Paper Group NANR 20
PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules. Capturing Dialogue State Variable Dependencies with an Energy-based Neural Dialogue State Tracker. SyntaxFest 2019 Invited talk - Dependency distance minimization: facts, theory and predictions. Capsule Network with Interactive Att …
PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules
| Title | PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules |
| Authors | Youngsoo Jang, Jongmin Lee, Jaeyoung Park, Kyeng-Hun Lee, Pierre Lison, Kee-Eung Kim |
| Abstract | We present PyOpenDial, a Python-based domain-independent, open-source toolkit for spoken dialogue systems. Recent advances in core components of dialogue systems, such as speech recognition, language understanding, dialogue management, and language generation, harness deep learning to achieve state-of-the-art performance. The original OpenDial, implemented in Java, provides a plugin architecture to integrate external modules, but lacks Python bindings, making it difficult to interface with popular deep learning frameworks such as Tensorflow or PyTorch. To this end, we re-implemented OpenDial in Python and extended the toolkit with a number of novel functionalities for neural dialogue state tracking and action planning. We describe the overall architecture and its extensions, and illustrate their use on an example where the system response model is implemented with a recurrent neural network. |
| Tasks | Dialogue Management, Dialogue State Tracking, Speech Recognition, Spoken Dialogue Systems, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3032/ |
| https://www.aclweb.org/anthology/D19-3032 | |
| PWC | https://paperswithcode.com/paper/pyopendial-a-python-based-domain-independent |
| Repo | |
| Framework | |
Capturing Dialogue State Variable Dependencies with an Energy-based Neural Dialogue State Tracker
| Title | Capturing Dialogue State Variable Dependencies with an Energy-based Neural Dialogue State Tracker |
| Authors | Anh Duong Trinh, Robert J. Ross, John D. Kelleher |
| Abstract | Dialogue state tracking requires the population and maintenance of a multi-slot frame representation of the dialogue state. Frequently, dialogue state tracking systems assume independence between slot values within a frame. In this paper we argue that treating the prediction of each slot value as an independent prediction task may ignore important associations between the slot values, and, consequently, we argue that treating dialogue state tracking as a structured prediction problem can help to improve dialogue state tracking performance. To support this argument, the research presented in this paper is structured into three stages: (i) analyzing variable dependencies in dialogue data; (ii) applying an energy-based methodology to model dialogue state tracking as a structured prediction task; and (iii) evaluating the impact of inter-slot relationships on model performance. Overall we demonstrate that modelling the associations between target slots with an energy-based formalism improves dialogue state tracking performance in a number of ways. |
| Tasks | Dialogue State Tracking, Structured Prediction |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5910/ |
| https://www.aclweb.org/anthology/W19-5910 | |
| PWC | https://paperswithcode.com/paper/capturing-dialogue-state-variable |
| Repo | |
| Framework | |
SyntaxFest 2019 Invited talk - Dependency distance minimization: facts, theory and predictions
| Title | SyntaxFest 2019 Invited talk - Dependency distance minimization: facts, theory and predictions |
| Authors | Ramon Ferrer-i-Cancho |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7901/ |
| https://www.aclweb.org/anthology/W19-7901 | |
| PWC | https://paperswithcode.com/paper/syntaxfest-2019-invited-talk-dependency |
| Repo | |
| Framework | |
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification
| Title | Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification |
| Authors | Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu |
| Abstract | Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context. The main challenge comes from multi-aspect sentences, which express multiple sentiment polarities towards different targets, resulting in overlapped feature representation. However, most existing neural models tend to utilize static pooling operation or attention mechanism to identify sentimental words, which therefore insufficient for dealing with overlapped features. To solve this problem, we propose to utilize capsule network to construct vector-based feature representation and cluster features by an EM routing algorithm. Furthermore, interactive attention mechanism is introduced in the capsule routing procedure to model the semantic relationship between aspect terms and context. The iterative routing also enables encoding sentence from a global perspective. Experimental results on three datasets show that our proposed model achieves state-of-the-art performance. |
| Tasks | Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1551/ |
| https://www.aclweb.org/anthology/D19-1551 | |
| PWC | https://paperswithcode.com/paper/capsule-network-with-interactive-attention |
| Repo | |
| Framework | |
CBNU System for SIGMORPHON 2019 Shared Task 2: a Pipeline Model
| Title | CBNU System for SIGMORPHON 2019 Shared Task 2: a Pipeline Model |
| Authors | Uygun Shadikhodjaev, Jae Sung Lee |
| Abstract | In this paper we describe our system for morphological analysis and lemmatization in context, using a transformer-based sequence to sequence model and a biaffine attention based BiLSTM model. First, a lemma is produced for a given word, and then both the lemma and the given word are used for morphological analysis. We also make use of character level word encodings and trainable encodings to improve accuracy. Overall, our system ranked fifth in lemmatization and sixth in morphological accuracy among twelve systems, and demonstrated considerable improvements over the baseline in morphological analysis. |
| Tasks | Lemmatization, Morphological Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4204/ |
| https://www.aclweb.org/anthology/W19-4204 | |
| PWC | https://paperswithcode.com/paper/cbnu-system-for-sigmorphon-2019-shared-task-2 |
| Repo | |
| Framework | |
Leveraging Adjective-Noun Phrasing Knowledge for Comparison Relation Prediction in Text-to-SQL
| Title | Leveraging Adjective-Noun Phrasing Knowledge for Comparison Relation Prediction in Text-to-SQL |
| Authors | Haoyan Liu, Lei Fang, Qian Liu, Bei Chen, Jian-Guang Lou, Zhoujun Li |
| Abstract | One key component in text-to-SQL is to predict the comparison relations between columns and their values. To the best of our knowledge, no existing models explicitly introduce external common knowledge to address this problem, thus their capabilities of predicting comparison relations are limited beyond training data. In this paper, we propose to leverage adjective-noun phrasing knowledge mined from the web to predict the comparison relations in text-to-SQL. Experimental results on both the original and the re-split Spider dataset show that our approach achieves significant improvement over state-of-the-art methods on comparison relation prediction. |
| Tasks | Text-To-Sql |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1356/ |
| https://www.aclweb.org/anthology/D19-1356 | |
| PWC | https://paperswithcode.com/paper/leveraging-adjective-noun-phrasing-knowledge |
| Repo | |
| Framework | |
Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network
| Title | Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network |
| Authors | Lingxue Song, Dihong Gong, Zhifeng Li, Changsong Liu, Wei Liu |
| Abstract | Deep Convolutional Neural Networks (CNNs) have been pushing the frontier of face recognition over past years. However, existing CNN models are far less accurate when handling partially occluded faces. These general face models generalize poorly for occlusions on variable facial areas. Inspired by the fact that human visual system explicitly ignores the occlusion and only focuses on the non-occluded facial areas, we propose a mask learning strategy to find and discard corrupted feature elements from recognition. A mask dictionary is firstly established by exploiting the differences between the top conv features of occluded and occlusion-free face pairs using innovatively designed pairwise differential siamese network (PDSN). Each item of this dictionary captures the correspondence between occluded facial areas and corrupted feature elements, which is named Feature Discarding Mask (FDM). When dealing with a face image with random partial occlusions, we generate its FDM by combining relevant dictionary items and then multiply it with the original features to eliminate those corrupted feature elements from recognition. Comprehensive experiments on both synthesized and realistic occluded face datasets show that the proposed algorithm significantly outperforms the state-of-the-art systems. |
| Tasks | Face Recognition, Robust Face Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Song_Occlusion_Robust_Face_Recognition_Based_on_Mask_Learning_With_Pairwise_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Song_Occlusion_Robust_Face_Recognition_Based_on_Mask_Learning_With_Pairwise_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/occlusion-robust-face-recognition-based-on-1 |
| Repo | |
| Framework | |
Distraction-Aware Shadow Detection
| Title | Distraction-Aware Shadow Detection |
| Authors | Quanlong Zheng, Xiaotian Qiao, Ying Cao, Rynson W.H. Lau |
| Abstract | Shadow detection is an important and challenging task for scene understanding. Despite promising results from recent deep learning based methods. Existing works still struggle with ambiguous cases where the visual appearances of shadow and non-shadow regions are similar (referred to as distraction in our context). In this paper, we propose a Distraction-aware Shadow Detection Network (DSDNet) by explicitly learning and integrating the semantics of visual distraction regions in an end-to-end framework. At the core of our framework is a novel standalone, differentiable Distraction-aware Shadow (DS) module, which allows us to learn distraction-aware, discriminative features for robust shadow detection, by explicitly predicting false positives and false negatives. We conduct extensive experiments on three public shadow detection datasets, SBU, UCF and ISTD, to evaluate our method. Experimental results demonstrate that our model can boost shadow detection performance, by effectively suppressing the detection of false positives and false negatives, achieving state-of-the-art results. |
| Tasks | Scene Understanding, Shadow Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zheng_Distraction-Aware_Shadow_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zheng_Distraction-Aware_Shadow_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/distraction-aware-shadow-detection |
| Repo | |
| Framework | |
Corpus Building for Low Resource Languages in the DARPA LORELEI Program
| Title | Corpus Building for Low Resource Languages in the DARPA LORELEI Program |
| Authors | Jennifer Tracey, Stephanie Strassel, Ann Bies, Zhiyi Song, Michael Arrigo, Kira Griffitt, Dana Delgado, Dave Graff, Seth Kulick, Justin Mott, Neil Kuster |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6808/ |
| https://www.aclweb.org/anthology/W19-6808 | |
| PWC | https://paperswithcode.com/paper/corpus-building-for-low-resource-languages-in |
| Repo | |
| Framework | |
Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis
| Title | Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis |
| Authors | Hiroki Ouchi, Jun Suzuki, Kentaro Inui |
| Abstract | In transductive learning, an unlabeled test set is used for model training. Although this setting deviates from the common assumption of a completely unseen test set, it is applicable in many real-world scenarios, wherein the texts to be processed are known in advance. However, despite its practical advantages, transductive learning is underexplored in natural language processing. Here we conduct an empirical study of transductive learning for neural models and demonstrate its utility in syntactic and semantic tasks. Specifically, we fine-tune language models (LMs) on an unlabeled test set to obtain test-set-specific word representations. Through extensive experiments, we demonstrate that despite its simplicity, transductive LM fine-tuning consistently improves state-of-the-art neural models in in-domain and out-of-domain settings. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1379/ |
| https://www.aclweb.org/anthology/D19-1379 | |
| PWC | https://paperswithcode.com/paper/transductive-learning-of-neural-language |
| Repo | |
| Framework | |
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
| Title | Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference |
| Authors | Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan, Iryna Gurevych |
| Abstract | While recent progress on abstractive summarization has led to remarkably fluent summaries, factual errors in generated summaries still severely limit their use in practice. In this paper, we evaluate summaries produced by state-of-the-art models via crowdsourcing and show that such errors occur frequently, in particular with more abstractive models. We study whether textual entailment predictions can be used to detect such errors and if they can be reduced by reranking alternative predicted summaries. That leads to an interesting downstream application for entailment models. In our experiments, we find that out-of-the-box entailment models trained on NLI datasets do not yet offer the desired performance for the downstream task and we therefore release our annotations as additional test data for future extrinsic evaluations of NLI. |
| Tasks | Abstractive Text Summarization, Natural Language Inference |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1213/ |
| https://www.aclweb.org/anthology/P19-1213 | |
| PWC | https://paperswithcode.com/paper/ranking-generated-summaries-by-correctness-an |
| Repo | |
| Framework | |
Domain Adaptation with BERT-based Domain Classification and Data Selection
| Title | Domain Adaptation with BERT-based Domain Classification and Data Selection |
| Authors | Xiaofei Ma, Peng Xu, Zhiguo Wang, Ramesh Nallapati, Bing Xiang |
| Abstract | The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data. For example, the pre-trained BERT model can be easily fine-tuned with just one additional output layer to create a state-of-the-art model for a wide range of tasks. However, the fine-tuned BERT model suffers considerably at zero-shot when applied to a different domain. In this paper, we present a novel two-step domain adaptation framework based on curriculum learning and domain-discriminative data selection. The domain adaptation is conducted in a mostly unsupervised manner using a small target domain validation set for hyper-parameter tuning. We tested the framework on four large public datasets with different domain similarities and task types. Our framework outperforms a popular discrepancy-based domain adaptation method on most transfer tasks while consuming only a fraction of the training budget. |
| Tasks | Domain Adaptation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6109/ |
| https://www.aclweb.org/anthology/D19-6109 | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-with-bert-based-domain |
| Repo | |
| Framework | |
SpatialNet: A Declarative Resource for Spatial Relations
| Title | SpatialNet: A Declarative Resource for Spatial Relations |
| Authors | Morgan Ulinski, Bob Coyne, Julia Hirschberg |
| Abstract | This paper introduces SpatialNet, a novel resource which links linguistic expressions to actual spatial configurations. SpatialNet is based on FrameNet (Ruppenhofer et al., 2016) and VigNet (Coyne et al., 2011), two resources which use frame semantics to encode lexical meaning. SpatialNet uses a deep semantic representation of spatial relations to provide a formal description of how a language expresses spatial information. This formal representation of the lexical semantics of spatial language also provides a consistent way to represent spatial meaning across multiple languages. In this paper, we describe the structure of SpatialNet, with examples from English and German. We also show how SpatialNet can be combined with other existing NLP tools to create a text-to-scene system for a language. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1607/ |
| https://www.aclweb.org/anthology/W19-1607 | |
| PWC | https://paperswithcode.com/paper/spatialnet-a-declarative-resource-for-spatial |
| Repo | |
| Framework | |
Tagging modality in Oceanic languages of Melanesia
| Title | Tagging modality in Oceanic languages of Melanesia |
| Authors | Annika Tjuka, Lena Wei{\ss}mann, Kilu von Prince |
| Abstract | Primary data from small, low-resource languages of Oceania have only recently become available through language documentation. In our study, we explore corpus data of five Oceanic languages of Melanesia which are known to be mood-prominent (in the sense of Bhat, 1999). In order to find out more about tense, aspect, modality, and polarity, we tagged these categories in a subset of our corpora. For the category of modality, we developed a novel tag set (MelaTAMP, 2017), which categorizes clauses into factual, possible, and counterfactual. Based on an analysis of the inter-annotator consistency, we argue that our tag set for the modal domain is efficient for our subject languages and might be useful for other languages and purposes. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4008/ |
| https://www.aclweb.org/anthology/W19-4008 | |
| PWC | https://paperswithcode.com/paper/tagging-modality-in-oceanic-languages-of |
| Repo | |
| Framework | |
A preconditioned accelerated stochastic gradient descent algorithm
| Title | A preconditioned accelerated stochastic gradient descent algorithm |
| Authors | Alexandru Onose, Seyed Iman Mossavat, Henk-Jan H. Smilde |
| Abstract | We propose a preconditioned accelerated stochastic gradient method suitable for large scale optimization. We derive sufficient convergence conditions for the minimization of convex functions using a generic class of diagonal preconditioners and provide a formal convergence proof based on a framework originally used for on-line learning. Inspired by recent popular adaptive per-feature algorithms, we propose a specific preconditioner based on the second moment of the gradient. The sufficient convergence conditions motivate a critical adaptation of the per-feature updates in order to ensure convergence. We show empirical results for the minimization of convex and non-convex cost functions, in the context of neural network training. The method compares favorably with respect to current, first order, stochastic optimization methods. |
| Tasks | Stochastic Optimization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJgODj05KX |
| https://openreview.net/pdf?id=HJgODj05KX | |
| PWC | https://paperswithcode.com/paper/a-preconditioned-accelerated-stochastic |
| Repo | |
| Framework | |
