class) that TVCG is a richer representation of the heartbeat and that it could be useful for problems involving the cardiac signal and pattern recognition.* Source code available from http://www.decom.ufop.br/csilab/site_media/uploads/code/tvcg_pso.zip |
| Tasks | Arrhythmia Detection, ECG Classification, Electrocardiography (ECG), Feature Selection, Heartbeat Classification |
| Published | 2017-09-05 |
| URL | https://doi.org/10.1038/s41598-017-09837-3 |
| https://www.nature.com/articles/s41598-017-09837-3.pdf | |
| PWC | https://paperswithcode.com/paper/inter-patient-ecg-heartbeat-classification |
| Repo | |
| Framework | |
Shape and Material from Sound
| Title | Shape and Material from Sound |
| Authors | Zhoutong Zhang, Qiujia Li, Zhengjia Huang, Jiajun Wu, Josh Tenenbaum, Bill Freeman |
| Abstract | Hearing an object falling onto the ground, humans can recover rich information including its rough shape, material, and falling height. In this paper, we build machines to approximate such competency. We first mimic human knowledge of the physical world by building an efficient, physics-based simulation engine. Then, we present an analysis-by-synthesis approach to infer properties of the falling object. We further accelerate the process by learning a mapping from a sound wave to object properties, and using the predicted values to initialize the inference. This mapping can be viewed as an approximation of human commonsense learned from past experience. Our model performs well on both synthetic audio clips and real recordings without requiring any annotated data. We conduct behavior studies to compare human responses with ours on estimating object shape, material, and falling height from sound. Our model achieves near-human performance. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6727-shape-and-material-from-sound |
| http://papers.nips.cc/paper/6727-shape-and-material-from-sound.pdf | |
| PWC | https://paperswithcode.com/paper/shape-and-material-from-sound |
| Repo | |
| Framework | |
Bilingual Word Embeddings with Bucketed CNN for Parallel Sentence Extraction
| Title | Bilingual Word Embeddings with Bucketed CNN for Parallel Sentence Extraction |
| Authors | Jeenu Grover, Pabitra Mitra |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3003/ |
| https://www.aclweb.org/anthology/P17-3003 | |
| PWC | https://paperswithcode.com/paper/bilingual-word-embeddings-with-bucketed-cnn |
| Repo | |
| Framework | |
Cross-language Learning with Adversarial Neural Networks
| Title | Cross-language Learning with Adversarial Neural Networks |
| Authors | Shafiq Joty, Preslav Nakov, Llu{'\i}s M{`a}rquez, Israa Jaradat |
| Abstract | We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system. |
| Tasks | Community Question Answering, Domain Adaptation, Machine Translation, Question Answering, Question Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1024/ |
| https://www.aclweb.org/anthology/K17-1024 | |
| PWC | https://paperswithcode.com/paper/cross-language-learning-with-adversarial |
| Repo | |
| Framework | |
Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation
| Title | Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1000/ |
| https://www.aclweb.org/anthology/Y17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-31st-pacific-asia |
| Repo | |
| Framework | |
Semantic Similarity of Arabic Sentences with Word Embeddings
| Title | Semantic Similarity of Arabic Sentences with Word Embeddings |
| Authors | El Moatez Billah Nagoudi, Didier Schwab |
| Abstract | Semantic textual similarity is the basis of countless applications and plays an important role in diverse areas, such as information retrieval, plagiarism detection, information extraction and machine translation. This article proposes an innovative word embedding-based system devoted to calculate the semantic similarity in Arabic sentences. The main idea is to exploit vectors as word representations in a multidimensional space in order to capture the semantic and syntactic properties of words. IDF weighting and Part-of-Speech tagging are applied on the examined sentences to support the identification of words that are highly descriptive in each sentence. The performance of our proposed system is confirmed through the Pearson correlation between our assigned semantic similarity scores and human judgments. |
| Tasks | Information Retrieval, Machine Translation, Part-Of-Speech Tagging, Semantic Similarity, Semantic Textual Similarity, Text Classification, Text Summarization, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1303/ |
| https://www.aclweb.org/anthology/W17-1303 | |
| PWC | https://paperswithcode.com/paper/semantic-similarity-of-arabic-sentences-with |
| Repo | |
| Framework | |
Chinese Zero Pronoun Resolution with Deep Memory Network
| Title | Chinese Zero Pronoun Resolution with Deep Memory Network |
| Authors | Qingyu Yin, Yu Zhang, Weinan Zhang, Ting Liu |
| Abstract | Existing approaches for Chinese zero pronoun resolution typically utilize only syntactical and lexical features while ignoring semantic information. The fundamental reason is that zero pronouns have no descriptive information, which brings difficulty in explicitly capturing their semantic similarities with antecedents. Meanwhile, representing zero pronouns is challenging since they are merely gaps that convey no actual content. In this paper, we address this issue by building a deep memory network that is capable of encoding zero pronouns into vector representations with information obtained from their contexts and potential antecedents. Consequently, our resolver takes advantage of semantic information by using these continuous distributed representations. Experiments on the OntoNotes 5.0 dataset show that the proposed memory network could substantially outperform the state-of-the-art systems in various experimental settings. |
| Tasks | Chinese Zero Pronoun Resolution, Feature Engineering, Information Retrieval |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1135/ |
| https://www.aclweb.org/anthology/D17-1135 | |
| PWC | https://paperswithcode.com/paper/chinese-zero-pronoun-resolution-with-deep |
| Repo | |
| Framework | |
An Adaptable Lexical Simplification Architecture for Major Ibero-Romance Languages
| Title | An Adaptable Lexical Simplification Architecture for Major Ibero-Romance Languages |
| Authors | Daniel Ferr{'e}s, Horacio Saggion, Xavier G{'o}mez Guinovart |
| Abstract | Lexical Simplification is the task of reducing the lexical complexity of textual documents by replacing difficult words with easier to read (or understand) expressions while preserving the original meaning. The development of robust pipelined multilingual architectures able to adapt to new languages is of paramount importance in lexical simplification. This paper describes and evaluates a modular hybrid linguistic-statistical Lexical Simplifier that deals with the four major Ibero-Romance Languages: Spanish, Portuguese, Catalan, and Galician. The architecture of the system is the same for the four languages addressed, only the language resources used during simplification are language specific. |
| Tasks | Lexical Simplification, Text Simplification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5406/ |
| https://www.aclweb.org/anthology/W17-5406 | |
| PWC | https://paperswithcode.com/paper/an-adaptable-lexical-simplification |
| Repo | |
| Framework | |
End-to-End Differentiable Adversarial Imitation Learning
| Title | End-to-End Differentiable Adversarial Imitation Learning |
| Authors | Nir Baram, Oron Anschel, Itai Caspi, Shie Mannor |
| Abstract | Generative Adversarial Networks (GANs) have been successfully applied to the problem of policy imitation in a model-free setup. However, the computation graph of GANs, that include a stochastic policy as the generative model, is no longer differentiable end-to-end, which requires the use of high-variance gradient estimation. In this paper, we introduce the Model-based Generative Adversarial Imitation Learning (MGAIL) algorithm. We show how to use a forward model to make the computation fully differentiable, which enables training policies using the exact gradient of the discriminator. The resulting algorithm trains competent policies using relatively fewer expert samples and interactions with the environment. We test it on both discrete and continuous action domains and report results that surpass the state-of-the-art. |
| Tasks | Imitation Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=586 |
| http://proceedings.mlr.press/v70/baram17a/baram17a.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-differentiable-adversarial |
| Repo | |
| Framework | |
Domain Attention with an Ensemble of Experts
| Title | Domain Attention with an Ensemble of Experts |
| Authors | Young-Bum Kim, Karl Stratos, Dongchan Kim |
| Abstract | An important problem in domain adaptation is to quickly generalize to a new domain with limited supervision given K existing domains. One approach is to retrain a global model across all K + 1 domains using standard techniques, for instance Daum{'e} III (2009). However, it is desirable to adapt without having to re-estimate a global model from scratch each time a new domain with potentially new intents and slots is added. We describe a solution based on attending an ensemble of domain experts. We assume K domain specific intent and slot models trained on respective domains. When given domain K + 1, our model uses a weighted combination of the K domain experts{'} feedback along with its own opinion to make predictions on the new domain. In experiments, the model significantly outperforms baselines that do not use domain adaptation and also performs better than the full retraining approach. |
| Tasks | Domain Adaptation, Spoken Language Understanding |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1060/ |
| https://www.aclweb.org/anthology/P17-1060 | |
| PWC | https://paperswithcode.com/paper/domain-attention-with-an-ensemble-of-experts |
| Repo | |
| Framework | |
