Paper Group NANR 80
TakeLab-QA at SemEval-2017 Task 3: Classification Experiments for Answer Retrieval in Community QA. Universal Dependency Evaluation. Educational Content Generation for Business and Administration FL Courses with the NBU PLT Platform. Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association. Feature …
TakeLab-QA at SemEval-2017 Task 3: Classification Experiments for Answer Retrieval in Community QA
| Title | TakeLab-QA at SemEval-2017 Task 3: Classification Experiments for Answer Retrieval in Community QA |
| Authors | Filip {\v{S}}aina, Toni Kukurin, Lukrecija Pulji{'c}, Mladen Karan, Jan {\v{S}}najder |
| Abstract | In this paper we present the TakeLab-QA entry to SemEval 2017 task 3, which is a question-comment re-ranking problem. We present a classification based approach, including two supervised learning models {–} Support Vector Machines (SVM) and Convolutional Neural Networks (CNN). We use features based on different semantic similarity models (e.g., Latent Dirichlet Allocation), as well as features based on several types of pre-trained word embeddings. Moreover, we also use some hand-crafted task-specific features. For training, our system uses no external labeled data apart from that provided by the organizers. Our primary submission achieves a MAP-score of 81.14 and F1-score of 66.99 {–} ranking us 10th on the SemEval 2017 task 3, subtask A. |
| Tasks | Community Question Answering, Information Retrieval, Question Answering, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2055/ |
| https://www.aclweb.org/anthology/S17-2055 | |
| PWC | https://paperswithcode.com/paper/takelab-qa-at-semeval-2017-task-3 |
| Repo | |
| Framework | |
Universal Dependency Evaluation
| Title | Universal Dependency Evaluation |
| Authors | Joakim Nivre, Chiao-Ting Fang |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0411/ |
| https://www.aclweb.org/anthology/W17-0411 | |
| PWC | https://paperswithcode.com/paper/universal-dependency-evaluation |
| Repo | |
| Framework | |
Educational Content Generation for Business and Administration FL Courses with the NBU PLT Platform
| Title | Educational Content Generation for Business and Administration FL Courses with the NBU PLT Platform |
| Authors | Maria Stambolieva |
| Abstract | The paper presents part of an ongoing project of the Laboratory for Language Technologies of New Bulgarian University {–} {``}An e-Platform for Language Teaching (PLT){''} {–} the development of corpus-based teaching content for Business English courses. The presentation offers information on: 1/ corpus creation and corpus management with PLT; 2/ PLT corpus annotation; 3/ language task generation and the Language Task Bank (LTB); 4/ content transfer to the NBU Moodle platform, test generation and feedback on student performance. | |
| Tasks | Language Acquisition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7804/ |
| https://doi.org/10.26615/978-954-452-040-3_004 | |
| PWC | https://paperswithcode.com/paper/educational-content-generation-for-business |
| Repo | |
| Framework | |
Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association
| Title | Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association |
| Authors | Yasheng Wang, Yang Zhang, Bing Liu |
| Abstract | Although many sentiment lexicons in different languages exist, most are not comprehensive. In a recent sentiment analysis application, we used a large Chinese sentiment lexicon and found that it missed a large number of sentiment words in social media. This prompted us to make a new attempt to study sentiment lexicon expansion. This paper first poses the problem as a PU learning problem, which is a new formulation. It then proposes a new PU learning method suitable for our problem using a neural network. The results are enhanced further with a new dictionary-based technique and a novel polarity classification technique. Experimental results show that the proposed approach outperforms baseline methods greatly. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1059/ |
| https://www.aclweb.org/anthology/D17-1059 | |
| PWC | https://paperswithcode.com/paper/sentiment-lexicon-expansion-based-on-neural |
| Repo | |
| Framework | |
Feature Selection as Causal Inference: Experiments with Text Classification
| Title | Feature Selection as Causal Inference: Experiments with Text Classification |
| Authors | Michael J. Paul |
| Abstract | This paper proposes a matching technique for learning causal associations between word features and class labels in document classification. The goal is to identify more meaningful and generalizable features than with only correlational approaches. Experiments with sentiment classification show that the proposed method identifies interpretable word associations with sentiment and improves classification performance in a majority of cases. The proposed feature selection method is particularly effective when applied to out-of-domain data. |
| Tasks | Causal Inference, Document Classification, Domain Adaptation, Feature Selection, Sentiment Analysis, Text Classification |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1018/ |
| https://www.aclweb.org/anthology/K17-1018 | |
| PWC | https://paperswithcode.com/paper/feature-selection-as-causal-inference |
| Repo | |
| Framework | |
PyDial: A Multi-domain Statistical Dialogue System Toolkit
| Title | PyDial: A Multi-domain Statistical Dialogue System Toolkit |
| Authors | Stefan Ultes, Lina M. Rojas-Barahona, Pei-Hao Su, V, David yke, Dongho Kim, I{~n}igo Casanueva, Pawe{\l} Budzianowski, Nikola Mrk{\v{s}}i{'c}, Tsung-Hsien Wen, Milica Ga{\v{s}}i{'c}, Steve Young |
| Abstract | |
| Tasks | Dialogue Management, Speech Recognition, Speech Synthesis, Spoken Dialogue Systems, Text Generation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4013/ |
| https://www.aclweb.org/anthology/P17-4013 | |
| PWC | https://paperswithcode.com/paper/pydial-a-multi-domain-statistical-dialogue |
| Repo | |
| Framework | |
Learning Stable Stochastic Nonlinear Dynamical Systems
| Title | Learning Stable Stochastic Nonlinear Dynamical Systems |
| Authors | Jonas Umlauft, Sandra Hirche |
| Abstract | A data-driven identification of dynamical systems requiring only minimal prior knowledge is promising whenever no analytically derived model structure is available, e.g., from first principles in physics. However, meta-knowledge on the system’s behavior is often given and should be exploited: Stability as fundamental property is essential when the model is used for controller design or movement generation. Therefore, this paper proposes a framework for learning stable stochastic systems from data. We focus on identifying a state-dependent coefficient form of the nonlinear stochastic model which is globally asymptotically stable according to probabilistic Lyapunov methods. We compare our approach to other state of the art methods on real-world datasets in terms of flexibility and stability. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=531 |
| http://proceedings.mlr.press/v70/umlauft17a/umlauft17a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-stable-stochastic-nonlinear |
| Repo | |
| Framework | |
Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation
| Title | Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation |
| Authors | S Singh, hya, Ritesh Panjwani, Anoop Kunchukuttan, Pushpak Bhattacharyya |
| Abstract | In this paper, we empirically compare the two encoder-decoder neural machine translation architectures: convolutional sequence to sequence model (ConvS2S) and recurrent sequence to sequence model (RNNS2S) for English-Hindi language pair as part of IIT Bombay{'}s submission to WAT2017 shared task. We report the results for both English-Hindi and Hindi-English direction of language pair. |
| Tasks | Image Captioning, Language Modelling, Machine Translation, Question Answering, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5717/ |
| https://www.aclweb.org/anthology/W17-5717 | |
| PWC | https://paperswithcode.com/paper/comparing-recurrent-and-convolutional |
| Repo | |
| Framework | |
Grounding sound change in ideal observer models of perception
| Title | Grounding sound change in ideal observer models of perception |
| Authors | Zachary Burchill, T. Florian Jaeger |
| Abstract | An important predictor of historical sound change, functional load, fails to capture insights from speech perception. Building on ideal observer models of word recognition, we devise a new definition of functional load that incorporates both a priori predictability and perceptual information. We explore this new measure with a simple model and find that it outperforms traditional measures. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0703/ |
| https://www.aclweb.org/anthology/W17-0703 | |
| PWC | https://paperswithcode.com/paper/grounding-sound-change-in-ideal-observer |
| Repo | |
| Framework | |
Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames
| Title | Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames |
| Authors | Gongye Jin, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | This paper presents a method for applying automatically acquired knowledge to semantic role labeling (SRL). We use a large amount of automatically extracted knowledge to improve the performance of SRL. We present two varieties of knowledge, which we call surface case frames and deep case frames. Although the surface case frames are compiled from syntactic parses and can be used as rich syntactic knowledge, they have limited capability for resolving semantic ambiguity. To compensate the deficiency of the surface case frames, we compile deep case frames from automatic semantic roles. We also consider quality management for both types of knowledge in order to get rid of the noise brought from the automatic analyses. The experimental results show that Chinese SRL can be improved using automatically acquired knowledge and the quality management shows a positive effect on this task. |
| Tasks | Dependency Parsing, Machine Translation, Question Answering, Semantic Role Labeling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1054/ |
| https://www.aclweb.org/anthology/E17-1054 | |
| PWC | https://paperswithcode.com/paper/improving-chinese-semantic-role-labeling |
| Repo | |
| Framework | |
基於雙工音高感知模型之神經網路旋律抽取演算法 (The duplex model of pitch perception inspired neural network for melody extraction) [In Chinese]
| Title | 基於雙工音高感知模型之神經網路旋律抽取演算法 (The duplex model of pitch perception inspired neural network for melody extraction) [In Chinese] |
| Authors | Hsin Chou, Tai-Shih Chi |
| Abstract | |
| Tasks | Melody Extraction |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1017/ |
| https://www.aclweb.org/anthology/O17-1017 | |
| PWC | https://paperswithcode.com/paper/ao14eae3ec-aa1i-cc2ii12a14c3-the-duplex-model |
| Repo | |
| Framework | |
Delexicalized Word Embeddings for Cross-lingual Dependency Parsing
| Title | Delexicalized Word Embeddings for Cross-lingual Dependency Parsing |
| Authors | Mathieu Dehouck, Pascal Denis |
| Abstract | This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language. Specifically, this approach first constructs word vector representations that exploit structural (i.e., dependency-based) contexts but only considering the morpho-syntactic information associated with each word and its contexts. These delexicalized word embeddings, which can be trained on any set of languages and capture features shared across languages, are then used in combination with standard language-specific features to train a lexicalized parser in the target language. We evaluate our approach through experiments on a set of eight different languages that are part the Universal Dependencies Project. Our main results show that using such delexicalized embeddings, either trained in a monolingual or multilingual fashion, achieves significant improvements over monolingual baselines. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1023/ |
| https://www.aclweb.org/anthology/E17-1023 | |
| PWC | https://paperswithcode.com/paper/delexicalized-word-embeddings-for-cross |
| Repo | |
| Framework | |
Modeling Derivational Morphology in Ukrainian
| Title | Modeling Derivational Morphology in Ukrainian |
| Authors | Mariia Melymuka, Gabriella Lapesa, Max Kisselew, Sebastian Pad{'o} |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6928/ |
| https://www.aclweb.org/anthology/W17-6928 | |
| PWC | https://paperswithcode.com/paper/modeling-derivational-morphology-in-ukrainian |
| Repo | |
| Framework | |
Tandem Anchoring: a Multiword Anchor Approach for Interactive Topic Modeling
| Title | Tandem Anchoring: a Multiword Anchor Approach for Interactive Topic Modeling |
| Authors | Jeffrey Lund, Connor Cook, Kevin Seppi, Jordan Boyd-Graber |
| Abstract | Interactive topic models are powerful tools for those seeking to understand large collections of text. However, existing sampling-based interactive topic modeling approaches scale poorly to large data sets. Anchor methods, which use a single word to uniquely identify a topic, offer the speed needed for interactive work but lack both a mechanism to inject prior knowledge and lack the intuitive semantics needed for user-facing applications. We propose combinations of words as anchors, going beyond existing single word anchor algorithms{—}an approach we call {``}Tandem Anchors{''}. We begin with a synthetic investigation of this approach then apply the approach to interactive topic modeling in a user study and compare it to interactive and non-interactive approaches. Tandem anchors are faster and more intuitive than existing interactive approaches. | |
| Tasks | Document Classification, Information Retrieval, Sentiment Analysis, Topic Models |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1083/ |
| https://www.aclweb.org/anthology/P17-1083 | |
| PWC | https://paperswithcode.com/paper/tandem-anchoring-a-multiword-anchor-approach |
| Repo | |
| Framework | |
Tomography of the London Underground: a Scalable Model for Origin-Destination Data
| Title | Tomography of the London Underground: a Scalable Model for Origin-Destination Data |
| Authors | Nicolò Colombo, Ricardo Silva, Soong Moon Kang |
| Abstract | The paper addresses the classical network tomography problem of inferring local traffic given origin-destination observations. Focussing on large complex public transportation systems, we build a scalable model that exploits input-output information to estimate the unobserved link/station loads and the users path preferences. Based on the reconstruction of the users’ travel time distribution, the model is flexible enough to capture possible different path-choice strategies and correlations between users travelling on similar paths at similar times. The corresponding likelihood function is intractable for medium or large-scale networks and we propose two distinct strategies, namely the exact maximum-likelihood inference of an approximate but tractable model and the variational inference of the original intractable model. As an application of our approach, we consider the emblematic case of the London Underground network, where a tap-in/tap-out system tracks the start/exit time and location of all journeys in a day. A set of synthetic simulations and real data provided by Transport For London are used to validate and test the model on the predictions of observable and unobservable quantities. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6899-tomography-of-the-london-underground-a-scalable-model-for-origin-destination-data |
| http://papers.nips.cc/paper/6899-tomography-of-the-london-underground-a-scalable-model-for-origin-destination-data.pdf | |
| PWC | https://paperswithcode.com/paper/tomography-of-the-london-underground-a |
| Repo | |
| Framework | |
