Paper Group NANR 22
Generation of Company descriptions using concept-to-text and text-to-text deep models: dataset collection and systems evaluation. Structured Variationally Auto-encoded Optimization. A Multilingual Approach to Question Classification. MRF Optimization with Separable Convex Prior on Partially Ordered Labels. An Integrated Formal Representation for Te …
Generation of Company descriptions using concept-to-text and text-to-text deep models: dataset collection and systems evaluation
| Title | Generation of Company descriptions using concept-to-text and text-to-text deep models: dataset collection and systems evaluation |
| Authors | Raheel Qader, Khoder Jneid, Fran{\c{c}}ois Portet, Cyril Labb{'e} |
| Abstract | In this paper we study the performance of several state-of-the-art sequence-to-sequence models applied to generation of short company descriptions. The models are evaluated on a newly created and publicly available company dataset that has been collected from Wikipedia. The dataset consists of around 51K company descriptions that can be used for both concept-to-text and text-to-text generation tasks. Automatic metrics and human evaluation scores computed on the generated company descriptions show promising results despite the difficulty of the task as the dataset (like most available datasets) has not been originally designed for machine learning. In addition, we perform correlation analysis between automatic metrics and human evaluations and show that certain automatic metrics are more correlated to human judgments. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6532/ |
| https://www.aclweb.org/anthology/W18-6532 | |
| PWC | https://paperswithcode.com/paper/generation-of-company-descriptions-using |
| Repo | |
| Framework | |
Structured Variationally Auto-encoded Optimization
| Title | Structured Variationally Auto-encoded Optimization |
| Authors | Xiaoyu Lu, Javier Gonzalez, Zhenwen Dai, Neil Lawrence |
| Abstract | We tackle the problem of optimizing a black-box objective function defined over a highly-structured input space. This problem is ubiquitous in science and engineering. In machine learning, inferring the structure of a neural network or the Automatic Statistician (AS), where the optimal kernel combination for a Gaussian process is selected, are two important examples. We use the \as as a case study to describe our approach, that can be easily generalized to other domains. We propose an Structure Generating Variational Auto-encoder (SG-VAE) to embed the original space of kernel combinations into some low-dimensional continuous manifold where Bayesian optimization (BO) ideas are used. This is possible when structural knowledge of the problem is available, which can be given via a simulator or any other form of generating potentially good solutions. The right exploration-exploitation balance is imposed by propagating into the search the uncertainty of the latent space of the SG-VAE, that is computed using variational inference. The key aspect of our approach is that the SG-VAE can be used to bias the search towards relevant regions, making it suitable for transfer learning tasks. Several experiments in various application domains are used to illustrate the utility and generality of the approach described in this work. |
| Tasks | Transfer Learning |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2328 |
| http://proceedings.mlr.press/v80/lu18c/lu18c.pdf | |
| PWC | https://paperswithcode.com/paper/structured-variationally-auto-encoded |
| Repo | |
| Framework | |
A Multilingual Approach to Question Classification
| Title | A Multilingual Approach to Question Classification |
| Authors | Aikaterini-Lida Kalouli, Katharina Kaiser, Annette Hautli-Janisz, Georg A. Kaiser, Miriam Butt |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1430/ |
| https://www.aclweb.org/anthology/L18-1430 | |
| PWC | https://paperswithcode.com/paper/a-multilingual-approach-to-question |
| Repo | |
| Framework | |
MRF Optimization with Separable Convex Prior on Partially Ordered Labels
| Title | MRF Optimization with Separable Convex Prior on Partially Ordered Labels |
| Authors | Csaba Domokos, Frank R. Schmidt, Daniel Cremers |
| Abstract | Solving a multi-labeling problem with a convex penalty can be achieved in polynomial time if the label set is totally ordered. In this paper we propose a generalization to partially ordered sets. To this end, we assume that the label set is the Cartesian product of totally ordered sets and the convex prior is separable. For this setting we introduce a general combinatorial optimization framework that provides an approximate solution. More specifically, we first construct a graph whose minimal cut provides a lower bound to our energy. The result of this relaxation is then used to get a feasible solution via classical move-making cuts. To speed up the optimization, we propose an efficient coarse-to-fine approach over the label space. We demonstrate the proposed framework through extensive experiments for optical flow estimation. |
| Tasks | Combinatorial Optimization, Optical Flow Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Csaba_Domokos_MRF_Optimization_with_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Csaba_Domokos_MRF_Optimization_with_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mrf-optimization-with-separable-convex-prior |
| Repo | |
| Framework | |
An Integrated Formal Representation for Terminological and Lexical Data included in Classification Schemes
| Title | An Integrated Formal Representation for Terminological and Lexical Data included in Classification Schemes |
| Authors | Thierry Declerck, Kseniya Egorova, Eileen Schnur |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1094/ |
| https://www.aclweb.org/anthology/L18-1094 | |
| PWC | https://paperswithcode.com/paper/an-integrated-formal-representation-for |
| Repo | |
| Framework | |
Comprehension Driven Document Planning in Natural Language Generation Systems
| Title | Comprehension Driven Document Planning in Natural Language Generation Systems |
| Authors | Craig Thomson, Ehud Reiter, Somayajulu Sripada |
| Abstract | This paper proposes an approach to NLG system design which focuses on generating output text which can be more easily processed by the reader. Ways in which cognitive theory might be combined with existing NLG techniques are discussed and two simple experiments in content ordering are presented. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6544/ |
| https://www.aclweb.org/anthology/W18-6544 | |
| PWC | https://paperswithcode.com/paper/comprehension-driven-document-planning-in |
| Repo | |
| Framework | |
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
| Title | Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling |
| Authors | Kyowoon Lee, Sol-A Kim, Jaesik Choi, Seong-Whan Lee |
| Abstract | Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces. Recently, deep neural networks have successfully been applied to games with discrete actions spaces. However, deep neural networks for discrete actions are not suitable for devising strategies for games where a very small change in an action can dramatically affect the outcome. In this paper, we present a new self-play reinforcement learning framework which equips a continuous search algorithm which enables to search in continuous action spaces with a kernel regression method. Without any hand-crafted features, our network is trained by supervised learning followed by self-play reinforcement learning with a high-fidelity simulator for the Olympic sport of curling. The program trained under our framework outperforms existing programs equipped with several hand-crafted features and won an international digital curling competition. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2461 |
| http://proceedings.mlr.press/v80/lee18b/lee18b.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-in-continuous |
| Repo | |
| Framework | |
Analyzing Citation-Distance Networks for Evaluating Publication Impact
| Title | Analyzing Citation-Distance Networks for Evaluating Publication Impact |
| Authors | Drahomira Herrmannova, Petr Knoth, Robert Patton |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1561/ |
| https://www.aclweb.org/anthology/L18-1561 | |
| PWC | https://paperswithcode.com/paper/analyzing-citation-distance-networks-for |
| Repo | |
| Framework | |
Investigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts
| Title | Investigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts |
| Authors | Hai-Long Trieu, Nhung T. H. Nguyen, Makoto Miwa, Sophia Ananiadou |
| Abstract | Existing biomedical coreference resolution systems depend on features and/or rules based on syntactic parsers. In this paper, we investigate the utility of the state-of-the-art general domain neural coreference resolution system on biomedical texts. The system is an end-to-end system without depending on any syntactic parsers. We also investigate the domain specific features to enhance the system for biomedical texts. Experimental results on the BioNLP Protein Coreference dataset and the CRAFT corpus show that, with no parser information, the adapted system compared favorably with the systems that depend on parser information on these datasets, achieving 51.23{%} on the BioNLP dataset and 36.33{%} on the CRAFT corpus in F1 score. In-domain embeddings and domain-specific features helped improve the performance on the BioNLP dataset, but they did not on the CRAFT corpus. |
| Tasks | Coreference Resolution, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2324/ |
| https://www.aclweb.org/anthology/W18-2324 | |
| PWC | https://paperswithcode.com/paper/investigating-domain-specific-information-for |
| Repo | |
| Framework | |
Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena
| Title | Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena |
| Authors | Ina Roesiger, Sarah Schulz, Nils Reiter |
| Abstract | Coreference resolution is the task of grouping together references to the same discourse entity. Resolving coreference in literary texts could benefit a number of Digital Humanities (DH) tasks, such as analyzing the depiction of characters and/or their relations. Domain-dependent training data has shown to improve coreference resolution for many domains, e.g. the biomedical domain, as its properties differ significantly from news text or dialogue, on which automatic systems are typically trained. Literary texts could also benefit from corpora annotated with coreference. We therefore analyze the specific properties of coreference-related phenomena on a number of texts and give directions for the adaptation of annotation guidelines. As some of the adaptations have profound impact, we also present a new annotation tool for coreference, with a focus on enabling annotation of long texts with many discourse entities. |
| Tasks | Coreference Resolution, Natural Language Inference, Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4515/ |
| https://www.aclweb.org/anthology/W18-4515 | |
| PWC | https://paperswithcode.com/paper/towards-coreference-for-literary-text |
| Repo | |
| Framework | |
Graph Based Decoding for Event Sequencing and Coreference Resolution
| Title | Graph Based Decoding for Event Sequencing and Coreference Resolution |
| Authors | Zhengzhong Liu, Teruko Mitamura, Eduard Hovy |
| Abstract | Events in text documents are interrelated in complex ways. In this paper, we study two types of relation: Event Coreference and Event Sequencing. We show that the popular tree-like decoding structure for automated Event Coreference is not suitable for Event Sequencing. To this end, we propose a graph-based decoding algorithm that is applicable to both tasks. The new decoding algorithm supports flexible feature sets for both tasks. Empirically, our event coreference system has achieved state-of-the-art performance on the TAC-KBP 2015 event coreference task and our event sequencing system beats a strong temporal-based, oracle-informed baseline. We discuss the challenges of studying these event relations. |
| Tasks | Coreference Resolution |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1309/ |
| https://www.aclweb.org/anthology/C18-1309 | |
| PWC | https://paperswithcode.com/paper/graph-based-decoding-for-event-sequencing-and |
| Repo | |
| Framework | |
Augmenting Image Question Answering Dataset by Exploiting Image Captions
| Title | Augmenting Image Question Answering Dataset by Exploiting Image Captions |
| Authors | Masashi Yokota, Hideki Nakayama |
| Abstract | |
| Tasks | Data Augmentation, Image Captioning, Image Classification, Machine Translation, Question Answering, Reading Comprehension, Visual Question Answering |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1436/ |
| https://www.aclweb.org/anthology/L18-1436 | |
| PWC | https://paperswithcode.com/paper/augmenting-image-question-answering-dataset |
| Repo | |
| Framework | |
Semi-supervised Training Data Generation for Multilingual Question Answering
| Title | Semi-supervised Training Data Generation for Multilingual Question Answering |
| Authors | Kyungjae Lee, Kyoungho Yoon, Sunghyun Park, Seung-won Hwang |
| Abstract | |
| Tasks | Machine Translation, Named Entity Recognition, Object Recognition, Question Answering, Reading Comprehension, Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1437/ |
| https://www.aclweb.org/anthology/L18-1437 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-training-data-generation-for |
| Repo | |
| Framework | |
Reinforcement Cutting-Agent Learning for Video Object Segmentation
| Title | Reinforcement Cutting-Agent Learning for Video Object Segmentation |
| Authors | Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, Xiaodan Liang |
| Abstract | Video object segmentation is a fundamental yet challenging task in computer vision community. In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework. Essentially, learning agents for segmentation is nontrivial as segmentation is a nearly continuous decision-making process, where the number of the involved agents (pixels or superpixels) and action steps from the seed (super)pixels to the whole object mask might be incredibly huge. To overcome this difficulty, this paper simplifies the learning of segmentation agents to the learning of a cutting-agent, which only has a limited number of action units and can converge in just a few action steps. The basic assumption is that object segmentation mainly relies on the interaction between object regions and their context. Thus, with an optimal object (box) region and context (box) region, we can obtain the desirable segmentation mask through further inference. Based on this assumption, we establish a novel reinforcement cutting-agent learning framework, where the cutting-agent consists of a cutting-policy network and a cutting-execution network. The former learns policies for deciding optimal object-context box pair, while the latter executing the cutting function based on the inferred object-context box pair. With the collaborative interaction between the two networks, our method can achieve the outperforming VOS performance on two public benchmarks, which demonstrates the rationality of our assumption as well as the effectiveness of the proposed learning framework. |
| Tasks | Decision Making, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Han_Reinforcement_Cutting-Agent_Learning_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Han_Reinforcement_Cutting-Agent_Learning_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-cutting-agent-learning-for |
| Repo | |
| Framework | |
Creating a Verb Synonym Lexicon Based on a Parallel Corpus
| Title | Creating a Verb Synonym Lexicon Based on a Parallel Corpus |
| Authors | Zde{\v{n}}ka Ure{\v{s}}ov{'a}, Eva Fu{\v{c}}{'\i}kov{'a}, Eva Haji{\v{c}}ov{'a}, Jan Haji{\v{c}} |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1227/ |
| https://www.aclweb.org/anthology/L18-1227 | |
| PWC | https://paperswithcode.com/paper/creating-a-verb-synonym-lexicon-based-on-a |
| Repo | |
| Framework | |
