Paper Group NANR 69
Hybrid Neural Networks for Learning the Trend in Time Series. Exploring Vector Spaces for Semantic Relations. An Object-oriented Model of Role Framing and Attitude Prediction. Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision. Neural Sequence Learning Models for Word Sense Disambiguation. If mice were reptiles, then …
Hybrid Neural Networks for Learning the Trend in Time Series
| Title | Hybrid Neural Networks for Learning the Trend in Time Series |
| Authors | Tao Lin∗，Tian Guo∗，Karl Aberer |
| Abstract | Trend of time series characterizes the intermediate upward and downward behaviour of time series. Learning and forecasting the trend in time series data play an important role in many real applica- tions, ranging from resource allocation in data cen- ters, load schedule in smart grid, and so on. In- spired by the recent successes of neural networks, in this paper we propose TreNet, a novel end-to- end hybrid neural network to learn local and global contextual features for predicting the trend of time series. TreNet leverages convolutional neural net- works (CNNs) to extract salient features from local raw data of time series. Meanwhile, considering the long-range dependency existing in the sequence of historical trends, TreNet uses a long-short term memory recurrent neural network (LSTM) to cap- ture such dependency. Then, a feature fusion layer is to learn joint representation for predicting the trend. TreNet demonstrates its effectiveness by out- performing CNN, LSTM, the cascade of CNN and LSTM, Hidden Markov Model based method and various kernel based baselines on real datasets. |
| Tasks | Time Series |
| Published | 2017-07-01 |
| URL | https://www.ijcai.org/Proceedings/2017/316 |
| https://www.ijcai.org/Proceedings/2017/316 | |
| PWC | https://paperswithcode.com/paper/hybrid-neural-networks-for-learning-the-trend |
| Repo | |
| Framework | |
Exploring Vector Spaces for Semantic Relations
| Title | Exploring Vector Spaces for Semantic Relations |
| Authors | Kata G{'a}bor, Ha{"\i}fa Zargayouna, Isabelle Tellier, Davide Buscaldi, Thierry Charnois |
| Abstract | Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words. Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities. In this paper, we explore the potential of pre-trained word embeddings to identify generic types of semantic relations in an unsupervised experiment. We propose a new relational similarity measure based on the combination of word2vec{'}s CBOW input and output vectors which outperforms concurrent vector representations, when used for unsupervised clustering on SemEval 2010 Relation Classification data. |
| Tasks | Relation Classification, Relation Extraction, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1193/ |
| https://www.aclweb.org/anthology/D17-1193 | |
| PWC | https://paperswithcode.com/paper/exploring-vector-spaces-for-semantic |
| Repo | |
| Framework | |
An Object-oriented Model of Role Framing and Attitude Prediction
| Title | An Object-oriented Model of Role Framing and Attitude Prediction |
| Authors | Manfred Klenner |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6917/ |
| https://www.aclweb.org/anthology/W17-6917 | |
| PWC | https://paperswithcode.com/paper/an-object-oriented-model-of-role-framing-and |
| Repo | |
| Framework | |
Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision
| Title | Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision |
| Authors | Haoruo Peng, Ming-Wei Chang, Wen-tau Yih |
| Abstract | Neural networks have achieved state-of-the-art performance on several structured-output prediction tasks, trained in a fully supervised fashion. However, annotated examples in structured domains are often costly to obtain, which thus limits the applications of neural networks. In this work, we propose Maximum Margin Reward Networks, a neural network-based framework that aims to learn from both explicit (full structures) and implicit supervision signals (delayed feedback on the correctness of the predicted structure). On named entity recognition and semantic parsing, our model outperforms previous systems on the benchmark datasets, CoNLL-2003 and WebQuestionsSP. |
| Tasks | Dependency Parsing, Named Entity Recognition, Part-Of-Speech Tagging, Semantic Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1252/ |
| https://www.aclweb.org/anthology/D17-1252 | |
| PWC | https://paperswithcode.com/paper/maximum-margin-reward-networks-for-learning |
| Repo | |
| Framework | |
Neural Sequence Learning Models for Word Sense Disambiguation
| Title | Neural Sequence Learning Models for Word Sense Disambiguation |
| Authors | Aless Raganato, ro, Claudio Delli Bovi, Roberto Navigli |
| Abstract | Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features. |
| Tasks | Information Retrieval, Machine Translation, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1120/ |
| https://www.aclweb.org/anthology/D17-1120 | |
| PWC | https://paperswithcode.com/paper/neural-sequence-learning-models-for-word |
| Repo | |
| Framework | |
If mice were reptiles, then reptiles could be mammals or How to detect errors in the JeuxDeMots lexical network?
| Title | If mice were reptiles, then reptiles could be mammals or How to detect errors in the JeuxDeMots lexical network? |
| Authors | Mathieu Lafourcade, Alain Joubert, Nathalie Le Brun |
| Abstract | Correcting errors in a data set is a critical issue. This task can be either hand-made by experts, or by crowdsourcing methods, or automatically done using algorithms. Although the rate of errors present in the JeuxDeMots network is rather low, it is important to reduce it. We present here automatic methods for detecting potential secondary errors that would result from automatic inference mechanisms when they rely on an initial error manually detected. Encouraging results also invite us to consider strategies that would automatically detect {``}erroneous{''} initial relations, which could lead to the automatic detection of the majority of errors in the network. | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1056/ |
| https://doi.org/10.26615/978-954-452-049-6_056 | |
| PWC | https://paperswithcode.com/paper/if-mice-were-reptiles-then-reptiles-could-be |
| Repo | |
| Framework | |
Training Data Augmentation for Low-Resource Morphological Inflection
| Title | Training Data Augmentation for Low-Resource Morphological Inflection |
| Authors | Toms Bergmanis, Katharina Kann, Hinrich Sch{"u}tze, Sharon Goldwater |
| Abstract | |
| Tasks | Data Augmentation, Morphological Inflection, Transfer Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2002/ |
| https://www.aclweb.org/anthology/K17-2002 | |
| PWC | https://paperswithcode.com/paper/training-data-augmentation-for-low-resource |
| Repo | |
| Framework | |
Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks v2.0
| Title | Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks v2.0 |
| Authors | Juhani Luotolahti, Jenna Kanerva, Filip Ginter |
| Abstract | In this paper we present our system in the DiscoMT 2017 Shared Task on Crosslingual Pronoun Prediction. Our entry builds on our last year{'}s success, our system based on deep recurrent neural networks outperformed all the other systems with a clear margin. This year we investigate whether different pre-trained word embeddings can be used to improve the neural systems, and whether the recently published Gated Convolutions outperform the Gated Recurrent Units used last year. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4808/ |
| https://www.aclweb.org/anthology/W17-4808 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-pronoun-prediction-with-deep-1 |
| Repo | |
| Framework | |
Aligning phonemes using finte-state methods
| Title | Aligning phonemes using finte-state methods |
| Authors | Kimmo Koskenniemi |
| Abstract | |
| Tasks | Speech Synthesis, Spelling Correction |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0207/ |
| https://www.aclweb.org/anthology/W17-0207 | |
| PWC | https://paperswithcode.com/paper/aligning-phonemes-using-finte-state-methods |
| Repo | |
| Framework | |
Replacing OOV Words For Dependency Parsing With Distributional Semantics
| Title | Replacing OOV Words For Dependency Parsing With Distributional Semantics |
| Authors | Prasanth Kolachina, Martin Riedl, Chris Biemann |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0202/ |
| https://www.aclweb.org/anthology/W17-0202 | |
| PWC | https://paperswithcode.com/paper/replacing-oov-words-for-dependency-parsing |
| Repo | |
| Framework | |
Coarse-to-Fine Question Answering for Long Documents
| Title | Coarse-to-Fine Question Answering for Long Documents |
| Authors | Eunsol Choi, Daniel Hewlett, Jakob Uszkoreit, Illia Polosukhin, Alex Lacoste, re, Jonathan Berant |
| Abstract | We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neural networks (RNNs), running them over long documents is prohibitively slow because it is difficult to parallelize over sequences. Inspired by how people first skim the document, identify relevant parts, and carefully read these parts to produce an answer, we combine a coarse, fast model for selecting relevant sentences and a more expensive RNN for producing the answer from those sentences. We treat sentence selection as a latent variable trained jointly from the answer only using reinforcement learning. Experiments demonstrate state-of-the-art performance on a challenging subset of the WikiReading dataset and on a new dataset, while speeding up the model by 3.5x-6.7x. |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1020/ |
| https://www.aclweb.org/anthology/P17-1020 | |
| PWC | https://paperswithcode.com/paper/coarse-to-fine-question-answering-for-long |
| Repo | |
| Framework | |
Imitation learning for structured prediction in natural language processing
| Title | Imitation learning for structured prediction in natural language processing |
| Authors | Andreas Vlachos, Gerasimos Lampouras, Sebastian Riedel |
| Abstract | Imitation learning is a learning paradigm originally developed to learn robotic controllers from demonstrations by humans, e.g. autonomous flight from pilot demonstrations. Recently, algorithms for structured prediction were proposed under this paradigm and have been applied successfully to a number of tasks including syntactic dependency parsing, information extraction, coreference resolution, dynamic feature selection, semantic parsing and natural language generation. Key advantages are the ability to handle large output search spaces and to learn with non-decomposable loss functions. Our aim in this tutorial is to have a unified presentation of the various imitation algorithms for structure prediction, and show how they can be applied to a variety of NLP tasks.All material associated with the tutorial will be made available through https://sheffieldnlp.github.io/ImitationLearningTutorialEACL2017/. |
| Tasks | Coreference Resolution, Dependency Parsing, Feature Selection, Imitation Learning, Semantic Parsing, Structured Prediction, Text Generation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-5003/ |
| https://www.aclweb.org/anthology/E17-5003 | |
| PWC | https://paperswithcode.com/paper/imitation-learning-for-structured-prediction |
| Repo | |
| Framework | |
Enriching ASR Lattices with POS Tags for Dependency Parsing
| Title | Enriching ASR Lattices with POS Tags for Dependency Parsing |
| Authors | Moritz Stiefel, Ngoc Thang Vu |
| Abstract | Parsing speech requires a richer representation than 1-best or n-best hypotheses, e.g. lattices. Moreover, previous work shows that part-of-speech (POS) tags are a valuable resource for parsing. In this paper, we therefore explore a joint modeling approach of automatic speech recognition (ASR) and POS tagging to enrich ASR word lattices. To that end, we manipulate the ASR process from the pronouncing dictionary onward to use word-POS pairs instead of words. We evaluate ASR, POS tagging and dependency parsing (DP) performance demonstrating a successful lattice-based integration of ASR and POS tagging. |
| Tasks | Dependency Parsing, Speech Recognition, Spoken Language Understanding |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4605/ |
| https://www.aclweb.org/anthology/W17-4605 | |
| PWC | https://paperswithcode.com/paper/enriching-asr-lattices-with-pos-tags-for |
| Repo | |
| Framework | |
Say the Right Thing Right: Ethics Issues in Natural Language Generation Systems
| Title | Say the Right Thing Right: Ethics Issues in Natural Language Generation Systems |
| Authors | Charese Smiley, Frank Schilder, Vassilis Plachouras, Jochen L. Leidner |
| Abstract | We discuss the ethical implications of Natural Language Generation systems. We use one particular system as a case study to identify and classify issues, and we provide an ethics checklist, in the hope that future system designers may benefit from conducting their own ethics reviews based on our checklist. |
| Tasks | Text Generation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1613/ |
| https://www.aclweb.org/anthology/W17-1613 | |
| PWC | https://paperswithcode.com/paper/say-the-right-thing-right-ethics-issues-in |
| Repo | |
| Framework | |
Group Linguistic Bias Aware Neural Response Generation
| Title | Group Linguistic Bias Aware Neural Response Generation |
| Authors | Jianan Wang, Xin Wang, Fang Li, Zhen Xu, Zhuoran Wang, Baoxun Wang |
| Abstract | For practical chatbots, one of the essential factor for improving user experience is the capability of customizing the talking style of the agents, that is, to make chatbots provide responses meeting users{'} preference on language styles, topics, etc. To address this issue, this paper proposes to incorporate linguistic biases, which implicitly involved in the conversation corpora generated by human groups in the Social Network Services (SNS), into the encoder-decoder based response generator. By attaching a specially designed neural component to dynamically control the impact of linguistic biases in response generation, a Group Linguistic Bias Aware Neural Response Generation (GLBA-NRG) model is eventually presented. The experimental results on the dataset from the Chinese SNS show that the proposed architecture outperforms the current response generating models by producing both meaningful and vivid responses with customized styles. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-6001/ |
| https://www.aclweb.org/anthology/W17-6001 | |
| PWC | https://paperswithcode.com/paper/group-linguistic-bias-aware-neural-response |
| Repo | |
| Framework | |
