Paper Group NANR 89
Conditional Random Fields for Metaphor Detection. What It Takes to Achieve 100% Condition Accuracy on WikiSQL. Dialogue-act-driven Conversation Model : An Experimental Study. Linguistic Features of Sarcasm and Metaphor Production Quality. Weakly Supervised Semantic Parsing with Abstract Examples. Language Generation via DAG Transduction. How to re …
Conditional Random Fields for Metaphor Detection
| Title | Conditional Random Fields for Metaphor Detection |
| Authors | Anna Mosolova, Ivan Bondarenko, Vadim Fomin |
| Abstract | We present an algorithm for detecting metaphor in sentences which was used in Shared Task on Metaphor Detection by First Workshop on Figurative Language Processing. The algorithm is based on different features and Conditional Random Fields. |
| Tasks | Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0915/ |
| https://www.aclweb.org/anthology/W18-0915 | |
| PWC | https://paperswithcode.com/paper/conditional-random-fields-for-metaphor |
| Repo | |
| Framework | |
What It Takes to Achieve 100% Condition Accuracy on WikiSQL
| Title | What It Takes to Achieve 100% Condition Accuracy on WikiSQL |
| Authors | Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan |
| Abstract | WikiSQL is a newly released dataset for studying the natural language sequence to SQL translation problem. The SQL queries in WikiSQL are simple: Each involves one relation and does not have any join operation. Despite of its simplicity, none of the publicly reported structured query generation models can achieve an accuracy beyond 62{%}, which is still far from enough for practical use. In this paper, we ask two questions, {}Why is the accuracy still low for such simple queries?{''} and {}What does it take to achieve 100{%} accuracy on WikiSQL?{''} To limit the scope of our study, we focus on the WHERE clause in SQL. The answers will help us gain insights about the directions we should explore in order to further improve the translation accuracy. We will then investigate alternative solutions to realize the potential ceiling performance on WikiSQL. Our proposed solution can reach up to 88.6{%} condition accuracy on the WikiSQL dataset. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1197/ |
| https://www.aclweb.org/anthology/D18-1197 | |
| PWC | https://paperswithcode.com/paper/what-it-takes-to-achieve-100-percent |
| Repo | |
| Framework | |
Dialogue-act-driven Conversation Model : An Experimental Study
| Title | Dialogue-act-driven Conversation Model : An Experimental Study |
| Authors | Harshit Kumar, Arvind Agarwal, Sachindra Joshi |
| Abstract | The utility of additional semantic information for the task of next utterance selection in an automated dialogue system is the focus of study in this paper. In particular, we show that additional information available in the form of dialogue acts {–}when used along with context given in the form of dialogue history{–} improves the performance irrespective of the underlying model being generative or discriminative. In order to show the model agnostic behavior of dialogue acts, we experiment with several well-known models such as sequence-to-sequence encoder-decoder model, hierarchical encoder-decoder model, and Siamese-based models with and without hierarchy; and show that in all models, incorporating dialogue acts improves the performance by a significant margin. We, furthermore, propose a novel way of encoding dialogue act information, and use it along with hierarchical encoder to build a model that can use the sequential dialogue act information in a natural way. Our proposed model achieves an MRR of about 84.8{%} for the task of next utterance selection on a newly introduced Daily Dialogue dataset, and outperform the baseline models. We also provide a detailed analysis of results including key insights that explain the improvement in MRR because of dialog act information. |
| Tasks | Dialogue Generation, Text Generation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1106/ |
| https://www.aclweb.org/anthology/C18-1106 | |
| PWC | https://paperswithcode.com/paper/dialogue-act-driven-conversation-model-an |
| Repo | |
| Framework | |
Linguistic Features of Sarcasm and Metaphor Production Quality
| Title | Linguistic Features of Sarcasm and Metaphor Production Quality |
| Authors | Stephen Skalicky, Scott Crossley |
| Abstract | Using linguistic features to detect figurative language has provided a deeper in-sight into figurative language. The purpose of this study is to assess whether linguistic features can help explain differences in quality of figurative language. In this study a large corpus of metaphors and sarcastic responses are collected from human subjects and rated for figurative language quality based on theoretical components of metaphor, sarcasm, and creativity. Using natural language processing tools, specific linguistic features related to lexical sophistication and semantic cohesion were used to predict the human ratings of figurative language quality. Results demonstrate linguistic features were able to predict small amounts of variance in metaphor and sarcasm production quality. |
| Tasks | Language Identification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0902/ |
| https://www.aclweb.org/anthology/W18-0902 | |
| PWC | https://paperswithcode.com/paper/linguistic-features-of-sarcasm-and-metaphor |
| Repo | |
| Framework | |
Weakly Supervised Semantic Parsing with Abstract Examples
| Title | Weakly Supervised Semantic Parsing with Abstract Examples |
| Authors | Omer Goldman, Veronica Latcinnik, Ehud Nave, Amir Globerson, Jonathan Berant |
| Abstract | Training semantic parsers from weak supervision (denotations) rather than strong supervision (programs) complicates training in two ways. First, a large search space of potential programs needs to be explored at training time to find a correct program. Second, spurious programs that accidentally lead to a correct denotation add noise to training. In this work we propose that in closed worlds with clear semantic types, one can substantially alleviate these problems by utilizing an abstract representation, where tokens in both the language utterance and program are lifted to an abstract form. We show that these abstractions can be defined with a handful of lexical rules and that they result in sharing between different examples that alleviates the difficulties in training. To test our approach, we develop the first semantic parser for CNLVR, a challenging visual reasoning dataset, where the search space is large and overcoming spuriousness is critical, because denotations are either TRUE or FALSE, and thus random programs are likely to lead to a correct denotation. Our method substantially improves performance, and reaches 82.5{%} accuracy, a 14.7{%} absolute accuracy improvement compared to the best reported accuracy so far. |
| Tasks | Semantic Parsing, Visual Reasoning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1168/ |
| https://www.aclweb.org/anthology/P18-1168 | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-semantic-parsing-with |
| Repo | |
| Framework | |
Language Generation via DAG Transduction
| Title | Language Generation via DAG Transduction |
| Authors | Yajie Ye, Weiwei Sun, Xiaojun Wan |
| Abstract | A DAG automaton is a formal device for manipulating graphs. By augmenting a DAG automaton with transduction rules, a DAG transducer has potential applications in fundamental NLP tasks. In this paper, we propose a novel DAG transducer to perform graph-to-program transformation. The target structure of our transducer is a program licensed by a declarative programming language rather than linguistic structures. By executing such a program, we can easily get a surface string. Our transducer is designed especially for natural language generation (NLG) from type-logical semantic graphs. Taking Elementary Dependency Structures, a format of English Resource Semantics, as input, our NLG system achieves a BLEU-4 score of 68.07. This remarkable result demonstrates the feasibility of applying a DAG transducer to resolve NLG, as well as the effectiveness of our design. |
| Tasks | Semantic Parsing, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1179/ |
| https://www.aclweb.org/anthology/P18-1179 | |
| PWC | https://paperswithcode.com/paper/language-generation-via-dag-transduction |
| Repo | |
| Framework | |
How to represent a word and predict it, too: Improving tied architectures for language modelling
| Title | How to represent a word and predict it, too: Improving tied architectures for language modelling |
| Authors | Kristina Gulordava, Laura Aina, Gemma Boleda |
| Abstract | Recent state-of-the-art neural language models share the representations of words given by the input and output mappings. We propose a simple modification to these architectures that decouples the hidden state from the word embedding prediction. Our architecture leads to comparable or better results compared to previous tied models and models without tying, with a much smaller number of parameters. We also extend our proposal to word2vec models, showing that tying is appropriate for general word prediction tasks. |
| Tasks | Language Modelling, Representation Learning, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1323/ |
| https://www.aclweb.org/anthology/D18-1323 | |
| PWC | https://paperswithcode.com/paper/how-to-represent-a-word-and-predict-it-too |
| Repo | |
| Framework | |
Kernelized Subspace Pooling for Deep Local Descriptors
| Title | Kernelized Subspace Pooling for Deep Local Descriptors |
| Authors | Xing Wei, Yue Zhang, Yihong Gong, Nanning Zheng |
| Abstract | Representing local image patches in an invariant and discriminative manner is an active research topic in computer vision. It has recently been demonstrated that local feature learning based on deep Convolutional Neural Network (CNN) can significantly improve the matching performance. Previous works on learning such descriptors have focused on developing various loss functions, regularizations and data mining strategies to learn discriminative CNN representations. Such methods, however, have little analysis on how to increase geometric invariance of their generated descriptors. In this paper, we propose a descriptor that has both highly invariant and discriminative power. The abilities come from a novel pooling method, dubbed Subspace Pooling (SP) which is invariant to a range of geometric deformations. To further increase the discriminative power of our descriptor, we propose a simple distance kernel integrated to the marginal triplet loss that helps to focus on hard examples in CNN training. Finally, we show that by combining SP with the projection distance metric, the generated feature descriptor is equivalent to that of the Bilinear CNN model, but outperforms the latter with much lower memory and computation consumptions. The proposed method is simple, easy to understand and achieves good performance. Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wei_Kernelized_Subspace_Pooling_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Kernelized_Subspace_Pooling_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/kernelized-subspace-pooling-for-deep-local |
| Repo | |
| Framework | |
Towards a Standardized Dataset for Noun Compound Interpretation
| Title | Towards a Standardized Dataset for Noun Compound Interpretation |
| Authors | Girishkumar Ponkiya, Kevin Patel, Pushpak Bhattacharyya, Girish K Palshikar |
| Abstract | |
| Tasks | Machine Translation, Question Answering |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1489/ |
| https://www.aclweb.org/anthology/L18-1489 | |
| PWC | https://paperswithcode.com/paper/towards-a-standardized-dataset-for-noun |
| Repo | |
| Framework | |
Egocentric Spatial Memory Network
| Title | Egocentric Spatial Memory Network |
| Authors | Mengmi Zhang, Keng Teck Ma, Joo Hwee Lim, Shih-Cheng Yen, Qi Zhao, Jiashi Feng |
| Abstract | Inspired by neurophysiological discoveries of navigation cells in the mammalian brain, we introduce the first deep neural network architecture for modeling Egocentric Spatial Memory (ESM). It learns to estimate the pose of the agent and progressively construct top-down 2D global maps from egocentric views in a spatially extended environment. During the exploration, our proposed ESM network model updates belief of the global map based on local observations using a recurrent neural network. It also augments the local mapping with a novel external memory to encode and store latent representations of the visited places based on their corresponding locations in the egocentric coordinate. This enables the agents to perform loop closure and mapping correction. This work contributes in the following aspects: first, our proposed ESM network provides an accurate mapping ability which is vitally important for embodied agents to navigate to goal locations. In the experiments, we demonstrate the functionalities of the ESM network in random walks in complicated 3D mazes by comparing with several competitive baselines and state-of-the-art Simultaneous Localization and Mapping (SLAM) algorithms. Secondly, we faithfully hypothesize the functionality and the working mechanism of navigation cells in the brain. Comprehensive analysis of our model suggests the essential role of individual modules in our proposed architecture and demonstrates efficiency of communications among these modules. We hope this work would advance research in the collaboration and communications over both fields of computer science and computational neuroscience. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkmM6M_pW |
| https://openreview.net/pdf?id=SkmM6M_pW | |
| PWC | https://paperswithcode.com/paper/egocentric-spatial-memory-network |
| Repo | |
| Framework | |
Piecewise Linear Neural Networks verification: A comparative study
| Title | Piecewise Linear Neural Networks verification: A comparative study |
| Authors | Rudy Bunel, Ilker Turkaslan, Philip H.S. Torr, Pushmeet Kohli, M. Pawan Kumar |
| Abstract | The success of Deep Learning and its potential use in many important safety- critical applications has motivated research on formal verification of Neural Net- work (NN) models. Despite the reputation of learned NN models to behave as black boxes and theoretical hardness results of the problem of proving their prop- erties, researchers have been successful in verifying some classes of models by exploiting their piecewise linear structure. Unfortunately, most of these works test their algorithms on their own models and do not offer any comparison with other approaches. As a result, the advantages and downsides of the different al- gorithms are not well understood. Motivated by the need of accelerating progress in this very important area, we investigate the trade-offs of a number of different approaches based on Mixed Integer Programming, Satisfiability Modulo Theory, as well as a novel method based on the Branch-and-Bound framework. We also propose a new data set of benchmarks, in addition to a collection of previously released testcases that can be used to compare existing methods. Our analysis not only allowed a comparison to be made between different strategies, the compar- ision of results from different solvers also revealed implementation bugs in pub- lished methods. We expect that the availability of our benchmark and the analysis of the different approaches will allow researchers to invent and evaluate promising approaches for making progress on this important topic. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BkPrDFgR- |
| https://openreview.net/pdf?id=BkPrDFgR- | |
| PWC | https://paperswithcode.com/paper/piecewise-linear-neural-networks-verification |
| Repo | |
| Framework | |
Guessing lexicon entries using finite-state methods
| Title | Guessing lexicon entries using finite-state methods |
| Authors | Kimmo Koskenniemi |
| Abstract | |
| Tasks | Morphological Analysis |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0206/ |
| https://www.aclweb.org/anthology/W18-0206 | |
| PWC | https://paperswithcode.com/paper/guessing-lexicon-entries-using-finite-state |
| Repo | |
| Framework | |
節能知識問答機器人 (Energy Saving Knowledge Chatbot) [In Chinese]
| Title | 節能知識問答機器人 (Energy Saving Knowledge Chatbot) [In Chinese] |
| Authors | Jhih-Jie Chen, Shih-Ying Chang, Tsu-Jin Chiu, Ming-Chiao Tsai, Jason S. Chang |
| Abstract | |
| Tasks | Chatbot |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1027/ |
| https://www.aclweb.org/anthology/O18-1027 | |
| PWC | https://paperswithcode.com/paper/c-e12ceaca-aoo-energy-saving-knowledge |
| Repo | |
| Framework | |
An LSTM Approach to Short Text Sentiment Classification with Word Embeddings
| Title | An LSTM Approach to Short Text Sentiment Classification with Word Embeddings |
| Authors | Jenq-Haur Wang, Ting-Wei Liu, Xiong Luo, Long Wang |
| Abstract | |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1021/ |
| https://www.aclweb.org/anthology/O18-1021 | |
| PWC | https://paperswithcode.com/paper/an-lstm-approach-to-short-text-sentiment |
| Repo | |
| Framework | |
Deep Learning Approaches to Text Production
| Title | Deep Learning Approaches to Text Production |
| Authors | Claire Gardent, Shashi Narayan |
| Abstract | Text production is a key component of many NLP applications. In data-driven approaches, it is used for instance, to generate dialogue turns from dialogue moves, to verbalise the content of Knowledge bases or to generate natural English sentences from rich linguistic representations, such as dependency trees or Abstract Meaning Representations. In text-driven methods on the other hand, text production is at work in sentence compression, sentence fusion, paraphrasing, sentence (or text) simplification, text summarisation and end-to-end dialogue systems. Following the success of encoder-decoder models in modeling sequence-rewriting tasks such as machine translation, deep learning models have successfully been applied to the various text production tasks. In this tutorial, we will cover the fundamentals and the state-of-the-art research on neural models for text production. Each text production task raises a slightly different communication goal (e.g, how to take the dialogue context into account when producing a dialogue turn; how to detect and merge relevant information when summarising a text; or how to produce a well-formed text that correctly capture the information contained in some input data in the case of data-to-text generation). We will outline the constraints specific to each subtasks and examine how the existing neural models account for them. |
| Tasks | Data-to-Text Generation, Machine Translation, Sentence Compression, Text Generation, Text Simplification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-6002/ |
| https://www.aclweb.org/anthology/N18-6002 | |
| PWC | https://paperswithcode.com/paper/deep-learning-approaches-to-text-production |
| Repo | |
| Framework | |
