Paper Group NANR 70
Conceptualisation and Annotation of Drug Nonadherence Information for Knowledge Extraction from Patient-Generated Texts. Inverse Path Tracing for Joint Material and Lighting Estimation. Neural Network Alignment for Sentential Paraphrases. Duality of Link Prediction and Entailment Graph Induction. SSoC: Learning Spontaneous and Self-Organizing Commu …
Conceptualisation and Annotation of Drug Nonadherence Information for Knowledge Extraction from Patient-Generated Texts
| Title | Conceptualisation and Annotation of Drug Nonadherence Information for Knowledge Extraction from Patient-Generated Texts |
| Authors | Anja Belz, Richard Hoile, Elizabeth Ford, Azam Mullick |
| Abstract | Approaches to knowledge extraction (KE) in the health domain often start by annotating text to indicate the knowledge to be extracted, and then use the annotated text to train systems to perform the KE. This may work for annotat- ing named entities or other contiguous noun phrases (drugs, some drug effects), but be- comes increasingly difficult when items tend to be expressed across multiple, possibly non- contiguous, syntactic constituents (e.g. most descriptions of drug effects in user-generated text). Other issues include that it is not al- ways clear how annotations map to actionable insights, or how they scale up to, or can form part of, more complex KE tasks. This paper reports our efforts in developing an approach to extracting knowledge about drug nonadher- ence from health forums which led us to con- clude that development cannot proceed in sep- arate steps but that all aspects{—}from concep- tualisation to annotation scheme development, annotation, KE system training and knowl- edge graph instantiation{—}are interdependent and need to be co-developed. Our aim in this paper is two-fold: we describe a generally ap- plicable framework for developing a KE ap- proach, and present a specific KE approach, developed with the framework, for the task of gathering information about antidepressant drug nonadherence. We report the conceptual- isation, the annotation scheme, the annotated corpus, and an analysis of annotated texts. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5526/ |
| https://www.aclweb.org/anthology/D19-5526 | |
| PWC | https://paperswithcode.com/paper/conceptualisation-and-annotation-of-drug |
| Repo | |
| Framework | |
Inverse Path Tracing for Joint Material and Lighting Estimation
| Title | Inverse Path Tracing for Joint Material and Lighting Estimation |
| Authors | Dejan Azinovic, Tzu-Mao Li, Anton Kaplanyan, Matthias Niessner |
| Abstract | Modern computer vision algorithms have brought significant advancement to 3D geometry reconstruction. However, illumination and material reconstruction remain less studied, with current approaches assuming very simplified models for materials and illumination. We introduce Inverse Path Tracing, a novel approach to jointly estimate the material properties of objects and light sources in indoor scenes by using an invertible light transport simulation. We assume a coarse geometry scan, along with corresponding images and camera poses. The key contribution of this work is an accurate and simultaneous retrieval of light sources and physically based material properties (e.g., diffuse reflectance, specular reflectance, roughness, etc.) for the purpose of editing and re-rendering the scene under new conditions. To this end, we introduce a novel optimization method using a differentiable Monte Carlo renderer that computes derivatives with respect to the estimated unknown illumination and material properties. This enables joint optimization for physically correct light transport and material models using a tailored stochastic gradient descent. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Azinovic_Inverse_Path_Tracing_for_Joint_Material_and_Lighting_Estimation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Azinovic_Inverse_Path_Tracing_for_Joint_Material_and_Lighting_Estimation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-path-tracing-for-joint-material-and-1 |
| Repo | |
| Framework | |
Neural Network Alignment for Sentential Paraphrases
| Title | Neural Network Alignment for Sentential Paraphrases |
| Authors | Jessica Ouyang, Kathy McKeown |
| Abstract | We present a monolingual alignment system for long, sentence- or clause-level alignments, and demonstrate that systems designed for word- or short phrase-based alignment are ill-suited for these longer alignments. Our system is capable of aligning semantically similar spans of arbitrary length. We achieve significantly higher recall on aligning phrases of four or more words and outperform state-of-the- art aligners on the long alignments in the MSR RTE corpus. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1467/ |
| https://www.aclweb.org/anthology/P19-1467 | |
| PWC | https://paperswithcode.com/paper/neural-network-alignment-for-sentential |
| Repo | |
| Framework | |
Duality of Link Prediction and Entailment Graph Induction
| Title | Duality of Link Prediction and Entailment Graph Induction |
| Authors | Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, Mark Steedman |
| Abstract | Link prediction and entailment graph induction are often treated as different problems. In this paper, we show that these two problems are actually complementary. We train a link prediction model on a knowledge graph of assertions extracted from raw text. We propose an entailment score that exploits the new facts discovered by the link prediction model, and then form entailment graphs between relations. We further use the learned entailments to predict improved link prediction scores. Our results show that the two tasks can benefit from each other. The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores. |
| Tasks | Link Prediction |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1468/ |
| https://www.aclweb.org/anthology/P19-1468 | |
| PWC | https://paperswithcode.com/paper/duality-of-link-prediction-and-entailment |
| Repo | |
| Framework | |
SSoC: Learning Spontaneous and Self-Organizing Communication for Multi-Agent Collaboration
| Title | SSoC: Learning Spontaneous and Self-Organizing Communication for Multi-Agent Collaboration |
| Authors | Xiangyu Kong, Jing Li, Bo Xin, Yizhou Wang |
| Abstract | Multi-agent collaboration is required by numerous real-world problems. Although distributed setting is usually adopted by practical systems, local range communication and information aggregation still matter in fulfilling complex tasks. For multi-agent reinforcement learning, many previous studies have been dedicated to design an effective communication architecture. However, existing models usually suffer from an ossified communication structure, e.g., most of them predefine a particular communication mode by specifying a fixed time frequency and spatial scope for agents to communicate regardless of necessity. Such design is incapable of dealing with multi-agent scenarios that are capricious and complicated, especially when only partial information is available. Motivated by this, we argue that the solution is to build a spontaneous and self-organizing communication (SSoC) learning scheme. By treating the communication behaviour as an explicit action, SSoC learns to organize communication in an effective and efficient way. Particularly, it enables each agent to spontaneously decide when and who to send messages based on its observed states. In this way, a dynamic inter-agent communication channel is established in an online and self-organizing manner. The agents also learn how to adaptively aggregate the received messages and its own hidden states to execute actions. Various experiments have been conducted to demonstrate that SSoC really learns intelligent message passing among agents located far apart. With such agile communications, we observe that effective collaboration tactics emerge which have not been mastered by the compared baselines. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJ4vlh0qtm |
| https://openreview.net/pdf?id=rJ4vlh0qtm | |
| PWC | https://paperswithcode.com/paper/ssoc-learning-spontaneous-and-self-organizing |
| Repo | |
| Framework | |
To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies
| Title | To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies |
| Authors | Dirk V{"a}th, Ngoc Thang Vu |
| Abstract | In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show that each individual method improves the rewards and the task success rate but combining these methods in a Rainbow agent, which performs best across tasks and environments, is a non-trivial task. We, therefore, provide insights about the influence of each method on the combination and how to combine them to form a Rainbow agent. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5908/ |
| https://www.aclweb.org/anthology/W19-5908 | |
| PWC | https://paperswithcode.com/paper/to-combine-or-not-to-combine-a-rainbow-deep |
| Repo | |
| Framework | |
A Sequence Modeling Approach for Structured Data Extraction from Unstructured Text
| Title | A Sequence Modeling Approach for Structured Data Extraction from Unstructured Text |
| Authors | Jayati Deshmukh, Annervaz K M, Shubhashis Sengupta |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5809/ |
| https://www.aclweb.org/anthology/W19-5809 | |
| PWC | https://paperswithcode.com/paper/a-sequence-modeling-approach-for-structured |
| Repo | |
| Framework | |
Contextualized Representations for Low-resource Utterance Tagging
| Title | Contextualized Representations for Low-resource Utterance Tagging |
| Authors | Bhargavi Paranjape, Graham Neubig |
| Abstract | Utterance-level analysis of the speaker{'}s intentions and emotions is a core task in conversational understanding. Depending on the end objective of the conversational understanding task, different categorical dialog-act or affect labels are expertly designed to cover specific aspects of the speakers{'} intentions or emotions respectively. Accurately annotating with these labels requires a high level of human expertise, and thus applying this process to a large conversation corpus or new domains is prohibitively expensive. The resulting paucity of data limits the use of sophisticated neural models. In this paper, we tackle these limitations by performing unsupervised training of utterance representations from a large corpus of spontaneous dialogue data. Models initialized with these representations achieve competitive performance on utterance-level dialogue-act recognition and emotion classification, especially in low-resource settings encountered when analyzing conversations in new domains. |
| Tasks | Emotion Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5909/ |
| https://www.aclweb.org/anthology/W19-5909 | |
| PWC | https://paperswithcode.com/paper/contextualized-representations-for-low |
| Repo | |
| Framework | |
DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension
| Title | DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension |
| Authors | Kai Sun, Dian Yu, Jianshu Chen, Dong Yu, Yejin Choi, Claire Cardie |
| Abstract | We present DREAM, the first dialogue-based multiple-choice reading comprehension data set. Collected from English as a Foreign Language examinations designed by human experts to evaluate the comprehension level of Chinese learners of English, our data set contains 10,197 multiple-choice questions for 6,444 dialogues. In contrast to existing reading comprehension data sets, DREAM is the first to focus on in-depth multi-turn multi-party dialogue understanding. DREAM is likely to present significant challenges for existing reading comprehension systems: 84{%} of answers are non-extractive, 85{%} of questions require reasoning beyond a single sentence, and 34{%} of questions also involve commonsense knowledge. We apply several popular neural reading comprehension models that primarily exploit surface information within the text and find them to, at best, just barely outperform a rule-based approach. We next investigate the effects of incorporating dialogue structure and different kinds of general world knowledge into both rule-based and (neural and non-neural) machine learning-based reading comprehension models. Experimental results on the DREAM data set show the effectiveness of dialogue structure and general world knowledge. DREAM is available at https://dataset.org/dream/. |
| Tasks | Dialogue Understanding, Reading Comprehension |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1014/ |
| https://www.aclweb.org/anthology/Q19-1014 | |
| PWC | https://paperswithcode.com/paper/dream-a-challenge-data-set-and-models-for |
| Repo | |
| Framework | |
Escaping Flat Areas via Function-Preserving Structural Network Modifications
| Title | Escaping Flat Areas via Function-Preserving Structural Network Modifications |
| Authors | Yannic Kilcher, Gary Bécigneul, Thomas Hofmann |
| Abstract | Hierarchically embedding smaller networks in larger networks, e.g.~by increasing the number of hidden units, has been studied since the 1990s. The main interest was in understanding possible redundancies in the parameterization, as well as in studying how such embeddings affect critical points. We take these results as a point of departure to devise a novel strategy for escaping from flat regions of the error surface and to address the slow-down of gradient-based methods experienced in plateaus of saddle points. The idea is to expand the dimensionality of a network in a way that guarantees the existence of new escape directions. We call this operation the opening of a tunnel. One may then continue with the larger network either temporarily, i.e.~closing the tunnel later, or permanently, i.e.~iteratively growing the network, whenever needed. We develop our method for fully-connected as well as convolutional layers. Moreover, we present a practical version of our algorithm that requires no network structure modification and can be deployed as plug-and-play into any current deep learning framework. Experimentally, our method shows significant speed-ups. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1eadi0cFQ |
| https://openreview.net/pdf?id=H1eadi0cFQ | |
| PWC | https://paperswithcode.com/paper/escaping-flat-areas-via-function-preserving |
| Repo | |
| Framework | |
Feature Transformers: A Unified Representation Learning Framework for Lifelong Learning
| Title | Feature Transformers: A Unified Representation Learning Framework for Lifelong Learning |
| Authors | Hariharan Ravishankar, Rahul Venkataramani, Saihareesh Anamandra, Prasad Sudhakar |
| Abstract | Despite the recent advances in representation learning, lifelong learning continues to be one of the most challenging and unconquered problems. Catastrophic forgetting and data privacy constitute two of the important challenges for a successful lifelong learner. Further, existing techniques are designed to handle only specific manifestations of lifelong learning, whereas a practical lifelong learner is expected to switch and adapt seamlessly to different scenarios. In this paper, we present a single, unified mathematical framework for handling the myriad variants of lifelong learning, while alleviating these two challenges. We utilize an external memory to store only the features representing past data and learn richer and newer representations incrementally through transformation neural networks - feature transformers. We define, simulate and demonstrate exemplary performance on a realistic lifelong experimental setting using the MNIST rotations dataset, paving the way for practical lifelong learners. To illustrate the applicability of our method in data sensitive domains like healthcare, we study the pneumothorax classification problem from X-ray images, achieving near gold standard performance. We also benchmark our approach with a number of state-of-the art methods on MNIST rotations and iCIFAR100 datasets demonstrating superior performance. |
| Tasks | Representation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJfvAoC9YQ |
| https://openreview.net/pdf?id=BJfvAoC9YQ | |
| PWC | https://paperswithcode.com/paper/feature-transformers-a-unified-representation |
| Repo | |
| Framework | |
MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy
| Title | MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy |
| Authors | Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang |
| Abstract | We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning scenarios. Compared to the well-studied many-class many-shot and few-class few-shot problems, MCFS problem commonly occurs in practical applications but is rarely studied. MCFS brings new challenges because it needs to distinguish between many classes, but only a few samples per class are available for training. In this paper, we propose memory-augmented hierarchical-classification network (MahiNet)'' for MCFS learning. It addresses the many-class’’ problem by exploring the class hierarchy, e.g., the coarse-class label that covers a subset of fine classes, which helps to narrow down the candidates for the fine class and is cheaper to obtain. MahiNet uses a convolutional neural network (CNN) to extract features, and integrates a memory-augmented attention module with a multi-layer perceptron (MLP) to produce the probabilities over coarse and fine classes. While the MLP extends the linear classifier, the attention module extends a KNN classifier, both together targeting the ‘‘`few-shot’’ problem. We design different training strategies of MahiNet for supervised learning and meta-learning. Moreover, we propose two novel benchmark datasets ‘‘mcfsImageNet’’ (as a subset of ImageNet) and ‘‘mcfsOmniglot’’ (re-splitted Omniglot) specifically for MCFS problem. In experiments, we show that MahiNet outperforms several state-of-the-art models on MCFS classification tasks in both supervised learning and meta-learning scenarios. | |
| Tasks | Few-Shot Learning, Meta-Learning, Omniglot |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJlcV2Actm |
| https://openreview.net/pdf?id=rJlcV2Actm | |
| PWC | https://paperswithcode.com/paper/mahinet-a-neural-network-for-many-class-few |
| Repo | |
| Framework | |
THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq
| Title | THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq |
| Authors | Byung-Doh Oh, Pranav Maneriker, Nanjiang Jiang |
| Abstract | This paper describes the OSU submission to the SIGMORPHON 2019 shared task, Crosslinguality and Context in Morphology. Our system addresses the \textit{contextual morphological analysis} subtask of Task 2, which is to produce the morphosyntactic description (MSD) of each fully inflected word within a given sentence. We frame this as a sequence generation task and employ a neural encoder-decoder (seq2seq) architecture to generate the sequence of MSD tags given the encoded representation of each token. Follow-up analyses reveal that our system most significantly improves performance on morphologically complex languages whose inflected word forms typically have longer MSD tag sequences. In addition, our system seems to capture the structured correlation between MSD tags, such as that between the {``}verb{''} tag and TAM-related tags. | |
| Tasks | Morphological Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4210/ |
| https://www.aclweb.org/anthology/W19-4210 | |
| PWC | https://paperswithcode.com/paper/thomas-the-hegemonic-osu-morphological |
| Repo | |
| Framework | |
Modeling language constructs with fuzzy sets: some approaches, examples and interpretations
| Title | Modeling language constructs with fuzzy sets: some approaches, examples and interpretations |
| Authors | Pavlo Kapustin, Michael Kapustin |
| Abstract | We present and discuss a couple of approaches, including different types of projections, and some examples, discussing the use of fuzzy sets for modeling meaning of certain types of language constructs. We are mostly focusing on words other than adjectives and linguistic hedges as these categories are the most studied from before. We discuss logical and linguistic interpretations of membership functions. We argue that using fuzzy sets for modeling meaning of words and other natural language constructs, along with situations described with natural language is interesting both from purely linguistic perspective, and also as a knowledge representation for problems of computational linguistics and natural language processing. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0604/ |
| https://www.aclweb.org/anthology/W19-0604 | |
| PWC | https://paperswithcode.com/paper/modeling-language-constructs-with-fuzzy-sets |
| Repo | |
| Framework | |
Beyond BLEU:Training Neural Machine Translation with Semantic Similarity
| Title | Beyond BLEU:Training Neural Machine Translation with Semantic Similarity |
| Authors | John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel, Graham Neubig |
| Abstract | While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy. However, training with BLEU has some limitations: it doesn{'}t assign partial credit, it has a limited range of output values, and it can penalize semantically correct hypotheses if they differ lexically from the reference. In this paper, we introduce an alternative reward function for optimizing NMT systems that is based on recent work in semantic similarity. We evaluate on four disparate languages trans-lated to English, and find that training with our proposed metric results in better translations as evaluated by BLEU, semantic similarity, and human evaluation, and also that the optimization procedure converges faster. Analysis suggests that this is because the proposed metric is more conducive to optimization, assigning partial credit and providing more diversity in scores than BLEU |
| Tasks | Machine Translation, Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1427/ |
| https://www.aclweb.org/anthology/P19-1427 | |
| PWC | https://paperswithcode.com/paper/beyond-bleutraining-neural-machine |
| Repo | |
| Framework | |
