Paper Group NANR 60
3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis. Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge. Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text. CCGweb: a New Annotation Tool and a First Quadrilingual CCG Treebank. Compilin …
3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis
| Title | 3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis |
| Authors | Xiaojuan Qi, Zhengzhe Liu, Qifeng Chen, Jiaya Jia |
| Abstract | A future video is the 2D projection of a 3D scene with predicted camera and object motion. Accurate future video prediction inherently requires understanding of 3D motion and geometry of a scene. In this paper, we propose a RGBD scene forecasting model with 3D motion decomposition. We predict ego-motion and foreground motion that are combined to generate a future 3D dynamic scene, which is then projected into a 2D image plane to synthesize future motion, RGB images and depth maps. Optional semantic maps can be integrated. Experimental results on KITTI and Driving datasets show that our model outperforms other state-of-the- arts in forecasting future RGBD dynamic scenes. |
| Tasks | Video Prediction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Qi_3D_Motion_Decomposition_for_RGBD_Future_Dynamic_Scene_Synthesis_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Qi_3D_Motion_Decomposition_for_RGBD_Future_Dynamic_Scene_Synthesis_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-motion-decomposition-for-rgbd-future |
| Repo | |
| Framework | |
Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge
| Title | Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge |
| Authors | Ziran Li, Ning Ding, Zhiyuan Liu, Haitao Zheng, Ying Shen |
| Abstract | Chinese relation extraction is conducted using neural networks with either character-based or word-based inputs, and most existing methods typically suffer from segmentation errors and ambiguity of polysemy. To address the issues, we propose a multi-grained lattice framework (MG lattice) for Chinese relation extraction to take advantage of multi-grained language information and external linguistic knowledge. In this framework, (1) we incorporate word-level information into character sequence inputs so that segmentation errors can be avoided. (2) We also model multiple senses of polysemous words with the help of external linguistic knowledge, so as to alleviate polysemy ambiguity. Experiments on three real-world datasets in distinct domains show consistent and significant superiority and robustness of our model, as compared with other baselines. We will release the source code of this paper in the future. |
| Tasks | Relation Extraction |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1430/ |
| https://www.aclweb.org/anthology/P19-1430 | |
| PWC | https://paperswithcode.com/paper/chinese-relation-extraction-with-multi |
| Repo | |
| Framework | |
Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text
| Title | Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text |
| Authors | Elena Sergeeva, Henghui Zhu, Amir Tahmasebi, Peter Szolovits |
| Abstract | Since the introduction of context-aware token representation techniques such as Embeddings from Language Models (ELMo) and Bidirectional Encoder Representations from Transformers (BERT), there has been numerous reports on improved performance on a variety of natural language tasks. Nevertheless, the degree to which the resulting context-aware representations encode information about morpho-syntactic properties of the word/token in a sentence remains unclear. In this paper, we investigate the application and impact of state-of-the-art neural token representations for automatic cue-conditional speculation and negation scope detection coupled with the independently computed morpho-syntactic information. Through this work, We establish a new state-of-the-art for the BioScope and NegPar corpus. More importantly, we provide a thorough analysis of neural representations and additional features interactions, cue-representation for conditioning, discuss model behavior on different datasets and address the annotation-induced biases in the learned representations. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6221/ |
| https://www.aclweb.org/anthology/D19-6221 | |
| PWC | https://paperswithcode.com/paper/neural-token-representations-and-negation-and |
| Repo | |
| Framework | |
CCGweb: a New Annotation Tool and a First Quadrilingual CCG Treebank
| Title | CCGweb: a New Annotation Tool and a First Quadrilingual CCG Treebank |
| Authors | Kilian Evang, Lasha Abzianidze, Johan Bos |
| Abstract | We present the first open-source graphical annotation tool for combinatory categorial grammar (CCG), and the first set of detailed guidelines for syntactic annotation with CCG, for four languages: English, German, Italian, and Dutch. We also release a parallel pilot CCG treebank based on these guidelines, with 4x100 adjudicated sentences, 10K single-annotator fully corrected sentences, and 82K single-annotator partially corrected sentences. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4005/ |
| https://www.aclweb.org/anthology/W19-4005 | |
| PWC | https://paperswithcode.com/paper/ccgweb-a-new-annotation-tool-and-a-first |
| Repo | |
| Framework | |
Compiling and Analysing a Corpus of Transcribed Spoken Gulf Pidgin Arabic Based on Length of Stay in the Gulf
| Title | Compiling and Analysing a Corpus of Transcribed Spoken Gulf Pidgin Arabic Based on Length of Stay in the Gulf |
| Authors | Najah Albaqawi, Michael Oakes |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5602/ |
| https://www.aclweb.org/anthology/W19-5602 | |
| PWC | https://paperswithcode.com/paper/compiling-and-analysing-a-corpus-of |
| Repo | |
| Framework | |
Proceedings of the 3rd Workshop on Arabic Corpus Linguistics
| Title | Proceedings of the 3rd Workshop on Arabic Corpus Linguistics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5600/ |
| https://www.aclweb.org/anthology/W19-5600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-3rd-workshop-on-arabic |
| Repo | |
| Framework | |
Handling cross-cutting properties in automatic inference of lexical classes: A case study of Chintang
| Title | Handling cross-cutting properties in automatic inference of lexical classes: A case study of Chintang |
| Authors | Olga Zamaraeva, Kristen Howell, Emily M. Bender H cross-cutting properties in automatic inference of lexical classes: A case study of Chintang, ling |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6005/ |
| https://www.aclweb.org/anthology/W19-6005 | |
| PWC | https://paperswithcode.com/paper/handling-cross-cutting-properties-in |
| Repo | |
| Framework | |
Sample Efficient Active Learning of Causal Trees
| Title | Sample Efficient Active Learning of Causal Trees |
| Authors | Kristjan Greenewald, Dmitriy Katz, Karthikeyan Shanmugam, Sara Magliacane, Murat Kocaoglu, Enric Boix Adsera, Guy Bresler |
| Abstract | We consider the problem of experimental design for learning causal graphs that have a tree structure. We propose an adaptive framework that determines the next intervention based on a Bayesian prior updated with the outcomes of previous experiments, focusing on the setting where observational data is cheap (assumed infinite) and interventional data is expensive. While information greedy approaches are popular in active learning, we show that in this setting they can be exponentially suboptimal (in the number of interventions required), and instead propose an algorithm that exploits graph structure in the form of a centrality measure. If infinite interventional data is available, we show that the algorithm requires a number of interventions less than or equal to a factor of 2 times the minimum achievable number. We show that the algorithm and the associated theory can be adapted to the setting where each performed intervention yields finitely many samples. Several extensions are also presented, to the case where a specified set of nodes cannot be intervened on, to the case where $K$ interventions are scheduled at once, and to the fully adaptive case where each experiment yields only one sample. In the case of finite interventional data, through simulated experiments we show that our algorithms outperform different adaptive baseline algorithms. |
| Tasks | Active Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9575-sample-efficient-active-learning-of-causal-trees |
| http://papers.nips.cc/paper/9575-sample-efficient-active-learning-of-causal-trees.pdf | |
| PWC | https://paperswithcode.com/paper/sample-efficient-active-learning-of-causal |
| Repo | |
| Framework | |
How to Use Gazetteers for Entity Recognition with Neural Models
| Title | How to Use Gazetteers for Entity Recognition with Neural Models |
| Authors | Simone Magnolini, Valerio Piccioni, Vevake Balaraman, Marco Guerini, Bernardo Magnini |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5807/ |
| https://www.aclweb.org/anthology/W19-5807 | |
| PWC | https://paperswithcode.com/paper/how-to-use-gazetteers-for-entity-recognition |
| Repo | |
| Framework | |
Learning to remember: Dynamic Generative Memory for Continual Learning
| Title | Learning to remember: Dynamic Generative Memory for Continual Learning |
| Authors | Oleksiy Ostapenko, Mihai Puscas, Tassilo Klein, Moin Nabi |
| Abstract | Continuously trainable models should be able to learn from a stream of data over an undefined period of time. This becomes even more difficult in a strictly incremental context, where data access to previously seen categories is not possible. To that end, we propose making use of a conditional generative adversarial model where the generator is used as a memory module through neural masking to emulate neural plasticity in the human brain. This memory module is further associated with a dynamic capacity expansion mechanism. Taken together, this method facilitates a resource efficient capacity adaption to accommodate new tasks, while retaining previously attained knowledge. The proposed approach outperforms state-of-the-art algorithms on publicly available datasets, overcoming catastrophic forgetting. |
| Tasks | Continual Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1lIzhC9FX |
| https://openreview.net/pdf?id=H1lIzhC9FX | |
| PWC | https://paperswithcode.com/paper/learning-to-remember-dynamic-generative |
| Repo | |
| Framework | |
Findings of the WMT 2019 Biomedical Translation Shared Task: Evaluation for MEDLINE Abstracts and Biomedical Terminologies
| Title | Findings of the WMT 2019 Biomedical Translation Shared Task: Evaluation for MEDLINE Abstracts and Biomedical Terminologies |
| Authors | Rachel Bawden, Kevin Bretonnel Cohen, Cristian Grozea, Antonio Jimeno Yepes, Madeleine Kittner, Martin Krallinger, Nancy Mah, Aurelie Neveol, Mariana Neves, Felipe Soares, Amy Siu, Karin Verspoor, Maika Vicente Navarro |
| Abstract | In the fourth edition of the WMT Biomedical Translation task, we considered a total of six languages, namely Chinese (zh), English (en), French (fr), German (de), Portuguese (pt), and Spanish (es). We performed an evaluation of automatic translations for a total of 10 language directions, namely, zh/en, en/zh, fr/en, en/fr, de/en, en/de, pt/en, en/pt, es/en, and en/es. We provided training data based on MEDLINE abstracts for eight of the 10 language pairs and test sets for all of them. In addition to that, we offered a new sub-task for the translation of terms in biomedical terminologies for the en/es language direction. Higher BLEU scores (close to 0.5) were obtained for the es/en, en/es and en/pt test sets, as well as for the terminology sub-task. After manual validation of the primary runs, some submissions were judged to be better than the reference translations, for instance, for de/en, en/es and es/en. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5403/ |
| https://www.aclweb.org/anthology/W19-5403 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-wmt-2019-biomedical |
| Repo | |
| Framework | |
Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
| Title | Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers |
| Authors | Hanh Nguyen, Dirk Hovy |
| Abstract | User reviews provide a significant source of information for companies to understand their market and audience. In order to discover broad trends in this source, researchers have typically used topic models such as Latent Dirichlet Allocation (LDA). However, while there are metrics to choose the {``}best{''} number of topics, it is not clear whether the resulting topics can also provide in-depth, actionable product analysis. Our paper examines this issue by analyzing user reviews from the Best Buy US website for smart speakers. Using coherence scores to choose topics, we test whether the results help us to understand user interests and concerns. We find that while coherence scores are a good starting point to identify a number of topics, it still requires manual adaptation based on domain knowledge to provide market insights. We show that the resulting dimensions capture brand performance and differences, and differentiate the market into two distinct groups with different properties. | |
| Tasks | Topic Models |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5510/ |
| https://www.aclweb.org/anthology/D19-5510 | |
| PWC | https://paperswithcode.com/paper/hey-siri-ok-google-alexa-a-topic-modeling-of |
| Repo | |
| Framework | |
Tuning Multilingual Transformers for Language-Specific Named Entity Recognition
| Title | Tuning Multilingual Transformers for Language-Specific Named Entity Recognition |
| Authors | Mikhail Arkhipov, Maria Trofimova, Yuri Kuratov, Alexey Sorokin |
| Abstract | Our paper addresses the problem of multilingual named entity recognition on the material of 4 languages: Russian, Bulgarian, Czech and Polish. We solve this task using the BERT model. We use a hundred languages multilingual model as base for transfer to the mentioned Slavic languages. Unsupervised pre-training of the BERT model on these 4 languages allows to significantly outperform baseline neural approaches and multilingual BERT. Additional improvement is achieved by extending BERT with a word-level CRF layer. Our system was submitted to BSNLP 2019 Shared Task on Multilingual Named Entity Recognition and demonstrated top performance in multilingual setting for two competition metrics. We open-sourced NER models and BERT model pre-trained on the four Slavic languages. |
| Tasks | Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3712/ |
| https://www.aclweb.org/anthology/W19-3712 | |
| PWC | https://paperswithcode.com/paper/tuning-multilingual-transformers-for-language |
| Repo | |
| Framework | |
Precision-Recall Balanced Topic Modelling
| Title | Precision-Recall Balanced Topic Modelling |
| Authors | Seppo Virtanen, Mark Girolami |
| Abstract | Topic models are becoming increasingly relevant probabilistic models for dimensionality reduction of text data, inferring topics that capture meaningful themes of frequently co-occurring terms. We formulate topic modelling as an information retrieval task, where the goal is, based on the latent topic representation, to capture relevant term co-occurrence patterns. We evaluate performance for this task rigorously with regard to two types of errors, false negatives and positives, based on the well-known precision-recall trade-off and provide a statistical model that allows the user to balance between the contributions of the different error types. When the user focuses solely on the contribution of false negatives ignoring false positives altogether our proposed model reduces to a standard topic model. Extensive experiments demonstrate the proposed approach is effective and infers more coherent topics than existing related approaches. |
| Tasks | Dimensionality Reduction, Information Retrieval, Topic Models |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8900-precision-recall-balanced-topic-modelling |
| http://papers.nips.cc/paper/8900-precision-recall-balanced-topic-modelling.pdf | |
| PWC | https://paperswithcode.com/paper/precision-recall-balanced-topic-modelling |
| Repo | |
| Framework | |
Sentence Simplification for Semantic Role Labelling and Information Extraction
| Title | Sentence Simplification for Semantic Role Labelling and Information Extraction |
| Authors | Richard Evans, Constantin Orasan |
| Abstract | In this paper, we report on the extrinsic evaluation of an automatic sentence simplification method with respect to two NLP tasks: semantic role labelling (SRL) and information extraction (IE). The paper begins with our observation of challenges in the intrinsic evaluation of sentence simplification systems, which motivates the use of extrinsic evaluation of these systems with respect to other NLP tasks. We describe the two NLP systems and the test data used in the extrinsic evaluation, and present arguments and evidence motivating the integration of a sentence simplification step as a means of improving the accuracy of these systems. Our evaluation reveals that their performance is improved by the simplification step: the SRL system is better able to assign semantic roles to the majority of the arguments of verbs and the IE system is better able to identify fillers for all IE template slots. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1033/ |
| https://www.aclweb.org/anthology/R19-1033 | |
| PWC | https://paperswithcode.com/paper/sentence-simplification-for-semantic-role |
| Repo | |
| Framework | |
