Paper Group NANR 73
community2vec: Vector representations of online communities encode semantic relationships. Key-value Attention Mechanism for Neural Machine Translation. Character and Subword-Based Word Representation for Neural Language Modeling Prediction. Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neura …
community2vec: Vector representations of online communities encode semantic relationships
| Title | community2vec: Vector representations of online communities encode semantic relationships |
| Authors | Trevor Martin |
| Abstract | Vector embeddings of words have been shown to encode meaningful semantic relationships that enable solving of complex analogies. This vector embedding concept has been extended successfully to many different domains and in this paper we both create and visualize vector representations of an unstructured collection of online communities based on user participation. Further, we quantitatively and qualitatively show that these representations allow solving of semantically meaningful community analogies and also other more general types of relationships. These results could help improve community recommendation engines and also serve as a tool for sociological studies of community relatedness. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2904/ |
| https://www.aclweb.org/anthology/W17-2904 | |
| PWC | https://paperswithcode.com/paper/community2vec-vector-representations-of |
| Repo | |
| Framework | |
Key-value Attention Mechanism for Neural Machine Translation
| Title | Key-value Attention Mechanism for Neural Machine Translation |
| Authors | Hideya Mino, Masao Utiyama, Eiichiro Sumita, Takenobu Tokunaga |
| Abstract | In this paper, we propose a neural machine translation (NMT) with a key-value attention mechanism on the source-side encoder. The key-value attention mechanism separates the source-side content vector into two types of memory known as the key and the value. The key is used for calculating the attention distribution, and the value is used for encoding the context representation. Experiments on three different tasks indicate that our model outperforms an NMT model with a conventional attention mechanism. Furthermore, we perform experiments with a conventional NMT framework, in which a part of the initial value of a weight matrix is set to zero so that the matrix is as the same initial-state as the key-value attention mechanism. As a result, we obtain comparable results with the key-value attention mechanism without changing the network structure. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2049/ |
| https://www.aclweb.org/anthology/I17-2049 | |
| PWC | https://paperswithcode.com/paper/key-value-attention-mechanism-for-neural |
| Repo | |
| Framework | |
Character and Subword-Based Word Representation for Neural Language Modeling Prediction
| Title | Character and Subword-Based Word Representation for Neural Language Modeling Prediction |
| Authors | Matthieu Labeau, Alex Allauzen, re |
| Abstract | Most of neural language models use different kinds of embeddings for word prediction. While word embeddings can be associated to each word in the vocabulary or derived from characters as well as factored morphological decomposition, these word representations are mainly used to parametrize the input, i.e. the context of prediction. This work investigates the effect of using subword units (character and factored morphological decomposition) to build output representations for neural language modeling. We present a case study on Czech, a morphologically-rich language, experimenting with different input and output representations. When working with the full training vocabulary, despite unstable training, our experiments show that augmenting the output word representations with character-based embeddings can significantly improve the performance of the model. Moreover, reducing the size of the output look-up table, to let the character-based embeddings represent rare words, brings further improvement. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4101/ |
| https://www.aclweb.org/anthology/W17-4101 | |
| PWC | https://paperswithcode.com/paper/character-and-subword-based-word |
| Repo | |
| Framework | |
Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit
| Title | Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit |
| Authors | Laurence Aitchison, Lloyd Russell, Adam M. Packer, Jinyao Yan, Philippe Castonguay, Michael Hausser, Srinivas C. Turaga |
| Abstract | Population activity measurement by calcium imaging can be combined with cellular resolution optogenetic activity perturbations to enable the mapping of neural connectivity in vivo. This requires accurate inference of perturbed and unperturbed neural activity from calcium imaging measurements, which are noisy and indirect, and can also be contaminated by photostimulation artifacts. We have developed a new fully Bayesian approach to jointly inferring spiking activity and neural connectivity from in vivo all-optical perturbation experiments. In contrast to standard approaches that perform spike inference and analysis in two separate maximum-likelihood phases, our joint model is able to propagate uncertainty in spike inference to the inference of connectivity and vice versa. We use the framework of variational autoencoders to model spiking activity using discrete latent variables, low-dimensional latent common input, and sparse spike-and-slab generalized linear coupling between neurons. Additionally, we model two properties of the optogenetic perturbation: off-target photostimulation and photostimulation transients. Using this model, we were able to fit models on 30 minutes of data in just 10 minutes. We performed an all-optical circuit mapping experiment in primary visual cortex of the awake mouse, and use our approach to predict neural connectivity between excitatory neurons in layer 2/3. Predicted connectivity is sparse and consistent with known correlations with stimulus tuning, spontaneous correlation and distance. |
| Tasks | Bayesian Inference |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6940-model-based-bayesian-inference-of-neural-activity-and-connectivity-from-all-optical-interrogation-of-a-neural-circuit |
| http://papers.nips.cc/paper/6940-model-based-bayesian-inference-of-neural-activity-and-connectivity-from-all-optical-interrogation-of-a-neural-circuit.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-bayesian-inference-of-neural |
| Repo | |
| Framework | |
A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output
| Title | A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output |
| Authors | Xing Niu, Marianna Martindale, Marine Carpuat |
| Abstract | Stylistic variations of language, such as formality, carry speakers{'} intention beyond literal meaning and should be conveyed adequately in translation. We propose to use lexical formality models to control the formality level of machine translation output. We demonstrate the effectiveness of our approach in empirical evaluations, as measured by automatic metrics and human assessments. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1299/ |
| https://www.aclweb.org/anthology/D17-1299 | |
| PWC | https://paperswithcode.com/paper/a-study-of-style-in-machine-translation |
| Repo | |
| Framework | |
A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light
| Title | A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light |
| Authors | Mahdi Abbaspour Tehrani, Thabo Beeler, Anselm Grundhofer |
| Abstract | Calibrating the intrinsic properties of a camera is one of the fundamental tasks required for a variety of computer vision and image processing tasks. The precise measurement of focal length, location of the principal point as well as distortion parameters of the lens is crucial, for example, for 3D reconstruction. Although a variety of methods exist to achieve this goal, they are often cumbersome to carry out, require substantial manual interaction, expert knowledge, and a significant operating volume. We propose a novel calibration method based on the usage of directionally encoded light rays for estimating the intrinsic parameters. It enables a fully automatic calibration with a small device mounted close to the front lens element and still enables an accuracy comparable to standard methods even when the lens is focused up to infinity. Our method overcomes the mentioned limitations since it guarantees an accurate calibration without any human intervention while requiring only a limited amount of space. Besides that, the approach also allows to estimate the distance of the focal plane as well as the size of the aperture. We demonstrate the advantages of the proposed method by evaluating several camera/lens configurations using prototypical devices. |
| Tasks | 3D Reconstruction, Calibration |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Tehrani_A_Practical_Method_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Tehrani_A_Practical_Method_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-practical-method-for-fully-automatic |
| Repo | |
| Framework | |
Stock Market Prediction with Deep Learning: A Character-based Neural Language Model for Event-based Trading
| Title | Stock Market Prediction with Deep Learning: A Character-based Neural Language Model for Event-based Trading |
| Authors | Leonardo dos Santos Pinheiro, Mark Dras |
| Abstract | |
| Tasks | Feature Engineering, Feature Selection, Language Modelling, Stock Market Prediction, Stock Prediction, Text Classification |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1001/ |
| https://www.aclweb.org/anthology/U17-1001 | |
| PWC | https://paperswithcode.com/paper/stock-market-prediction-with-deep-learning-a |
| Repo | |
| Framework | |
SuperOCR for ALTA 2017 Shared Task
| Title | SuperOCR for ALTA 2017 Shared Task |
| Authors | Yufei Wang |
| Abstract | |
| Tasks | Language Modelling, Named Entity Recognition, Optical Character Recognition |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1016/ |
| https://www.aclweb.org/anthology/U17-1016 | |
| PWC | https://paperswithcode.com/paper/superocr-for-alta-2017-shared-task |
| Repo | |
| Framework | |
Effective search space reduction for spell correction using character neural embeddings
| Title | Effective search space reduction for spell correction using character neural embeddings |
| Authors | P, Harshit e |
| Abstract | We present a novel, unsupervised, and distance measure agnostic method for search space reduction in spell correction using neural character embeddings. The embeddings are learned by skip-gram word2vec training on sequences generated from dictionary words in a phonetic information-retentive manner. We report a very high performance in terms of both success rates and reduction of search space on the Birkbeck spelling error corpus. To the best of our knowledge, this is the first application of word2vec to spell correction. |
| Tasks | Optical Character Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2027/ |
| https://www.aclweb.org/anthology/E17-2027 | |
| PWC | https://paperswithcode.com/paper/effective-search-space-reduction-for-spell |
| Repo | |
| Framework | |
MUSST: A Multilingual Syntactic Simplification Tool
| Title | MUSST: A Multilingual Syntactic Simplification Tool |
| Authors | Carolina Scarton, Alessio Palmero Aprosio, Sara Tonelli, Tamara Mart{'\i}n Wanton, Lucia Specia |
| Abstract | We describe MUSST, a multilingual syntactic simplification tool. The tool supports sentence simplifications for English, Italian and Spanish, and can be easily extended to other languages. Our implementation includes a set of general-purpose simplification rules, as well as a sentence selection module (to select sentences to be simplified) and a confidence model (to select only promising simplifications). The tool was implemented in the context of the European project SIMPATICO on text simplification for Public Administration (PA) texts. Our evaluation on sentences in the PA domain shows that we obtain correct simplifications for 76{%} of the simplified cases in English, 71{%} of the cases in Spanish. For Italian, the results are lower (38{%}) but the tool is still under development. |
| Tasks | Lexical Simplification, Text Simplification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3007/ |
| https://www.aclweb.org/anthology/I17-3007 | |
| PWC | https://paperswithcode.com/paper/musst-a-multilingual-syntactic-simplification |
| Repo | |
| Framework | |
Guess What: A Question Answering Game via On-demand Knowledge Validation
| Title | Guess What: A Question Answering Game via On-demand Knowledge Validation |
| Authors | Yu-Sheng Li, Chien-Hui Tseng, Chian-Yun Huang, Wei-Yun Ma |
| Abstract | In this paper, we propose an idea of ondemand knowledge validation and fulfill the idea through an interactive Question-Answering (QA) game system, which is named Guess What. An object (e.g. dog) is first randomly chosen by the system, and then a user can repeatedly ask the system questions in natural language to guess what the object is. The system would respond with yes/no along with a confidence score. Some useful hints can also be given if needed. The proposed framework provides a pioneering example of on-demand knowledge validation in dialog environment to address such needs in AI agents/chatbots. Moreover, the released log data that the system gathered can be used to identify the most critical concepts/attributes of an existing knowledge base, which reflects human{'}s cognition about the world. |
| Tasks | Chatbot, Question Answering |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3015/ |
| https://www.aclweb.org/anthology/I17-3015 | |
| PWC | https://paperswithcode.com/paper/guess-what-a-question-answering-game-via-on |
| Repo | |
| Framework | |
Using Gaze Data to Predict Multiword Expressions
| Title | Using Gaze Data to Predict Multiword Expressions |
| Authors | Omid Rohanian, Shiva Taslimipoor, Victoria Yaneva, Le An Ha |
| Abstract | In recent years gaze data has been increasingly used to improve and evaluate NLP models due to the fact that it carries information about the cognitive processing of linguistic phenomena. In this paper we conduct a preliminary study towards the automatic identification of multiword expressions based on gaze features from native and non-native speakers of English. We report comparisons between a part-of-speech (POS) and frequency baseline to: i) a prediction model based solely on gaze data and ii) a combined model of gaze data, POS and frequency. In spite of the challenging nature of the task, best performance was achieved by the latter. Furthermore, we explore how the type of gaze data (from native versus non-native speakers) affects the prediction, showing that data from the two groups is discriminative to an equal degree for the task. Finally, we show that late processing measures are more predictive than early ones, which is in line with previous research on idioms and other formulaic structures. |
| Tasks | Part-Of-Speech Tagging, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1078/ |
| https://doi.org/10.26615/978-954-452-049-6_078 | |
| PWC | https://paperswithcode.com/paper/using-gaze-data-to-predict-multiword |
| Repo | |
| Framework | |
Follow the Moving Leader in Deep Learning
| Title | Follow the Moving Leader in Deep Learning |
| Authors | Shuai Zheng, James T. Kwok |
| Abstract | Deep networks are highly nonlinear and difficult to optimize. During training, the parameter iterate may move from one local basin to another, or the data distribution may even change. Inspired by the close connection between stochastic optimization and online learning, we propose a variant of the follow the regularized leader (FTRL) algorithm called follow the moving leader (FTML). Unlike the FTRL family of algorithms, the recent samples are weighted more heavily in each iteration and so FTML can adapt more quickly to changes. We show that FTML enjoys the nice properties of RMSprop and Adam, while avoiding their pitfalls. Experimental results on a number of deep learning models and tasks demonstrate that FTML converges quickly, and outperforms other state-of-the-art optimizers. |
| Tasks | Stochastic Optimization |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=810 |
| http://proceedings.mlr.press/v70/zheng17a/zheng17a.pdf | |
| PWC | https://paperswithcode.com/paper/follow-the-moving-leader-in-deep-learning |
| Repo | |
| Framework | |
Comparing Recurring Lexico-Syntactic Trees (RLTs) and Ngram Techniques for Extended Phraseology Extraction
| Title | Comparing Recurring Lexico-Syntactic Trees (RLTs) and Ngram Techniques for Extended Phraseology Extraction |
| Authors | Agn{`e}s Tutin, Olivier Kraif |
| Abstract | This paper aims at assessing to what extent a syntax-based method (Recurring Lexico-syntactic Trees (RLT) extraction) allows us to extract large phraseological units such as prefabricated routines, e.g. {}as previously said{''} or {}as far as we/I know{''} in scientific writing. In order to evaluate this method, we compare it to the classical ngram extraction technique, on a subset of recurring segments including speech verbs in a French corpus of scientific writing. Results show that the LRT extraction technique is far more efficient for extended MWEs such as routines or collocations but performs more poorly for surface phenomena such as syntactic constructions or fully frozen expressions. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1724/ |
| https://www.aclweb.org/anthology/W17-1724 | |
| PWC | https://paperswithcode.com/paper/comparing-recurring-lexico-syntactic-trees |
| Repo | |
| Framework | |
The Event StoryLine Corpus: A New Benchmark for Causal and Temporal Relation Extraction
| Title | The Event StoryLine Corpus: A New Benchmark for Causal and Temporal Relation Extraction |
| Authors | Tommaso Caselli, Piek Vossen |
| Abstract | This paper reports on the Event StoryLine Corpus (ESC) v1.0, a new benchmark dataset for the temporal and causal relation detection. By developing this dataset, we also introduce a new task, the StoryLine Extraction from news data, which aims at extracting and classifying events relevant for stories, from across news documents spread in time and clustered around a single seminal event or topic. In addition to describing the dataset, we also report on three baselines systems whose results show the complexity of the task and suggest directions for the development of more robust systems. |
| Tasks | Natural Language Inference, Question Answering, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2711/ |
| https://www.aclweb.org/anthology/W17-2711 | |
| PWC | https://paperswithcode.com/paper/the-event-storyline-corpus-a-new-benchmark |
| Repo | |
| Framework | |
