Paper Group NANR 129
A Proof-Theoretic Semantics for Transitive Verbs with an Implicit Object. Natural Value Approximators: Learning when to Trust Past Estimates. The QT21 Combined Machine Translation System for English to Latvian. Huntsville, hospitals, and hockey teams: Names can reveal your location. Importance sampling for unbiased on-demand evaluation of knowledge …
A Proof-Theoretic Semantics for Transitive Verbs with an Implicit Object
| Title | A Proof-Theoretic Semantics for Transitive Verbs with an Implicit Object |
| Authors | Nissim Francez |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3406/ |
| https://www.aclweb.org/anthology/W17-3406 | |
| PWC | https://paperswithcode.com/paper/a-proof-theoretic-semantics-for-transitive |
| Repo | |
| Framework | |
Natural Value Approximators: Learning when to Trust Past Estimates
| Title | Natural Value Approximators: Learning when to Trust Past Estimates |
| Authors | Zhongwen Xu, Joseph Modayil, Hado P. Van Hasselt, Andre Barreto, David Silver, Tom Schaul |
| Abstract | Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output. However, in reinforcement learning domains with sparse rewards, value functions have non-smooth structure with a characteristic asymmetric discontinuity whenever rewards arrive. We propose a mechanism that learns an interpolation between a direct value estimate and a projected value estimate computed from the encountered reward and the previous estimate. This reduces the need to learn about discontinuities, and thus improves the value function approximation. Furthermore, as the interpolation is learned and state-dependent, our method can deal with heterogeneous observability. We demonstrate that this one change leads to significant improvements on multiple Atari games, when applied to the state-of-the-art A3C algorithm. |
| Tasks | Atari Games |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6807-natural-value-approximators-learning-when-to-trust-past-estimates |
| http://papers.nips.cc/paper/6807-natural-value-approximators-learning-when-to-trust-past-estimates.pdf | |
| PWC | https://paperswithcode.com/paper/natural-value-approximators-learning-when-to |
| Repo | |
| Framework | |
The QT21 Combined Machine Translation System for English to Latvian
| Title | The QT21 Combined Machine Translation System for English to Latvian |
| Authors | Jan-Thorsten Peter, Hermann Ney, Ond{\v{r}}ej Bojar, Ngoc-Quan Pham, Jan Niehues, Alex Waibel, Franck Burlot, Fran{\c{c}}ois Yvon, M{=a}rcis Pinnis, Valters {\v{S}}ics, Joost Bastings, Miguel Rios, Wilker Aziz, Philip Williams, Fr{'e}d{'e}ric Blain, Lucia Specia |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4734/ |
| https://www.aclweb.org/anthology/W17-4734 | |
| PWC | https://paperswithcode.com/paper/the-qt21-combined-machine-translation-system |
| Repo | |
| Framework | |
Huntsville, hospitals, and hockey teams: Names can reveal your location
| Title | Huntsville, hospitals, and hockey teams: Names can reveal your location |
| Authors | Bahar Salehi, Dirk Hovy, Eduard Hovy, Anders S{\o}gaard |
| Abstract | Geolocation is the task of identifying a social media user{'}s primary location, and in natural language processing, there is a growing literature on to what extent automated analysis of social media posts can help. However, not all content features are equally revealing of a user{'}s location. In this paper, we evaluate nine name entity (NE) types. Using various metrics, we find that GEO-LOC, FACILITY and SPORT-TEAM are more informative for geolocation than other NE types. Using these types, we improve geolocation accuracy and reduce distance error over various famous text-based methods. |
| Tasks | Knowledge Base Population, Recommendation Systems, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4415/ |
| https://www.aclweb.org/anthology/W17-4415 | |
| PWC | https://paperswithcode.com/paper/huntsville-hospitals-and-hockey-teams-names |
| Repo | |
| Framework | |
Importance sampling for unbiased on-demand evaluation of knowledge base population
| Title | Importance sampling for unbiased on-demand evaluation of knowledge base population |
| Authors | Arun Chaganty, Ashwin Paranjape, Percy Liang, Christopher D. Manning |
| Abstract | Knowledge base population (KBP) systems take in a large document corpus and extract entities and their relations. Thus far, KBP evaluation has relied on judgements on the pooled predictions of existing systems. We show that this evaluation is problematic: when a new system predicts a previously unseen relation, it is penalized even if it is correct. This leads to significant bias against new systems, which counterproductively discourages innovation in the field. Our first contribution is a new importance-sampling based evaluation which corrects for this bias by annotating a new system{'}s predictions on-demand via crowdsourcing. We show this eliminates bias and reduces variance using data from the 2015 TAC KBP task. Our second contribution is an implementation of our method made publicly available as an online KBP evaluation service. We pilot the service by testing diverse state-of-the-art systems on the TAC KBP 2016 corpus and obtain accurate scores in a cost effective manner. |
| Tasks | Information Retrieval, Knowledge Base Population, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1109/ |
| https://www.aclweb.org/anthology/D17-1109 | |
| PWC | https://paperswithcode.com/paper/importance-sampling-for-unbiased-on-demand |
| Repo | |
| Framework | |
Online Learning with Transductive Regret
| Title | Online Learning with Transductive Regret |
| Authors | Mehryar Mohri, Scott Yang |
| Abstract | We study online learning with the general notion of transductive regret, that is regret with modification rules applying to expert sequences (as opposed to single experts) that are representable by weighted finite-state transducers. We show how transductive regret generalizes existing notions of regret, including: (1) external regret; (2) internal regret; (3) swap regret; and (4) conditional swap regret. We present a general and efficient online learning algorithm for minimizing transductive regret. We further extend that to design efficient algorithms for the time-selection and sleeping expert settings. A by-product of our study is an algorithm for swap regret, which, under mild assumptions, is more efficient than existing ones, and a substantially more efficient algorithm for time selection swap regret. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7106-online-learning-with-transductive-regret |
| http://papers.nips.cc/paper/7106-online-learning-with-transductive-regret.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-with-transductive-regret |
| Repo | |
| Framework | |
Transfer Learning and Sentence Level Features for Named Entity Recognition on Tweets
| Title | Transfer Learning and Sentence Level Features for Named Entity Recognition on Tweets |
| Authors | Pius von D{"a}niken, Mark Cieliebak |
| Abstract | We present our system for the WNUT 2017 Named Entity Recognition challenge on Twitter data. We describe two modifications of a basic neural network architecture for sequence tagging. First, we show how we exploit additional labeled data, where the Named Entity tags differ from the target task. Then, we propose a way to incorporate sentence level features. Our system uses both methods and ranked second for entity level annotations, achieving an F1-score of 40.78, and second for surface form annotations, achieving an F1-score of 39.33. |
| Tasks | Named Entity Recognition, Transfer Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4422/ |
| https://www.aclweb.org/anthology/W17-4422 | |
| PWC | https://paperswithcode.com/paper/transfer-learning-and-sentence-level-features |
| Repo | |
| Framework | |
Detecting Asymmetric Semantic Relations in Context: A Case-Study on Hypernymy Detection
| Title | Detecting Asymmetric Semantic Relations in Context: A Case-Study on Hypernymy Detection |
| Authors | Yogarshi Vyas, Marine Carpuat |
| Abstract | We introduce WHiC, a challenging testbed for detecting hypernymy, an asymmetric relation between words. While previous work has focused on detecting hypernymy between word types, we ground the meaning of words in specific contexts drawn from WordNet examples, and require predictions to be sensitive to changes in contexts. WHiC lets us analyze complementary properties of two approaches of inducing vector representations of word meaning in context. We show that such contextualized word representations also improve detection of a wider range of semantic relations in context. |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1004/ |
| https://www.aclweb.org/anthology/S17-1004 | |
| PWC | https://paperswithcode.com/paper/detecting-asymmetric-semantic-relations-in |
| Repo | |
| Framework | |
Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments
| Title | Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments |
| Authors | Qing Ping, Chaomei Chen |
| Abstract | With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good opportunity for highlight detection. However, this task is non-trivial: (1) time-sync comments often lag behind their corresponding shot; (2) time-sync comments are semantically sparse and noisy; (3) to determine which shots are highlights is highly subjective. The present paper aims to tackle these challenges by proposing a framework that (1) uses concept-mapped lexical-chains for lag-calibration; (2) models video highlights based on comment intensity and combination of emotion and concept concentration of each shot; (3) summarize each detected highlight using improved SumBasic with emotion and concept mapping. Experiments on large real-world datasets show that our highlight detection method and summarization method both outperform other benchmarks with considerable margins. |
| Tasks | Calibration |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4501/ |
| https://www.aclweb.org/anthology/W17-4501 | |
| PWC | https://paperswithcode.com/paper/video-highlights-detection-and-summarization |
| Repo | |
| Framework | |
Multimedia Summary Generation from Online Conversations: Current Approaches and Future Directions
| Title | Multimedia Summary Generation from Online Conversations: Current Approaches and Future Directions |
| Authors | Enamul Hoque, Giuseppe Carenini |
| Abstract | With the proliferation of Web-based social media, asynchronous conversations have become very common for supporting online communication and collaboration. Yet the increasing volume and complexity of conversational data often make it very difficult to get insights about the discussions. We consider combining textual summary with visual representation of conversational data as a promising way of supporting the user in exploring conversations. In this paper, we report our current work on developing visual interfaces that present multimedia summary combining text and visualization for online conversations and how our solutions have been tailored for a variety of domain problems. We then discuss the key challenges and opportunities for future work in this research space. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4502/ |
| https://www.aclweb.org/anthology/W17-4502 | |
| PWC | https://paperswithcode.com/paper/multimedia-summary-generation-from-online |
| Repo | |
| Framework | |
Deep Learning Models For Multiword Expression Identification
| Title | Deep Learning Models For Multiword Expression Identification |
| Authors | Waseem Gharbieh, Virendrakumar Bhavsar, Paul Cook |
| Abstract | Multiword expressions (MWEs) are lexical items that can be decomposed into multiple component words, but have properties that are unpredictable with respect to their component words. In this paper we propose the first deep learning models for token-level identification of MWEs. Specifically, we consider a layered feedforward network, a recurrent neural network, and convolutional neural networks. In experimental results we show that convolutional neural networks are able to outperform the previous state-of-the-art for MWE identification, with a convolutional neural network with three hidden layers giving the best performance. |
| Tasks | Information Retrieval, Machine Translation, Named Entity Recognition, Opinion Mining, Sentence Classification, Text Generation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1006/ |
| https://www.aclweb.org/anthology/S17-1006 | |
| PWC | https://paperswithcode.com/paper/deep-learning-models-for-multiword-expression |
| Repo | |
| Framework | |
Coarse-to-Fine Attention Models for Document Summarization
| Title | Coarse-to-Fine Attention Models for Document Summarization |
| Authors | Jeffrey Ling, Alex Rush, er |
| Abstract | Sequence-to-sequence models with attention have been successful for a variety of NLP problems, but their speed does not scale well for tasks with long source sequences such as document summarization. We propose a novel coarse-to-fine attention model that hierarchically reads a document, using coarse attention to select top-level chunks of text and fine attention to read the words of the chosen chunks. While the computation for training standard attention models scales linearly with source sequence length, our method scales with the number of top-level chunks and can handle much longer sequences. Empirically, we find that while coarse-to-fine attention models lag behind state-of-the-art baselines, our method achieves the desired behavior of sparsely attending to subsets of the document for generation. |
| Tasks | Document Summarization, Machine Translation, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4505/ |
| https://www.aclweb.org/anthology/W17-4505 | |
| PWC | https://paperswithcode.com/paper/coarse-to-fine-attention-models-for-document |
| Repo | |
| Framework | |
Total capture: 3D human pose estimation fusing video and inertial sensors
| Title | Total capture: 3D human pose estimation fusing video and inertial sensors |
| Authors | Matthew Trumble, Andrew Gilbert, Charles Malleson, Adrian Hilton, and John Collomosse |
| Abstract | We present an algorithm for fusing multi-viewpoint video (MVV) with inertial measurement unit (IMU) sensor data to accurately estimate 3D human pose. A 3-D convolutional neural network is used to learn a pose embedding from volumetric probabilistic visual hull data (PVH) derived from the MVV frames. We incorporate this model within a dual stream network integrating pose embeddings derived from MVV and a forward kinematic solve of the IMU data. A temporal model (LSTM) is incorporated within both streams prior to their fusion. Hybrid pose inference using these two complementary data sources is shown to resolve ambiguities within each sensor modality, yielding improved accuracy over prior methods. A further contribution of this work is a new hybrid MVV dataset (TotalCapture) comprising video, IMU and a skeletal joint ground truth derived from a commercial motion capture system. The dataset is available online at http://cvssp.org/data/totalcapture/ |
| Tasks | 3D Human Pose Estimation, Motion Capture, Pose Estimation |
| Published | 2017-09-04 |
| URL | https://cvssp.org/projects/totalcapture/TotalCapture/ |
| https://cvssp.org/projects/totalcapture/TotalCapture/TrumbleBMVC2017.pdf | |
| PWC | https://paperswithcode.com/paper/total-capture-3d-human-pose-estimation-fusing |
| Repo | |
| Framework | |
Integrating Meaning into Quality Evaluation of Machine Translation
| Title | Integrating Meaning into Quality Evaluation of Machine Translation |
| Authors | Osman Ba{\c{s}}kaya, Eray Yildiz, Doruk Tunao{\u{g}}lu, Mustafa Tolga Eren, A. Seza Do{\u{g}}ru{"o}z |
| Abstract | Machine translation (MT) quality is evaluated through comparisons between MT outputs and the human translations (HT). Traditionally, this evaluation relies on form related features (e.g. lexicon and syntax) and ignores the transfer of meaning reflected in HT outputs. Instead, we evaluate the quality of MT outputs through meaning related features (e.g. polarity, subjectivity) with two experiments. In the first experiment, the meaning related features are compared to human rankings individually. In the second experiment, combinations of meaning related features and other quality metrics are utilized to predict the same human rankings. The results of our experiments confirm the benefit of these features in predicting human evaluation of translation quality in addition to traditional metrics which focus mainly on form. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1020/ |
| https://www.aclweb.org/anthology/E17-1020 | |
| PWC | https://paperswithcode.com/paper/integrating-meaning-into-quality-evaluation |
| Repo | |
| Framework | |
Tw-StAR at SemEval-2017 Task 4: Sentiment Classification of Arabic Tweets
| Title | Tw-StAR at SemEval-2017 Task 4: Sentiment Classification of Arabic Tweets |
| Authors | Hala Mulki, Hatem Haddad, Mourad Gridach, Ismail Babaoglu |
| Abstract | In this paper, we present our contribution in SemEval 2017 international workshop. We have tackled task 4 entitled {``}Sentiment analysis in Twitter{''}, specifically subtask 4A-Arabic. We propose two Arabic sentiment classification models implemented using supervised and unsupervised learning strategies. In both models, Arabic tweets were preprocessed first then various schemes of bag-of-N-grams were extracted to be used as features. The final submission was selected upon the best performance achieved by the supervised learning-based model. However, the results obtained by the unsupervised learning-based model are considered promising and evolvable if more rich lexica are adopted in further work. | |
| Tasks | Decision Making, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2110/ |
| https://www.aclweb.org/anthology/S17-2110 | |
| PWC | https://paperswithcode.com/paper/tw-star-at-semeval-2017-task-4-sentiment |
| Repo | |
| Framework | |
