Paper Group NANR 135
The AFRL WMT19 Systems: Old Favorites and New Tricks. Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019). Proceedings of the First Workshop on NLP for Conversational AI. SIMILE: Introducing Sequential Information towards More Effective Imitation Learning. Seeing more than whitespace — Tokenisation and …
The AFRL WMT19 Systems: Old Favorites and New Tricks
| Title | The AFRL WMT19 Systems: Old Favorites and New Tricks |
| Authors | Jeremy Gwinnup, Grant Erdmann, Tim Anderson |
| Abstract | This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT19 evaluation campaign. This year, we refine our approach to training popular neural machine translation toolkits, experiment with a new domain adaptation technique and again measure improvements in performance on the Russian{–}English language pair. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5318/ |
| https://www.aclweb.org/anthology/W19-5318 | |
| PWC | https://paperswithcode.com/paper/the-afrl-wmt19-systems-old-favorites-and-new |
| Repo | |
| Framework | |
Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019)
| Title | Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8700/ |
| https://www.aclweb.org/anthology/W19-8700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-human-informed-translation |
| Repo | |
| Framework | |
Proceedings of the First Workshop on NLP for Conversational AI
| Title | Proceedings of the First Workshop on NLP for Conversational AI |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4100/ |
| https://www.aclweb.org/anthology/W19-4100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-nlp-for |
| Repo | |
| Framework | |
SIMILE: Introducing Sequential Information towards More Effective Imitation Learning
| Title | SIMILE: Introducing Sequential Information towards More Effective Imitation Learning |
| Authors | Yutong Bai, Lingxi Xie |
| Abstract | Reinforcement learning (RL) is a metaheuristic aiming at teaching an agent to interact with an environment and maximizing the reward in a complex task. RL algorithms often encounter the difficulty in defining a reward function in a sparse solution space. Imitation learning (IL) deals with this issue by providing a few expert demonstrations, and then either mimicking the expert’s behavior (behavioral cloning, BC) or recovering the reward function by assuming the optimality of the expert (inverse reinforcement learning, IRL). Conventional IL approaches formulate the agent policy by mapping one single state to a distribution over actions, which did not consider sequential information. This strategy can be less accurate especially in IL, a weakly supervised learning environment, especially when the number of expert demonstrations is limited. This paper presents an effective approach named Sequential IMItation LEarning (SIMILE). The core idea is to introduce sequential information, so that an agent can refer to both the current state and past state-action pairs to make a decision. We formulate our approach into a recurrent model, and instantiate it using LSTM so as to fuse both long-term and short-term information. SIMILE is a generalized IL framework which is easily applied to BL and IRL, two major types of IL algorithms. Experiments are performed on several robot controlling tasks in OpenAI Gym. SIMILE not only achieves performance gain over the baseline approaches, but also enjoys the benefit of faster convergence and better stability of testing performance. These advantages verify a higher learning efficiency of SIMILE, and implies its potential applications in real-world scenarios, i.e., when the agent-environment interaction is more difficult and/or expensive. |
| Tasks | Imitation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hyghb2Rct7 |
| https://openreview.net/pdf?id=Hyghb2Rct7 | |
| PWC | https://paperswithcode.com/paper/simile-introducing-sequential-information |
| Repo | |
| Framework | |
Seeing more than whitespace — Tokenisation and disambiguation in a North S'ami grammar checker
| Title | Seeing more than whitespace — Tokenisation and disambiguation in a North S'ami grammar checker |
| Authors | Linda Wiechetek, Sjur N{\o}rsteb{\o} Moshagen, Kevin Brubeck Unhammer Tokenization, {disambiguation of potential compounds in North S{'a}mi grammar checking} |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6007/ |
| https://www.aclweb.org/anthology/W19-6007 | |
| PWC | https://paperswithcode.com/paper/seeing-more-than-whitespace-tokenisation-and |
| Repo | |
| Framework | |
Pix2Scene: Learning Implicit 3D Representations from Images
| Title | Pix2Scene: Learning Implicit 3D Representations from Images |
| Authors | Sai Rajeswar, Fahim Mannan, Florian Golemo, David Vazquez, Derek Nowrouzezahrai, Aaron Courville |
| Abstract | Modelling 3D scenes from 2D images is a long-standing problem in computer vision with implications in, e.g., simulation and robotics. We propose pix2scene, a deep generative-based approach that implicitly models the geometric properties of a scene from images. Our method learns the depth and orientation of scene points visible in images. Our model can then predict the structure of a scene from various, previously unseen view points. It relies on a bi-directional adversarial learning mechanism to generate scene representations from a latent code, inferring the 3D representation of the underlying scene geometry. We showcase a novel differentiable renderer to train the 3D model in an end-to-end fashion, using only images. We demonstrate the generative ability of our model qualitatively on both a custom dataset and on ShapeNet. Finally, we evaluate the effectiveness of the learned 3D scene representation in supporting a 3D spatial reasoning. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJeem3C9F7 |
| https://openreview.net/pdf?id=BJeem3C9F7 | |
| PWC | https://paperswithcode.com/paper/pix2scene-learning-implicit-3d |
| Repo | |
| Framework | |
L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving
| Title | L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving |
| Authors | Weixin Lu, Yao Zhou, Guowei Wan, Shenhua Hou, Shiyu Song |
| Abstract | We present L3-Net - a novel learning-based LiDAR localization system that achieves centimeter-level localization accuracy, comparable to prior state-of-the-art systems with hand-crafted pipelines. Rather than relying on these hand-crafted modules, we innovatively implement the use of various deep neural network structures to establish a learning-based approach. L3-Net learns local descriptors specifically optimized for matching in different real-world driving scenarios. 3D convolutions over a cost volume built in the solution space significantly boosts the localization accuracy. RNNs are demonstrated to be effective in modeling the vehicle’s dynamics, yielding better temporal smoothness and accuracy. We comprehensively validate the effectiveness of our approach using freshly collected datasets. Multiple trials of repetitive data collection over the same road and areas make our dataset ideal for testing localization systems. The SunnyvaleBigLoop sequences, with a year’s time interval between the collected mapping and testing data, made it quite challenging, but the low localization error of our method in these datasets demonstrates its maturity for real industrial implementation. |
| Tasks | Autonomous Driving |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lu_L3-Net_Towards_Learning_Based_LiDAR_Localization_for_Autonomous_Driving_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lu_L3-Net_Towards_Learning_Based_LiDAR_Localization_for_Autonomous_Driving_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/l3-net-towards-learning-based-lidar |
| Repo | |
| Framework | |
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
| Title | Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5300/ |
| https://www.aclweb.org/anthology/W19-5300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fourth-conference-on-2 |
| Repo | |
| Framework | |
Grammar Error Correction in Morphologically Rich Languages: The Case of Russian
| Title | Grammar Error Correction in Morphologically Rich Languages: The Case of Russian |
| Authors | Alla Rozovskaya, Dan Roth |
| Abstract | Until now, most of the research in grammar error correction focused on English, and the problem has hardly been explored for other languages. We address the task of correcting writing mistakes in morphologically rich languages, with a focus on Russian. We present a corrected and error-tagged corpus of Russian learner writing and develop models that make use of existing state-of-the-art methods that have been well studied for English. Although impressive results have recently been achieved for grammar error correction of non-native English writing, these results are limited to domains where plentiful training data are available. Because annotation is extremely costly, these approaches are not suitable for the majority of domains and languages. We thus focus on methods that use {``}minimal supervision{''}; that is, those that do not rely on large amounts of annotated training data, and show how existing minimal-supervision approaches extend to a highly inflectional language such as Russian. The results demonstrate that these methods are particularly useful for correcting mistakes in grammatical phenomena that involve rich morphology. | |
| Tasks | |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1001/ |
| https://www.aclweb.org/anthology/Q19-1001 | |
| PWC | https://paperswithcode.com/paper/grammar-error-correction-in-morphologically |
| Repo | |
| Framework | |
From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry
| Title | From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry |
| Authors | Zhuohan Xie, Jey Han Lau, Trevor Cohn |
| Abstract | In this paper, we adapt Deep-speare, a joint neural network model for English sonnets, to Chinese poetry. We illustrate characteristics of Chinese quatrain and explain our architecture as well as training and generation procedure, which differs from Shakespeare sonnets in several aspects. We analyse the generated poetry and find that model works well for Chinese poetry, as it can: (1) generate coherent 4-line quatrains of different topics; and (2) capture rhyme automatically (to a certain extent). |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1002/ |
| https://www.aclweb.org/anthology/U19-1002 | |
| PWC | https://paperswithcode.com/paper/from-shakespeare-to-li-bai-adapting-a-sonnet |
| Repo | |
| Framework | |
On the Compositionality Prediction of Noun Phrases using Poincar'e Embeddings
| Title | On the Compositionality Prediction of Noun Phrases using Poincar'e Embeddings |
| Authors | Abhik Jana, Dima Puzyrev, Alex Panchenko, er, Pawan Goyal, Chris Biemann, Animesh Mukherjee |
| Abstract | The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositionality is a task that has been frequently addressed with distributional semantic models. We introduce a novel technique to blend hierarchical information with distributional information for predicting compositionality. In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar{'e} embeddings in addition to the distributional information to detect compositionality for noun phrases. Using a weighted average of the distributional similarity and a Poincar{'e} similarity function, we obtain consistent and substantial, statistically significant improvement across three gold standard datasets over state-of-the-art models based on distributional information only. Unlike traditional approaches that solely use an unsupervised setting, we have also framed the problem as a supervised task, obtaining comparable improvements. Further, we publicly release our Poincar{'e} embeddings, which are trained on the output of handcrafted lexical-syntactic patterns on a large corpus. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1316/ |
| https://www.aclweb.org/anthology/P19-1316 | |
| PWC | https://paperswithcode.com/paper/on-the-compositionality-prediction-of-noun-1 |
| Repo | |
| Framework | |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
| Title | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3000/ |
| https://www.aclweb.org/anthology/N19-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-conference-of-the-2 |
| Repo | |
| Framework | |
Mixed Multi-Head Self-Attention for Neural Machine Translation
| Title | Mixed Multi-Head Self-Attention for Neural Machine Translation |
| Authors | Hongyi Cui, Shohei Iida, Po-Hsuan Hung, Takehito Utsuro, Masaaki Nagata |
| Abstract | Recently, the Transformer becomes a state-of-the-art architecture in the filed of neural machine translation (NMT). A key point of its high-performance is the multi-head self-attention which is supposed to allow the model to independently attend to information from different representation subspaces. However, there is no explicit mechanism to ensure that different attention heads indeed capture different features, and in practice, redundancy has occurred in multiple heads. In this paper, we argue that using the same global attention in multiple heads limits multi-head self-attention{'}s capacity for learning distinct features. In order to improve the expressiveness of multi-head self-attention, we propose a novel Mixed Multi-Head Self-Attention (MMA) which models not only global and local attention but also forward and backward attention in different attention heads. This enables the model to learn distinct representations explicitly among multiple heads. In our experiments on both WAT17 English-Japanese as well as IWSLT14 German-English translation task, we show that, without increasing the number of parameters, our models yield consistent and significant improvements (0.9 BLEU scores on average) over the strong Transformer baseline. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5622/ |
| https://www.aclweb.org/anthology/D19-5622 | |
| PWC | https://paperswithcode.com/paper/mixed-multi-head-self-attention-for-neural |
| Repo | |
| Framework | |
A Comparison on Fine-grained Pre-trained Embeddings for the WMT19Chinese-English News Translation Task
| Title | A Comparison on Fine-grained Pre-trained Embeddings for the WMT19Chinese-English News Translation Task |
| Authors | Zhenhao Li, Lucia Specia |
| Abstract | This paper describes our submission to the WMT 2019 Chinese-English (zh-en) news translation shared task. Our systems are based on RNN architectures with pre-trained embeddings which utilize character and sub-character information. We compare models with these different granularity levels using different evaluating metics. We find that a finer granularity embeddings can help the model according to character level evaluation and that the pre-trained embeddings can also be beneficial for model performance marginally when the training data is limited. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5324/ |
| https://www.aclweb.org/anthology/W19-5324 | |
| PWC | https://paperswithcode.com/paper/a-comparison-on-fine-grained-pre-trained |
| Repo | |
| Framework | |
Cognate Projection for Low-Resource Inflection Generation
| Title | Cognate Projection for Low-Resource Inflection Generation |
| Authors | Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, Grzegorz Kondrak |
| Abstract | We propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task. The results on four language pairs show the method is effective when no low-resource training data is available. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4202/ |
| https://www.aclweb.org/anthology/W19-4202 | |
| PWC | https://paperswithcode.com/paper/cognate-projection-for-low-resource |
| Repo | |
| Framework | |
