Paper Group NANR 59
Modelling Tibetan Verbal Morphology. CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization. Noisy Neural Language Modeling for Typing Prediction in BCI Communication. Investigating Political Herd Mentality: A Community Sentiment Based Approach. A Study of Latent Structured Prediction Approaches to Passage Reranking. Sentence Boundary Detectio …
Modelling Tibetan Verbal Morphology
| Title | Modelling Tibetan Verbal Morphology |
| Authors | Qianji Di, Ekaterina Vylomova, Tim Baldwin |
| Abstract | |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1005/ |
| https://www.aclweb.org/anthology/U19-1005 | |
| PWC | https://paperswithcode.com/paper/modelling-tibetan-verbal-morphology |
| Repo | |
| Framework | |
CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization
| Title | CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization |
| Authors | Mingyu Ding, Zhe Wang, Jiankai Sun, Jianping Shi, Ping Luo |
| Abstract | Camera re-localization is an important but challenging task in applications like robotics and autonomous driving. Recently, retrieval-based methods have been considered as a promising direction as they can be easily generalized to novel scenes. Despite significant progress has been made, we observe that the performance bottleneck of previous methods actually lies in the retrieval module. These methods use the same features for both retrieval and relative pose regression tasks which have potential conflicts in learning. To this end, here we present a coarse-to-fine retrieval-based deep learning framework, which includes three steps, i.e., image-based coarse retrieval, pose-based fine retrieval and precise relative pose regression. With our carefully designed retrieval module, the relative pose regression task can be surprisingly simpler. We design novel retrieval losses with batch hard sampling criterion and two-stage retrieval to locate samples that adapt to the relative pose regression task. Extensive experiments show that our model (CamNet) outperforms the state-of-the-art methods by a large margin on both indoor and outdoor datasets. |
| Tasks | Autonomous Driving |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ding_CamNet_Coarse-to-Fine_Retrieval_for_Camera_Re-Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ding_CamNet_Coarse-to-Fine_Retrieval_for_Camera_Re-Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/camnet-coarse-to-fine-retrieval-for-camera-re |
| Repo | |
| Framework | |
Noisy Neural Language Modeling for Typing Prediction in BCI Communication
| Title | Noisy Neural Language Modeling for Typing Prediction in BCI Communication |
| Authors | Rui Dong, David Smith, Shiran Dudy, Steven Bedrick |
| Abstract | Language models have broad adoption in predictive typing tasks. When the typing history contains numerous errors, as in open-vocabulary predictive typing with brain-computer interface (BCI) systems, we observe significant performance degradation in both n-gram and recurrent neural network language models trained on clean text. In evaluations of ranking character predictions, training recurrent LMs on noisy text makes them much more robust to noisy histories, even when the error model is misspecified. We also propose an effective strategy for combining evidence from multiple ambiguous histories of BCI electroencephalogram measurements. |
| Tasks | Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1707/ |
| https://www.aclweb.org/anthology/W19-1707 | |
| PWC | https://paperswithcode.com/paper/noisy-neural-language-modeling-for-typing |
| Repo | |
| Framework | |
Investigating Political Herd Mentality: A Community Sentiment Based Approach
| Title | Investigating Political Herd Mentality: A Community Sentiment Based Approach |
| Authors | Anjali Bhavan, Rohan Mishra, Pradyumna Prakhar Sinha, Ramit Sawhney, Rajiv Ratn Shah |
| Abstract | Analyzing polarities and sentiments inherent in political speeches and debates poses an important problem today. This experiment aims to address this issue by analyzing publicly-available Hansard transcripts of the debates conducted in the UK Parliament. Our proposed approach, which uses community-based graph information to augment hand-crafted features based on topic modeling and emotion detection on debate transcripts, currently surpasses the benchmark results on the same dataset. Such sentiment classification systems could prove to be of great use in today{'}s politically turbulent times, for public knowledge of politicians{'} stands on various relevant issues proves vital for good governance and citizenship. The experiments also demonstrate that continuous feature representations learned from graphs can improve performance on sentiment classification tasks significantly. |
| Tasks | Sentiment Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2039/ |
| https://www.aclweb.org/anthology/P19-2039 | |
| PWC | https://paperswithcode.com/paper/investigating-political-herd-mentality-a |
| Repo | |
| Framework | |
A Study of Latent Structured Prediction Approaches to Passage Reranking
| Title | A Study of Latent Structured Prediction Approaches to Passage Reranking |
| Authors | Iryna Haponchyk, Aless Moschitti, ro |
| Abstract | The structured output framework provides a helpful tool for learning to rank problems. In this paper, we propose a structured output approach which regards rankings as latent variables. Our approach addresses the complex optimization of Mean Average Precision (MAP) ranking metric. We provide an inference procedure to find the max-violating ranking based on the decomposition of the corresponding loss. The results of our experiments on WikiQA and TREC13 datasets show that our reranking based on structured prediction is a promising research direction. |
| Tasks | Learning-To-Rank, Structured Prediction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1183/ |
| https://www.aclweb.org/anthology/N19-1183 | |
| PWC | https://paperswithcode.com/paper/a-study-of-latent-structured-prediction |
| Repo | |
| Framework | |
Sentence Boundary Detection in Legal Text
| Title | Sentence Boundary Detection in Legal Text |
| Authors | George Sanchez |
| Abstract | In this paper, we examined several algorithms to detect sentence boundaries in legal text. Legal text presents challenges for sentence tokenizers because of the variety of punctuations and syntax of legal text. Out-of-the-box algorithms perform poorly on legal text affecting further analysis of the text. A novel and domain-specific approach is needed to detect sentence boundaries to further analyze legal text. We present the results of our investigation in this paper. |
| Tasks | Boundary Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2204/ |
| https://www.aclweb.org/anthology/W19-2204 | |
| PWC | https://paperswithcode.com/paper/sentence-boundary-detection-in-legal-text |
| Repo | |
| Framework | |
Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes
| Title | Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes |
| Authors | Junzhe Zhang, Elias Bareinboim |
| Abstract | A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments and covariates’ history. These regimes are particularly effective for managing chronic disorders and is arguably one of the key aspects towards more personalized decision-making. In this paper, we investigate the online reinforcement learning (RL) problem for selecting optimal DTRs provided that observational data is available. We develop the first adaptive algorithm that achieves near-optimal regret in DTRs in online settings, without any access to historical data. We further derive informative bounds on the system dynamics of the underlying DTR from confounded, observational data. Finally, we combine these results and develop a novel RL algorithm that efficiently learns the optimal DTR while leveraging the abundant, yet imperfect confounded observations. |
| Tasks | Decision Making |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9496-near-optimal-reinforcement-learning-in-dynamic-treatment-regimes |
| http://papers.nips.cc/paper/9496-near-optimal-reinforcement-learning-in-dynamic-treatment-regimes.pdf | |
| PWC | https://paperswithcode.com/paper/near-optimal-reinforcement-learning-in-2 |
| Repo | |
| Framework | |
Evaluating Question Answering Evaluation
| Title | Evaluating Question Answering Evaluation |
| Authors | Anthony Chen, Gabriel Stanovsky, Sameer Singh, Matt Gardner |
| Abstract | As the complexity of question answering (QA) datasets evolve, moving away from restricted formats like span extraction and multiple-choice (MC) to free-form answer generation, it is imperative to understand how well current metrics perform in evaluating QA. This is especially important as existing metrics (BLEU, ROUGE, METEOR, and F1) are computed using n-gram similarity and have a number of well-known drawbacks. In this work, we study the suitability of existing metrics in QA. For generative QA, we show that while current metrics do well on existing datasets, converting multiple-choice datasets into free-response datasets is challenging for current metrics. We also look at span-based QA, where F1 is a reasonable metric. We show that F1 may not be suitable for all extractive QA tasks depending on the answer types. Our study suggests that while current metrics may be suitable for existing QA datasets, they limit the complexity of QA datasets that can be created. This is especially true in the context of free-form QA, where we would like our models to be able to generate more complex and abstractive answers, thus necessitating new metrics that go beyond n-gram based matching. As a step towards a better QA metric, we explore using BERTScore, a recently proposed metric for evaluating translation, for QA. We find that although it fails to provide stronger correlation with human judgements, future work focused on tailoring a BERT-based metric to QA evaluation may prove fruitful. |
| Tasks | Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5817/ |
| https://www.aclweb.org/anthology/D19-5817 | |
| PWC | https://paperswithcode.com/paper/evaluating-question-answering-evaluation |
| Repo | |
| Framework | |
Learning Mean-Field Games
| Title | Learning Mean-Field Games |
| Authors | Xin Guo, Anran Hu, Renyuan Xu, Junzi Zhang |
| Abstract | This paper presents a general mean-field game (GMFG) framework for simultaneous learning and decision-making in stochastic games with a large population. It first establishes the existence of a unique Nash Equilibrium to this GMFG, and explains that naively combining Q-learning with the fixed-point approach in classical MFGs yields unstable algorithms. It then proposes a Q-learning algorithm with Boltzmann policy (GMF-Q), with analysis of convergence property and computational complexity. The experiments on repeated Ad auction problems demonstrate that this GMF-Q algorithm is efficient and robust in terms of convergence and learning accuracy. Moreover, its performance is superior in convergence, stability, and learning ability, when compared with existing algorithms for multi-agent reinforcement learning. |
| Tasks | Decision Making, Multi-agent Reinforcement Learning, Q-Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8742-learning-mean-field-games |
| http://papers.nips.cc/paper/8742-learning-mean-field-games.pdf | |
| PWC | https://paperswithcode.com/paper/learning-mean-field-games |
| Repo | |
| Framework | |
TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting
| Title | TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting |
| Authors | Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu |
| Abstract | Most existing text spotting methods either focus on horizontal/oriented texts or perform arbitrary shaped text spotting with character-level annotations. In this paper, we propose a novel text spotting framework to detect and recognize text of arbitrary shapes in an end-to-end manner, using only word/line-level annotations for training. Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon. In TextDragon, a text detector is designed to describe the shape of text with a series of quadrangles, which can handle text of arbitrary shapes. To extract arbitrary text regions from feature maps, we propose a new differentiable operator named RoISlide, which is the key to connect arbitrary shaped text detection and recognition. Based on the extracted features through RoISlide, a CNN and CTC based text recognizer is introduced to make the framework free from labeling the location of characters. The proposed method achieves state-of-the-art performance on two curved text benchmarks CTW1500 and Total-Text, and competitive results on the ICDAR 2015 Dataset. |
| Tasks | Text Spotting |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Feng_TextDragon_An_End-to-End_Framework_for_Arbitrary_Shaped_Text_Spotting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Feng_TextDragon_An_End-to-End_Framework_for_Arbitrary_Shaped_Text_Spotting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/textdragon-an-end-to-end-framework-for |
| Repo | |
| Framework | |
Identification of Adjective-Noun Neologisms using Pretrained Language Models
| Title | Identification of Adjective-Noun Neologisms using Pretrained Language Models |
| Authors | John Philip McCrae |
| Abstract | Neologism detection is a key task in the constructing of lexical resources and has wider implications for NLP, however the identification of multiword neologisms has received little attention. In this paper, we show that we can effectively identify the distinction between compositional and non-compositional adjective-noun pairs by using pretrained language models and comparing this with individual word embeddings. Our results show that the use of these models significantly improves over baseline linguistic features, however the combination with linguistic features still further improves the results, suggesting the strength of a hybrid approach. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5116/ |
| https://www.aclweb.org/anthology/W19-5116 | |
| PWC | https://paperswithcode.com/paper/identification-of-adjective-noun-neologisms |
| Repo | |
| Framework | |
Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach
| Title | Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach |
| Authors | Shuyue Hu, Chin-Wing Leung, Ho-Fung Leung |
| Abstract | Modelling the dynamics of multi-agent learning has long been an important research topic, but all of the previous works focus on 2-agent settings and mostly use evolutionary game theoretic approaches. In this paper, we study an n-agent setting with n tends to infinity, such that agents learn their policies concurrently over repeated symmetric bimatrix games with some other agents. Using mean field theory, we approximate the effects of other agents on a single agent by an averaged effect. A Fokker-Planck equation that describes the evolution of the probability distribution of Q-values in the agent population is derived. To the best of our knowledge, this is the first time to show the Q-learning dynamics under an n-agent setting can be described by a system of only three equations. We validate our model through comparisons with agent-based simulations on typical symmetric bimatrix games and different initial settings of Q-values. |
| Tasks | Q-Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9380-modelling-the-dynamics-of-multiagent-q-learning-in-repeated-symmetric-games-a-mean-field-theoretic-approach |
| http://papers.nips.cc/paper/9380-modelling-the-dynamics-of-multiagent-q-learning-in-repeated-symmetric-games-a-mean-field-theoretic-approach.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-the-dynamics-of-multiagent-q |
| Repo | |
| Framework | |
Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title
| Title | Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title |
| Authors | Huimin Xu, Wenting Wang, Xin Mao, Xinyu Jiang, Man Lan |
| Abstract | Supplementing product information by extracting attribute values from title is a crucial task in e-Commerce domain. Previous studies treat each attribute only as an entity type and build one set of NER tags (e.g., BIO) for each of them, leading to a scalability issue which unfits to the large sized attribute system in real world e-Commerce. In this work, we propose a novel approach to support value extraction scaling up to thousands of attributes without losing performance: (1) We propose to regard attribute as a query and adopt only one global set of BIO tags for any attributes to reduce the burden of attribute tag or model explosion; (2) We explicitly model the semantic representations for attribute and title, and develop an attention mechanism to capture the interactive semantic relations in-between to enforce our framework to be attribute comprehensive. We conduct extensive experiments in real-life datasets. The results show that our model not only outperforms existing state-of-the-art NER tagging models, but also is robust and generates promising results for up to 8,906 attributes. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1514/ |
| https://www.aclweb.org/anthology/P19-1514 | |
| PWC | https://paperswithcode.com/paper/scaling-up-open-tagging-from-tens-to |
| Repo | |
| Framework | |
Without lexicons, multiword expression identification will never fly: A position statement
| Title | Without lexicons, multiword expression identification will never fly: A position statement |
| Authors | Agata Savary, Silvio Cordeiro, Carlos Ramisch |
| Abstract | Because most multiword expressions (MWEs), especially verbal ones, are semantically non-compositional, their automatic identification in running text is a prerequisite for semantically-oriented downstream applications. However, recent developments, driven notably by the PARSEME shared task on automatic identification of verbal MWEs, show that this task is harder than related tasks, despite recent contributions both in multilingual corpus annotation and in computational models. In this paper, we analyse possible reasons for this state of affairs. They lie in the nature of the MWE phenomenon, as well as in its distributional properties. We also offer a comparative analysis of the state-of-the-art systems, which exhibit particularly strong sensitivity to unseen data. On this basis, we claim that, in order to make strong headway in MWE identification, the community should bend its mind into coupling identification of MWEs with their discovery, via syntactic MWE lexicons. Such lexicons need not necessarily achieve a linguistically complete modelling of MWEs{'} behavior, but they should provide minimal morphosyntactic information to cover some potential uses, so as to complement existing MWE-annotated corpora. We define requirements for such minimal NLP-oriented lexicon, and we propose a roadmap for the MWE community driven by these requirements. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5110/ |
| https://www.aclweb.org/anthology/W19-5110 | |
| PWC | https://paperswithcode.com/paper/without-lexicons-multiword-expression |
| Repo | |
| Framework | |
Joint Type Inference on Entities and Relations via Graph Convolutional Networks
| Title | Joint Type Inference on Entities and Relations via Graph Convolutional Networks |
| Authors | Changzhi Sun, Yeyun Gong, Yuanbin Wu, Ming Gong, Daxin Jiang, Man Lan, Shiliang Sun, Nan Duan |
| Abstract | We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance. |
| Tasks | Relation Classification, Relation Extraction |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1131/ |
| https://www.aclweb.org/anthology/P19-1131 | |
| PWC | https://paperswithcode.com/paper/joint-type-inference-on-entities-and |
| Repo | |
| Framework | |
