Paper Group NANR 118
Complex Word Identification Using Character n-grams. 4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications. Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media. Neural Event Extraction from Movies Description. A Multi-lingual Multi-task Arc …
Complex Word Identification Using Character n-grams
| Title | Complex Word Identification Using Character n-grams |
| Authors | Maja Popovi{'c} |
| Abstract | This paper investigates the use of character n-gram frequencies for identifying complex words in English, German and Spanish texts. The approach is based on the assumption that complex words are likely to contain different character sequences than simple words. The multinomial Naive Bayes classifier was used with n-grams of different lengths as features, and the best results were obtained for the combination of 2-grams and 4-grams. This variant was submitted to the Complex Word Identification Shared Task 2018 for all texts and achieved F-scores between 70{%} and 83{%}. The system was ranked in the middle range for all English texts, as third of fourteen submissions for German, and as tenth of seventeen submissions for Spanish. The method is not very convenient for the cross-language task, achieving only 59{%} on the French text. |
| Tasks | Complex Word Identification, Lexical Simplification, Machine Translation, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0541/ |
| https://www.aclweb.org/anthology/W18-0541 | |
| PWC | https://paperswithcode.com/paper/complex-word-identification-using-character-n |
| Repo | |
| Framework | |
4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications
| Title | 4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications |
| Authors | Shiyang Cheng, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou |
| Abstract | The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases. To this end, we propose 4DFAB, a new large scale database of dynamic high resolution 3D faces (over 1,800,000 3D meshes). 4DFAB contain recordings of 180 subjects captured in four different sessions spanned over a five-year period. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. In this paper, we conduct several experiments and demonstrate the usefulness of the database in various applications. The database will be made publicly available for research purposes. |
| Tasks | Facial Expression Recognition |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Cheng_4DFAB_A_Large_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Cheng_4DFAB_A_Large_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/4dfab-a-large-scale-4d-database-for-facial |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media
| Title | Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1100/ |
| https://www.aclweb.org/anthology/W18-1100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-12 |
| Repo | |
| Framework | |
Neural Event Extraction from Movies Description
| Title | Neural Event Extraction from Movies Description |
| Authors | Alex Tozzo, Dejan Jovanovi{'c}, Mohamed Amer |
| Abstract | We present a novel approach for event extraction and abstraction from movie descriptions. Our event frame consists of {}who{''}, {}did what{''} {}to whom{''}, {}where{''}, and {``}when{''}. We formulate our problem using a recurrent neural network, enhanced with structural features extracted from syntactic parser, and trained using curriculum learning by progressively increasing the difficulty of the sentences. Our model serves as an intermediate step towards question answering systems, visual storytelling, and story completion tasks. We evaluate our approach on MovieQA dataset. | |
| Tasks | Machine Translation, Question Answering, Story Completion, Visual Storytelling |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1507/ |
| https://www.aclweb.org/anthology/W18-1507 | |
| PWC | https://paperswithcode.com/paper/neural-event-extraction-from-movies |
| Repo | |
| Framework | |
A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling
| Title | A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling |
| Authors | Ying Lin, Shengqi Yang, Veselin Stoyanov, Heng Ji |
| Abstract | We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer models using two layers of parameter sharing. On the first layer, we construct the basis of the architecture to provide universal word representation and feature extraction capability for all models. On the second level, we adopt different parameter sharing strategies for different transfer schemes. This architecture proves to be particularly effective for low-resource settings, when there are less than 200 training sentences for the target task. Using Name Tagging as a target task, our approach achieved 4.3{%}-50.5{%} absolute F-score gains compared to the mono-lingual single-task baseline model. |
| Tasks | Abstractive Text Summarization, Machine Translation, Multi-Task Learning, Part-Of-Speech Tagging, Text Summarization, Transfer Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1074/ |
| https://www.aclweb.org/anthology/P18-1074 | |
| PWC | https://paperswithcode.com/paper/a-multi-lingual-multi-task-architecture-for |
| Repo | |
| Framework | |
Catching Idiomatic Expressions in EFL Essays
| Title | Catching Idiomatic Expressions in EFL Essays |
| Authors | Michael Flor, Beata Beigman Klebanov |
| Abstract | This paper presents an exploratory study on large-scale detection of idiomatic expressions in essays written by non-native speakers of English. We describe a computational search procedure for automatic detection of idiom-candidate phrases in essay texts. The study used a corpus of essays written during a standardized examination of English language proficiency. Automatically-flagged candidate expressions were manually annotated for idiomaticity. The study found that idioms are widely used in EFL essays. The study also showed that a search algorithm that accommodates the syntactic and lexical exibility of idioms can increase the recall of idiom instances by 30{%}, but it also increases the amount of false positives. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0905/ |
| https://www.aclweb.org/anthology/W18-0905 | |
| PWC | https://paperswithcode.com/paper/catching-idiomatic-expressions-in-efl-essays |
| Repo | |
| Framework | |
Neural Monkey: The Current State and Beyond
| Title | Neural Monkey: The Current State and Beyond |
| Authors | Jind{\v{r}}ich Helcl, Jind{\v{r}}ich Libovick{'y}, Tom Kocmi, Tom{'a}{\v{s}} Musil, Ond{\v{r}}ej C{'\i}fka, Du{\v{s}}an Vari{\v{s}}, Ond{\v{r}}ej Bojar |
| Abstract | |
| Tasks | Image Captioning, Machine Translation, Optical Character Recognition, Sentiment Analysis, Text Summarization |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1816/ |
| https://www.aclweb.org/anthology/W18-1816 | |
| PWC | https://paperswithcode.com/paper/neural-monkey-the-current-state-and-beyond |
| Repo | |
| Framework | |
The MonPaGe_HA Database for the Documentation of Spoken French Throughout Adulthood
| Title | The MonPaGe_HA Database for the Documentation of Spoken French Throughout Adulthood |
| Authors | C{'e}cile Fougeron, V{'e}ronique Delvaux, Lucie M{'e}nard, Marina Laganaro |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1679/ |
| https://www.aclweb.org/anthology/L18-1679 | |
| PWC | https://paperswithcode.com/paper/the-monpage_ha-database-for-the-documentation |
| Repo | |
| Framework | |
Word2net: Deep Representations of Language
| Title | Word2net: Deep Representations of Language |
| Authors | Maja Rudolph, Francisco Ruiz, David Blei |
| Abstract | Word embeddings extract semantic features of words from large datasets of text. Most embedding methods rely on a log-bilinear model to predict the occurrence of a word in a context of other words. Here we propose word2net, a method that replaces their linear parametrization with neural networks. For each term in the vocabulary, word2net posits a neural network that takes the context as input and outputs a probability of occurrence. Further, word2net can use the hierarchical organization of its word networks to incorporate additional meta-data, such as syntactic features, into the embedding model. For example, we show how to share parameters across word networks to develop an embedding model that includes part-of-speech information. We study word2net with two datasets, a collection of Wikipedia articles and a corpus of U.S. Senate speeches. Quantitatively, we found that word2net outperforms popular embedding methods on predicting held- out words and that sharing parameters based on part of speech further boosts performance. Qualitatively, word2net learns interpretable semantic representations and, compared to vector-based methods, better incorporates syntactic information. |
| Tasks | Word Embeddings |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkJd_y-Cb |
| https://openreview.net/pdf?id=SkJd_y-Cb | |
| PWC | https://paperswithcode.com/paper/word2net-deep-representations-of-language |
| Repo | |
| Framework | |
LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers
| Title | LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers |
| Authors | Lorenzo Baraldi, Matthijs Douze, Rita Cucchiara, Hervé Jégou |
| Abstract | This paper considers a learnable approach for comparing and aligning videos. Our architecture builds upon and revisits temporal match kernels within neural networks: we propose a new temporal layer that finds temporal alignments by maximizing the scores between two sequences of vectors, according to a time-sensitive similarity metric parametrized in the Fourier domain. We learn this layer with a temporal proposal strategy, in which we minimize a triplet loss that takes into account both the localization accuracy and the recognition rate. We evaluate our approach on video alignment, copy detection and event retrieval. Our approach outperforms the state on the art on temporal video alignment and video copy detection datasets in comparable setups. It also attains the best reported results for particular event search, while precisely aligning videos. |
| Tasks | Video Alignment |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Baraldi_LAMV_Learning_to_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Baraldi_LAMV_Learning_to_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/lamv-learning-to-align-and-match-videos-with |
| Repo | |
| Framework | |
The Social and the Neural Network: How to Make Natural Language Processing about People again
| Title | The Social and the Neural Network: How to Make Natural Language Processing about People again |
| Authors | Dirk Hovy |
| Abstract | Over the years, natural language processing has increasingly focused on tasks that can be solved by statistical models, but ignored the social aspects of language. These limitations are in large part due to historically available data and the limitations of the models, but have narrowed our focus and biased the tools demographically. However, with the increased availability of data sets including socio-demographic information and more expressive (neural) models, we have the opportunity to address both issues. I argue that this combination can broaden the focus of NLP to solve a whole new range of tasks, enable us to generate novel linguistic insights, and provide fairer tools for everyone. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1106/ |
| https://www.aclweb.org/anthology/W18-1106 | |
| PWC | https://paperswithcode.com/paper/the-social-and-the-neural-network-how-to-make |
| Repo | |
| Framework | |
Test Sets for Chinese Nonlocal Dependency Parsing
| Title | Test Sets for Chinese Nonlocal Dependency Parsing |
| Authors | Manjuan Duan, William Schuler |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1715/ |
| https://www.aclweb.org/anthology/L18-1715 | |
| PWC | https://paperswithcode.com/paper/test-sets-for-chinese-nonlocal-dependency |
| Repo | |
| Framework | |
SandhiKosh: A Benchmark Corpus for Evaluating Sanskrit Sandhi Tools
| Title | SandhiKosh: A Benchmark Corpus for Evaluating Sanskrit Sandhi Tools |
| Authors | Shubham Bhardwaj, Neelamadhav Gantayat, Nikhil Chaturvedi, Rahul Garg, Sumeet Agarwal |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1712/ |
| https://www.aclweb.org/anthology/L18-1712 | |
| PWC | https://paperswithcode.com/paper/sandhikosh-a-benchmark-corpus-for-evaluating |
| Repo | |
| Framework | |
Stochastic Expectation Maximization with Variance Reduction
| Title | Stochastic Expectation Maximization with Variance Reduction |
| Authors | Jianfei Chen, Jun Zhu, Yee Whye Teh, Tong Zhang |
| Abstract | Expectation-Maximization (EM) is a popular tool for learning latent variable models, but the vanilla batch EM does not scale to large data sets because the whole data set is needed at every E-step. Stochastic Expectation Maximization (sEM) reduces the cost of E-step by stochastic approximation. However, sEM has a slower asymptotic convergence rate than batch EM, and requires a decreasing sequence of step sizes, which is difficult to tune. In this paper, we propose a variance reduced stochastic EM (sEM-vr) algorithm inspired by variance reduced stochastic gradient descent algorithms. We show that sEM-vr has the same exponential asymptotic convergence rate as batch EM. Moreover, sEM-vr only requires a constant step size to achieve this rate, which alleviates the burden of parameter tuning. We compare sEM-vr with batch EM, sEM and other algorithms on Gaussian mixture models and probabilistic latent semantic analysis, and sEM-vr converges significantly faster than these baselines. |
| Tasks | Latent Variable Models |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8021-stochastic-expectation-maximization-with-variance-reduction |
| http://papers.nips.cc/paper/8021-stochastic-expectation-maximization-with-variance-reduction.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-expectation-maximization-with |
| Repo | |
| Framework | |
Spoken Dialogue for Information Navigation
| Title | Spoken Dialogue for Information Navigation |
| Authors | Alex Papangelis, ros, Panagiotis Papadakos, Yannis Stylianou, Yannis Tzitzikas |
| Abstract | Aiming to expand the current research paradigm for training conversational AI agents that can address real-world challenges, we take a step away from traditional slot-filling goal-oriented spoken dialogue systems (SDS) and model the dialogue in a way that allows users to be more expressive in describing their needs. The goal is to help users make informed decisions rather than being fed matching items. To this end, we describe the Linked-Data SDS (LD-SDS), a system that exploits semantic knowledge bases that connect to linked data, and supports complex constraints and preferences. We describe the required changes in language understanding and state tracking, and the need for mined features, and we report the promising results (in terms of semantic errors, effort, etc) of a preliminary evaluation after training two statistical dialogue managers in various conditions. |
| Tasks | Information Retrieval, Slot Filling, Spoken Dialogue Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5025/ |
| https://www.aclweb.org/anthology/W18-5025 | |
| PWC | https://paperswithcode.com/paper/spoken-dialogue-for-information-navigation |
| Repo | |
| Framework | |
