Paper Group NANR 168
Proceedings of the Student Research Workshop Associated with RANLP 2019. Unsupervised Hierarchical Story Infilling. Calculating the Optimal Step in Shift-Reduce Dependency Parsing: From Cubic to Linear Time. Tree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations. Copula Multi-label Learning. Fully Quant …
Proceedings of the Student Research Workshop Associated with RANLP 2019
| Title | Proceedings of the Student Research Workshop Associated with RANLP 2019 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2000/ |
| https://www.aclweb.org/anthology/R19-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-student-research-workshop-8 |
| Repo | |
| Framework | |
Unsupervised Hierarchical Story Infilling
| Title | Unsupervised Hierarchical Story Infilling |
| Authors | Daphne Ippolito, David Grangier, Chris Callison-Burch, Douglas Eck |
| Abstract | Story infilling involves predicting words to go into a missing span from a story. This challenging task has the potential to transform interactive tools for creative writing. However, state-of-the-art conditional language models have trouble balancing fluency and coherence with novelty and diversity. We address this limitation with a hierarchical model which first selects a set of rare words and then generates text conditioned on that set. By relegating the high entropy task of picking rare words to a word-sampling model, the second-stage model conditioned on those words can achieve high fluency and coherence by searching for likely sentences, without sacrificing diversity. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2405/ |
| https://www.aclweb.org/anthology/W19-2405 | |
| PWC | https://paperswithcode.com/paper/unsupervised-hierarchical-story-infilling |
| Repo | |
| Framework | |
Calculating the Optimal Step in Shift-Reduce Dependency Parsing: From Cubic to Linear Time
| Title | Calculating the Optimal Step in Shift-Reduce Dependency Parsing: From Cubic to Linear Time |
| Authors | Mark-Jan Nederhof |
| Abstract | We present a new cubic-time algorithm to calculate the optimal next step in shift-reduce dependency parsing, relative to ground truth, commonly referred to as dynamic oracle. Unlike existing algorithms, it is applicable if the training corpus contains non-projective structures. We then show that for a projective training corpus, the time complexity can be improved from cubic to linear. |
| Tasks | Dependency Parsing |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1018/ |
| https://www.aclweb.org/anthology/Q19-1018 | |
| PWC | https://paperswithcode.com/paper/calculating-the-optimal-step-in-shift-reduce |
| Repo | |
| Framework | |
Tree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations
| Title | Tree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations |
| Authors | Sumeet Kumar, Kathleen Carley |
| Abstract | Learning from social-media conversations has gained significant attention recently because of its applications in areas like rumor detection. In this research, we propose a new way to represent social-media conversations as binarized constituency trees that allows comparing features in source-posts and their replies effectively. Moreover, we propose to use convolution units in Tree LSTMs that are better at learning patterns in features obtained from the source and reply posts. Our Tree LSTM models employ multi-task (stance + rumor) learning and propagate the useful stance signal up in the tree for rumor classification at the root node. The proposed models achieve state-of-the-art performance, outperforming the current best model by 12{%} and 15{%} on F1-macro for rumor-veracity classification and stance classification tasks respectively. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1498/ |
| https://www.aclweb.org/anthology/P19-1498 | |
| PWC | https://paperswithcode.com/paper/tree-lstms-with-convolution-units-to-predict |
| Repo | |
| Framework | |
Copula Multi-label Learning
| Title | Copula Multi-label Learning |
| Authors | Weiwei Liu |
| Abstract | A formidable challenge in multi-label learning is to model the interdependencies between labels and features. Unfortunately, the statistical properties of existing multi-label dependency modelings are still not well understood. Copulas are a powerful tool for modeling dependence of multivariate data, and achieve great success in a wide range of applications, such as finance, econometrics and systems neuroscience. This inspires us to develop a novel copula multi-label learning paradigm for modeling label and feature dependencies. The copula based paradigm enables to reveal new statistical insights in multi-label learning. In particular, the paper first leverages the kernel trick to construct continuous distribution in the output space, and then estimates our proposed model semiparametrically where the copula is modeled parametrically, while the marginal distributions are modeled nonparametrically. Theoretically, we show that our estimator is an unbiased and consistent estimator and follows asymptotically a normal distribution. Moreover, we bound the mean squared error of estimator. The experimental results from various domains validate the superiority of our proposed approach. |
| Tasks | Multi-Label Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8863-copula-multi-label-learning |
| http://papers.nips.cc/paper/8863-copula-multi-label-learning.pdf | |
| PWC | https://paperswithcode.com/paper/copula-multi-label-learning |
| Repo | |
| Framework | |
Fully Quantized Network for Object Detection
| Title | Fully Quantized Network for Object Detection |
| Authors | Rundong Li, Yan Wang, Feng Liang, Hongwei Qin, Junjie Yan, Rui Fan |
| Abstract | Efficient neural network inference is important in a number of practical domains, such as deployment in mobile settings. An effective method for increasing inference efficiency is to use low bitwidth arithmetic, which can subsequently be accelerated using dedicated hardware. However, designing effective quantization schemes while maintaining network accuracy is challenging. In particular, current techniques face difficulty in performing fully end-to-end quantization, making use of aggressively low bitwidth regimes such as 4-bit, and applying quantized networks to complex tasks such as object detection. In this paper, we demonstrate that many of these difficulties arise because of instability during the fine-tuning stage of the quantization process, and propose several novel techniques to overcome these instabilities. We apply our techniques to produce fully quantized 4-bit detectors based on RetinaNet and Faster R-CNN, and show that these achieve state-of-the-art performance for quantized detectors. The mAP loss due to quantization using our methods is more than 3.8x less than the loss from existing methods. |
| Tasks | Object Detection, Quantization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Fully_Quantized_Network_for_Object_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Fully_Quantized_Network_for_Object_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fully-quantized-network-for-object-detection |
| Repo | |
| Framework | |
Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag
| Title | Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag |
| Authors | Xinyu Xiao, Lingfeng Wang, Bin Fan, Shinming Xiang, Chunhong Pan |
| Abstract | In the current video captioning models, the video frames are collected in one network and the semantics are mixed into one feature, which not only increase the difficulty of the caption decoding, but also decrease the interpretability of the captioning models. To address these problems, we propose an Adaptive Semantic Guidance Network (ASGN), which instantiates the whole video semantics to different POS-aware semantics with the supervision of part of speech (POS) tag. In the encoding process, the POS tag activates the related neurons and parses the whole semantic information into corresponding encoded video representations. Furthermore, the potential of the model is stimulated by the POS-aware video features. In the decoding process, the related video features of noun and verb are used as the supervision to construct a new adaptive attention model which can decide whether to attend to the video feature or not. With the explicit improving of the interpretability of the network, the learning process is more transparent and the results are more predictable. Extensive experiments demonstrate the effectiveness of our model when compared with state-of-the-art models. |
| Tasks | Video Captioning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1213/ |
| https://www.aclweb.org/anthology/D19-1213 | |
| PWC | https://paperswithcode.com/paper/guiding-the-flowing-of-semantics |
| Repo | |
| Framework | |
Speculation and Negation detection in French biomedical corpora
| Title | Speculation and Negation detection in French biomedical corpora |
| Authors | Cl{'e}ment Dalloux, Vincent Claveau, Natalia Grabar |
| Abstract | In this work, we propose to address the detection of negation and speculation, and of their scope, in French biomedical documents. It has been indeed observed that they play an important role and provide crucial clues for other NLP applications. Our methods are based on CRFs and BiLSTM. We reach up to 97.21 {%} and 91.30 {%} F-measure for the detection of negation and speculation cues, respectively, using CRFs. For the computing of scope, we reach up to 90.81 {%} and 86.73 {%} F-measure on negation and speculation, respectively, using BiLSTM-CRF fed with word embeddings. |
| Tasks | Negation Detection, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1026/ |
| https://www.aclweb.org/anthology/R19-1026 | |
| PWC | https://paperswithcode.com/paper/speculation-and-negation-detection-in-french |
| Repo | |
| Framework | |
Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning
| Title | Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning |
| Authors | Ruiyi Zhang, Tong Yu, Yilin Shen, Hongxia Jin, Changyou Chen |
| Abstract | Text-based interactive recommendation provides richer user preferences and has demonstrated advantages over traditional interactive recommender systems. However, recommendations can easily violate preferences of users from their past natural-language feedback, since the recommender needs to explore new items for further improvement. To alleviate this issue, we propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference, which is incorporated into the standard RL objective of maximizing expected cumulative future rewards. Our proposed framework is general and is further extended to the task of constrained text generation. Empirical results show that the proposed method yields consistent improvement relative to standard RL methods. |
| Tasks | Recommendation Systems, Text Generation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9657-text-based-interactive-recommendation-via-constraint-augmented-reinforcement-learning |
| http://papers.nips.cc/paper/9657-text-based-interactive-recommendation-via-constraint-augmented-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/text-based-interactive-recommendation-via |
| Repo | |
| Framework | |
Nikolov-Radivchev at SemEval-2019 Task 6: Offensive Tweet Classification with BERT and Ensembles
| Title | Nikolov-Radivchev at SemEval-2019 Task 6: Offensive Tweet Classification with BERT and Ensembles |
| Authors | Alex Nikolov, Victor Radivchev |
| Abstract | This paper examines different approaches and models towards offensive tweet classification which were used as a part of the OffensEval 2019 competition. It reviews Tweet preprocessing, techniques for overcoming unbalanced class distribution in the provided test data, and comparison of multiple attempted machine learning models. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2123/ |
| https://www.aclweb.org/anthology/S19-2123 | |
| PWC | https://paperswithcode.com/paper/nikolov-radivchev-at-semeval-2019-task-6 |
| Repo | |
| Framework | |
Personalizing Grammatical Error Correction: Adaptation to Proficiency Level and L1
| Title | Personalizing Grammatical Error Correction: Adaptation to Proficiency Level and L1 |
| Authors | Maria Nadejde, Joel Tetreault |
| Abstract | Grammar error correction (GEC) systems have become ubiquitous in a variety of software applications, and have started to approach human-level performance for some datasets. However, very little is known about how to efficiently personalize these systems to the user{'}s characteristics, such as their proficiency level and first language, or to emerging domains of text. We present the first results on adapting a general purpose neural GEC system to both the proficiency level and the first language of a writer, using only a few thousand annotated sentences. Our study is the broadest of its kind, covering five proficiency levels and twelve different languages, and comparing three different adaptation scenarios: adapting to the proficiency level only, to the first language only, or to both aspects simultaneously. We show that tailoring to both scenarios achieves the largest performance improvement (3.6 F0.5) relative to a strong baseline. |
| Tasks | Grammatical Error Correction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5504/ |
| https://www.aclweb.org/anthology/D19-5504 | |
| PWC | https://paperswithcode.com/paper/personalizing-grammatical-error-correction |
| Repo | |
| Framework | |
Scalable Neural Theorem Proving on Knowledge Bases and Natural Language
| Title | Scalable Neural Theorem Proving on Knowledge Bases and Natural Language |
| Authors | Pasquale Minervini, Matko Bosnjak, Tim Rocktäschel, Edward Grefenstette, Sebastian Riedel |
| Abstract | Reasoning over text and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering. Transducing text to logical forms which can be operated on is a brittle and error-prone process. Operating directly on text by jointly learning representations and transformations thereof by means of neural architectures that lack the ability to learn and exploit general rules can be very data-inefficient and not generalise correctly. These issues are addressed by Neural Theorem Provers (NTPs) (Rocktäschel & Riedel, 2017), neuro-symbolic systems based on a continuous relaxation of Prolog’s backward chaining algorithm, where symbolic unification between atoms is replaced by a differentiable operator computing the similarity between their embedding representations. In this paper, we first propose Neighbourhood-approximated Neural Theorem Provers (NaNTPs) consisting of two extensions toNTPs, namely a) a method for drastically reducing the previously prohibitive time and space complexity during inference and learning, and b) an attention mechanism for improving the rule learning process, deeming them usable on real-world datasets. Then, we propose a novel approach for jointly reasoning over KB facts and textual mentions, by jointly embedding them in a shared embedding space. The proposed method is able to extract rules and provide explanations—involving both textual patterns and KB relations—from large KBs and text corpora. We show that NaNTPs perform on par with NTPs at a fraction of a cost, and can achieve competitive link prediction results on challenging large-scale datasets, including WN18, WN18RR, and FB15k-237 (with and without textual mentions) while being able to provide explanations for each prediction and extract interpretable rules. |
| Tasks | Automated Theorem Proving, Link Prediction, Question Answering, Reading Comprehension |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJzmzn0ctX |
| https://openreview.net/pdf?id=BJzmzn0ctX | |
| PWC | https://paperswithcode.com/paper/scalable-neural-theorem-proving-on-knowledge |
| Repo | |
| Framework | |
Developing and Orchestrating a Portfolio of Natural Legal Language Processing and Document Curation Services
| Title | Developing and Orchestrating a Portfolio of Natural Legal Language Processing and Document Curation Services |
| Authors | Georg Rehm, Juli{'a}n Moreno-Schneider, Jorge Gracia, Artem Revenko, Victor Mireles, Maria Khvalchik, Ilan Kernerman, Andis Lagzdins, Marcis Pinnis, Artus Vasilevskis, Elena Leitner, Jan Milde, Pia Wei{\ss}enhorn |
| Abstract | We present a portfolio of natural legal language processing and document curation services currently under development in a collaborative European project. First, we give an overview of the project and the different use cases, while, in the main part of the article, we focus upon the 13 different processing services that are being deployed in different prototype applications using a flexible and scalable microservices architecture. Their orchestration is operationalised using a content and document curation workflow manager. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2207/ |
| https://www.aclweb.org/anthology/W19-2207 | |
| PWC | https://paperswithcode.com/paper/developing-and-orchestrating-a-portfolio-of |
| Repo | |
| Framework | |
Slang Detection and Identification
| Title | Slang Detection and Identification |
| Authors | Zhengqi Pei, Zhewei Sun, Yang Xu |
| Abstract | The prevalence of informal language such as slang presents challenges for natural language systems, particularly in the automatic discovery of flexible word usages. Previous work has explored slang in terms of dictionary construction, sentiment analysis, word formation, and interpretation, but scarce research has attempted the basic problem of slang detection and identification. We examine the extent to which deep learning methods support automatic detection and identification of slang from natural sentences using a combination of bidirectional recurrent neural networks, conditional random field, and multilayer perceptron. We test these models based on a comprehensive set of linguistic features in sentence-level detection and token-level identification of slang. We found that a prominent feature of slang is the surprising use of words across syntactic categories or syntactic shift (e.g., verb-noun). Our best models detect the presence of slang at the sentence level with an F1-score of 0.80 and identify its exact position at the token level with an F1-Score of 0.50. |
| Tasks | Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1082/ |
| https://www.aclweb.org/anthology/K19-1082 | |
| PWC | https://paperswithcode.com/paper/slang-detection-and-identification |
| Repo | |
| Framework | |
AX Semantics’ Submission to the SIGMORPHON 2019 Shared Task
| Title | AX Semantics’ Submission to the SIGMORPHON 2019 Shared Task |
| Authors | Andreas Madsack, Robert Wei{\ss}graeber |
| Abstract | This paper describes the AX Semantics{'} submission to the SIGMORPHON 2019 shared task on morphological reinflection. We implemented two systems, both tackling the task for all languages in one codebase, without any underlying language specific features. The first one is an encoder-decoder model using AllenNLP; the second system uses the same model modified by a custom trainer that trains only with the target language resources after a specific threshold. We especially focused on building an implementation using AllenNLP with out-of-the-box methods to facilitate easy operation and reuse. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4201/ |
| https://www.aclweb.org/anthology/W19-4201 | |
| PWC | https://paperswithcode.com/paper/ax-semantics-submission-to-the-sigmorphon |
| Repo | |
| Framework | |
