Paper Group NANR 279
Policy Gradient For Multidimensional Action Spaces: Action Sampling and Entropy Bonus. Addressing Noise in Multidialectal Word Embeddings. NEWS 2018 Whitepaper. Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data. Spurious Ambiguity and Focalization. Autonomous Vehicle Fleet Coordina …
Policy Gradient For Multidimensional Action Spaces: Action Sampling and Entropy Bonus
| Title | Policy Gradient For Multidimensional Action Spaces: Action Sampling and Entropy Bonus |
| Authors | Vuong Ho Quan, Yiming Zhang, Kenny Song, Xiao-Yue Gong, Keith W. Ross |
| Abstract | In recent years deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. In this paper, we develop a novel policy gradient methodology for the case of large multidimensional discrete action spaces. We propose two approaches for creating parameterized policies: LSTM parameterization and a Modified MDP (MMDP) giving rise to Feed-Forward Network (FFN) parameterization. Both of these approaches provide expressive models to which backpropagation can be applied for training. We then consider entropy bonus, which is typically added to the reward function to enhance exploration. In the case of high-dimensional action spaces, calculating the entropy and the gradient of the entropy requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible. We develop several novel unbiased estimators for the entropy bonus and its gradient. Finally, we test our algorithms on two environments: a multi-hunter multi-rabbit grid game and a multi-agent multi-arm bandit problem. |
| Tasks | Atari Games |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rk3b2qxCW |
| https://openreview.net/pdf?id=rk3b2qxCW | |
| PWC | https://paperswithcode.com/paper/policy-gradient-for-multidimensional-action |
| Repo | |
| Framework | |
Addressing Noise in Multidialectal Word Embeddings
| Title | Addressing Noise in Multidialectal Word Embeddings |
| Authors | Alex Erdmann, er, Nasser Zalmout, Nizar Habash |
| Abstract | Word embeddings are crucial to many natural language processing tasks. The quality of embeddings relies on large non-noisy corpora. Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling. We make three contributions to address this noise. First, we describe simple but effective adaptations to word embedding tools to maximize the informative content leveraged in each training sentence. Second, we analyze methods for representing disparate dialects in one embedding space, either by mapping individual dialects into a shared space or learning a joint model of all dialects. Finally, we evaluate via dictionary induction, showing that two metrics not typically reported in the task enable us to analyze our contributions{'} effects on low and high frequency words. In addition to boosting performance between 2-53{%}, we specifically improve on noisy, low frequency forms without compromising accuracy on high frequency forms. |
| Tasks | Transliteration, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2089/ |
| https://www.aclweb.org/anthology/P18-2089 | |
| PWC | https://paperswithcode.com/paper/addressing-noise-in-multidialectal-word |
| Repo | |
| Framework | |
NEWS 2018 Whitepaper
| Title | NEWS 2018 Whitepaper |
| Authors | Nancy Chen, Xiangyu Duan, Min Zhang, Rafael E. Banchs, Haizhou Li |
| Abstract | Transliteration is defined as phonetic translation of names across languages. Transliteration of Named Entities (NEs) is necessary in many applications, such as machine translation, corpus alignment, cross-language IR, information extraction and automatic lexicon acquisition. All such systems call for high-performance transliteration, which is the focus of shared task in the NEWS 2018 workshop. The objective of the shared task is to promote machine transliteration research by providing a common benchmarking platform for the community to evaluate the state-of-the-art technologies. |
| Tasks | Machine Translation, Transliteration |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2408/ |
| https://www.aclweb.org/anthology/W18-2408 | |
| PWC | https://paperswithcode.com/paper/news-2018-whitepaper |
| Repo | |
| Framework | |
Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data
| Title | Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data |
| Authors | Ramon Ziai, Detmar Meurers |
| Abstract | Analyzing language in context, both from a theoretical and from a computational perspective, is receiving increased interest. Complementing the research in linguistics on discourse and information structure, in computational linguistics identifying discourse concepts was also shown to improve the performance of certain applications, for example, Short Answer Assessment systems (Ziai and Meurers, 2014). Building on the research that established detailed annotation guidelines for manual annotation of information structural concepts for written (Dipper et al., 2007; Ziai and Meurers, 2014) and spoken language data (Calhoun et al., 2010), this paper presents the first approach automating the analysis of focus in authentic written data. Our classification approach combines a range of lexical, syntactic, and semantic features to achieve an accuracy of 78.1{%} for identifying focus. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1011/ |
| https://www.aclweb.org/anthology/N18-1011 | |
| PWC | https://paperswithcode.com/paper/automatic-focus-annotation-bringing-formal |
| Repo | |
| Framework | |
Spurious Ambiguity and Focalization
| Title | Spurious Ambiguity and Focalization |
| Authors | Glyn Morrill, Oriol Valent{'\i}n |
| Abstract | Spurious ambiguity is the phenomenon whereby distinct derivations in grammar may assign the same structural reading, resulting in redundancy in the parse search space and inefficiency in parsing. Understanding the problem depends on identifying the essential mathematical structure of derivations. This is trivial in the case of context free grammar, where the parse structures are ordered trees; in the case of type logical categorial grammar, the parse structures are proof nets. However, with respect to multiplicatives, intrinsic proof nets have not yet been given for displacement calculus, and proof nets for additives, which have applications to polymorphism, are not easy to characterize. In this context we approach here multiplicative-additive spurious ambiguity by means of the proof-theoretic technique of focalization. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/J18-2003/ |
| https://www.aclweb.org/anthology/J18-2003 | |
| PWC | https://paperswithcode.com/paper/spurious-ambiguity-and-focalization |
| Repo | |
| Framework | |
Autonomous Vehicle Fleet Coordination With Deep Reinforcement Learning
| Title | Autonomous Vehicle Fleet Coordination With Deep Reinforcement Learning |
| Authors | Cane Punma |
| Abstract | Autonomous vehicles are becoming more common in city transportation. Companies will begin to find a need to teach these vehicles smart city fleet coordination. Currently, simulation based modeling along with hand coded rules dictate the decision making of these autonomous vehicles. We believe that complex intelligent behavior can be learned by these agents through Reinforcement Learning.In this paper, we discuss our work for solving this system by adapting the Deep Q-Learning (DQN) model to the multi-agent setting. Our approach applies deep reinforcement learning by combining convolutional neural networks with DQN to teach agents to fulfill customer demand in an environment that is partially observ-able to them. We also demonstrate how to utilize transfer learning to teach agents to balance multiple objectives such as navigating to a charging station when its en-ergy level is low. The two evaluations presented show that our solution has shown hat we are successfully able to teach agents cooperation policies while balancing multiple objectives. |
| Tasks | Autonomous Vehicles, Decision Making, Q-Learning, Transfer Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B1EGg7ZCb |
| https://openreview.net/pdf?id=B1EGg7ZCb | |
| PWC | https://paperswithcode.com/paper/autonomous-vehicle-fleet-coordination-with |
| Repo | |
| Framework | |
Part-of-Speech Tagging for Code-Switched, Transliterated Texts without Explicit Language Identification
| Title | Part-of-Speech Tagging for Code-Switched, Transliterated Texts without Explicit Language Identification |
| Authors | Kelsey Ball, Dan Garrette |
| Abstract | Code-switching, the use of more than one language within a single utterance, is ubiquitous in much of the world, but remains a challenge for NLP largely due to the lack of representative data for training models. In this paper, we present a novel model architecture that is trained exclusively on monolingual resources, but can be applied to unseen code-switched text at inference time. The model accomplishes this by jointly maintaining separate word representations for each of the possible languages, or scripts in the case of transliteration, allowing each to contribute to inferences without forcing the model to commit to a language. Experiments on Hindi-English part-of-speech tagging demonstrate that our approach outperforms standard models when training on monolingual text without transliteration, and testing on code-switched text with alternate scripts. |
| Tasks | Language Identification, Part-Of-Speech Tagging, Transliteration, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1347/ |
| https://www.aclweb.org/anthology/D18-1347 | |
| PWC | https://paperswithcode.com/paper/part-of-speech-tagging-for-code-switched-1 |
| Repo | |
| Framework | |
Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial Networks
| Title | Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial Networks |
| Authors | Siyeong Lee, Gwon Hwan An, Suk-Ju Kang |
| Abstract | High dynamic range images contain luminance information of the physical world and provide more realistic experience than conventional low dynamic range images. Because most images have a low dynamic range, recovering the lost dynamic range from a single low dynamic range image is still prevalent. We propose a novel method for restoring the lost dynamic range from a single low dynamic range image through a deep neural network. The proposed method is the first framework to create high dynamic range images based on the estimated multi-exposure stack using the conditional generative adversarial network structure. In this architecture, we train the network by setting an objective function that is a combination of L1 loss and generative adversarial network loss. In addition, this architecture has a simplified structure than the existing networks. In the experimental results, the proposed network generated a multi-exposure stack consisting of realistic images with varying exposure values while avoiding artifacts on public benchmarks, compared with the existing methods. In addition, both the multi-exposure stacks and high dynamic range images estimated by the proposed method are significantly similar to the ground truth than other state-of-the-art algorithms. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Siyeong_Lee_Deep_Recursive_HDRI_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Siyeong_Lee_Deep_Recursive_HDRI_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-recursive-hdri-inverse-tone-mapping |
| Repo | |
| Framework | |
Preferred Answer Selection in Stack Overflow: Better Text Representations … and Metadata, Metadata, Metadata
| Title | Preferred Answer Selection in Stack Overflow: Better Text Representations … and Metadata, Metadata, Metadata |
| Authors | Steven Xu, Andrew Bennett, Doris Hoogeveen, Jey Han Lau, Timothy Baldwin |
| Abstract | Community question answering (cQA) forums provide a rich source of data for facilitating non-factoid question answering over many technical domains. Given this, there is considerable interest in answer retrieval from these kinds of forums. However this is a difficult task as the structure of these forums is very rich, and both metadata and text features are important for successful retrieval. While there has recently been a lot of work on solving this problem using deep learning models applied to question/answer text, this work has not looked at how to make use of the rich metadata available in cQA forums. We propose an attention-based model which achieves state-of-the-art results for text-based answer selection alone, and by making use of complementary meta-data, achieves a substantially higher result over two reference datasets novel to this work. |
| Tasks | Answer Selection, Community Question Answering, Information Retrieval, Question Answering |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6119/ |
| https://www.aclweb.org/anthology/W18-6119 | |
| PWC | https://paperswithcode.com/paper/preferred-answer-selection-in-stack-overflow |
| Repo | |
| Framework | |
Extractive Headline Generation Based on Learning to Rank for Community Question Answering
| Title | Extractive Headline Generation Based on Learning to Rank for Community Question Answering |
| Authors | Tatsuru Higurashi, Hayato Kobayashi, Takeshi Masuyama, Kazuma Murao |
| Abstract | User-generated content such as the questions on community question answering (CQA) forums does not always come with appropriate headlines, in contrast to the news articles used in various headline generation tasks. In such cases, we cannot use paired supervised data, e.g., pairs of articles and headlines, to learn a headline generation model. To overcome this problem, we propose an extractive headline generation method based on learning to rank for CQA that extracts the most informative substring from each question as its headline. Experimental results show that our method outperforms several baselines, including a prefix-based method, which is widely used in real services. |
| Tasks | Community Question Answering, Learning-To-Rank, Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1148/ |
| https://www.aclweb.org/anthology/C18-1148 | |
| PWC | https://paperswithcode.com/paper/extractive-headline-generation-based-on |
| Repo | |
| Framework | |
Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation
| Title | Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation |
| Authors | Ivan Vuli{'c} |
| Abstract | Word vector space specialisation models offer a portable, light-weight approach to fine-tuning arbitrary distributional vector spaces to discern between synonymy and antonymy. Their effectiveness is drawn from external linguistic constraints that specify the exact lexical relation between words. In this work, we show that a careful selection of the external constraints can steer and improve the specialisation. By simply selecting appropriate constraints, we report state-of-the-art results on a suite of tasks with well-defined benchmarks where modeling lexical contrast is crucial: 1) true semantic similarity, with highest reported scores on SimLex-999 and SimVerb-3500 to date; 2) detecting antonyms; and 3) distinguishing antonyms from synonyms. |
| Tasks | Dialogue State Tracking, Representation Learning, Semantic Similarity, Semantic Textual Similarity, Spoken Language Understanding, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3018/ |
| https://www.aclweb.org/anthology/W18-3018 | |
| PWC | https://paperswithcode.com/paper/injecting-lexical-contrast-into-word-vectors |
| Repo | |
| Framework | |
QuAC: Question Answering in Context
| Title | QuAC: Question Answering in Context |
| Authors | Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer |
| Abstract | We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at \url{http://quac.ai}. |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1241/ |
| https://www.aclweb.org/anthology/D18-1241 | |
| PWC | https://paperswithcode.com/paper/quac-question-answering-in-context-1 |
| Repo | |
| Framework | |
Study of Readability of Health Documents with Eye-tracking Approaches
| Title | Study of Readability of Health Documents with Eye-tracking Approaches |
| Authors | Natalia Grabar, Emmanuel Farce, Laurent Sparrow |
| Abstract | |
| Tasks | Eye Tracking |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-7003/ |
| https://www.aclweb.org/anthology/W18-7003 | |
| PWC | https://paperswithcode.com/paper/study-of-readability-of-health-documents-with |
| Repo | |
| Framework | |
Lexical Substitution for Evaluating Compositional Distributional Models
| Title | Lexical Substitution for Evaluating Compositional Distributional Models |
| Authors | Maja Buljan, Sebastian Pad{'o}, Jan {\v{S}}najder |
| Abstract | Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space. They have been predominantly evaluated on limited, artificial tasks such as semantic sentence similarity on hand-constructed datasets. This paper argues for lexical substitution (LexSub) as a means to evaluate CDSMs. LexSub is a more natural task, enables us to evaluate meaning composition at the level of individual words, and provides a common ground to compare CDSMs with dedicated LexSub models. We create a LexSub dataset for CDSM evaluation from a corpus with manual {``}all-words{''} LexSub annotation. Our experiments indicate that the Practical Lexical Function CDSM outperforms simple component-wise CDSMs and performs on par with the context2vec LexSub model using the same context. | |
| Tasks | Natural Language Inference, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2033/ |
| https://www.aclweb.org/anthology/N18-2033 | |
| PWC | https://paperswithcode.com/paper/lexical-substitution-for-evaluating |
| Repo | |
| Framework | |
