Paper Group NANR 42
Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2). ConStance: Modeling Annotation Contexts to Improve Stance Classification. An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering. Quote Extraction and Attribution from Norwegian Newspapers. XJNLP at SemEval-2017 Task 12: Cl …
Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2)
| Title | Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7300/ |
| https://www.aclweb.org/anthology/W17-7300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-semantic |
| Repo | |
| Framework | |
ConStance: Modeling Annotation Contexts to Improve Stance Classification
| Title | ConStance: Modeling Annotation Contexts to Improve Stance Classification |
| Authors | Kenneth Joseph, Lisa Friedland, William Hobbs, David Lazer, Oren Tsur |
| Abstract | |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/D17-1116/d17-1116 |
| https://www.aclweb.org/anthology/D17-1116 | |
| PWC | https://paperswithcode.com/paper/constance-modeling-annotation-contexts-to |
| Repo | |
| Framework | |
An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering
| Title | An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering |
| Authors | Charles Chen, Razvan Bunescu |
| Abstract | The automation of tasks in community question answering (cQA) is dominated by machine learning approaches, whose performance is often limited by the number of training examples. Starting from a neural sequence learning approach with attention, we explore the impact of two data augmentation techniques on question ranking performance: a method that swaps reference questions with their paraphrases, and training on examples automatically selected from external datasets. Both methods are shown to lead to substantial gains in accuracy over a strong baseline. Further improvements are obtained by changing the model architecture to mirror the structure seen in the data. |
| Tasks | Community Question Answering, Data Augmentation, Question Answering, Question Similarity |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2075/ |
| https://www.aclweb.org/anthology/I17-2075 | |
| PWC | https://paperswithcode.com/paper/an-exploration-of-data-augmentation-and-rnn |
| Repo | |
| Framework | |
Quote Extraction and Attribution from Norwegian Newspapers
| Title | Quote Extraction and Attribution from Norwegian Newspapers |
| Authors | Andrew Salway, Paul Meurer, Knut Hofland, Ãystein Reigem |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-0241/w17-0241 |
| https://www.aclweb.org/anthology/W17-0241 | |
| PWC | https://paperswithcode.com/paper/quote-extraction-and-attribution-from |
| Repo | |
| Framework | |
XJNLP at SemEval-2017 Task 12: Clinical temporal information ex-traction with a Hybrid Model
| Title | XJNLP at SemEval-2017 Task 12: Clinical temporal information ex-traction with a Hybrid Model |
| Authors | Yu Long, Zhijing Li, Xuan Wang, Chen Li |
| Abstract | |
| Tasks | Domain Adaptation, Temporal Information Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/papers/S17-2178/s17-2178 |
| https://www.aclweb.org/anthology/S17-2178v2 | |
| PWC | https://paperswithcode.com/paper/xjnlp-at-semeval-2017-task-12-clinical |
| Repo | |
| Framework | |
A Systematic Study of Neural Discourse Models for Implicit Discourse Relation
| Title | A Systematic Study of Neural Discourse Models for Implicit Discourse Relation |
| Authors | Attapol Rutherford, Vera Demberg, Nianwen Xue |
| Abstract | Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Many neural network models have been proposed to tackle this problem. However, the comparison for this task is not unified, so we could hardly draw clear conclusions about the effectiveness of various architectures. Here, we propose neural network models that are based on feedforward and long-short term memory architecture and systematically study the effects of varying structures. To our surprise, the best-configured feedforward architecture outperforms LSTM-based model in most cases despite thorough tuning. Further, we compare our best feedforward system with competitive convolutional and recurrent networks and find that feedforward can actually be more effective. For the first time for this task, we compile and publish outputs from previous neural and non-neural systems to establish the standard for further comparison. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1027/ |
| https://www.aclweb.org/anthology/E17-1027 | |
| PWC | https://paperswithcode.com/paper/a-systematic-study-of-neural-discourse-models |
| Repo | |
| Framework | |
Automatic detection of stance towards vaccination in online discussion forums
| Title | Automatic detection of stance towards vaccination in online discussion forums |
| Authors | Maria Skeppstedt, Andreas Kerren, Manfred Stede |
| Abstract | A classifier for automatic detection of stance towards vaccination in online forums was trained and evaluated. Debate posts from six discussion threads on the British parental website Mumsnet were manually annotated for stance {}against{'} or {}for{'} vaccination, or as {}undecided{'}. A support vector machine, trained to detect the three classes, achieved a macro F-score of 0.44, while a macro F-score of 0.62 was obtained by the same type of classifier on the binary classification task of distinguishing stance {}against{'} vaccination from stance {`}for{'} vaccination. These results show that vaccine stance detection in online forums is a difficult task, at least for the type of model investigated and for the relatively small training corpus that was used. Future work will therefore include an expansion of the training data and an evaluation of other types of classifiers and features. | |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5801/ |
| https://www.aclweb.org/anthology/W17-5801 | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-stance-towards |
| Repo | |
| Framework | |
Annotation of negation in the IULA Spanish Clinical Record Corpus
| Title | Annotation of negation in the IULA Spanish Clinical Record Corpus |
| Authors | Montserrat Marimon, Jorge Vivaldi, N{'u}ria Bel |
| Abstract | This paper presents the IULA Spanish Clinical Record Corpus, a corpus of 3,194 sentences extracted from anonymized clinical records and manually annotated with negation markers and their scope. The corpus was conceived as a resource to support clinical text-mining systems, but it is also a useful resource for other Natural Language Processing systems handling clinical texts: automatic encoding of clinical records, diagnosis support, term extraction, among others, as well as for the study of clinical texts. The corpus is publicly available with a CC-BY-SA 3.0 license. |
| Tasks | Medical Diagnosis, Negation Detection |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1807/ |
| https://www.aclweb.org/anthology/W17-1807 | |
| PWC | https://paperswithcode.com/paper/annotation-of-negation-in-the-iula-spanish |
| Repo | |
| Framework | |
Translating Implicit Discourse Connectives Based on Cross-lingual Annotation and Alignment
| Title | Translating Implicit Discourse Connectives Based on Cross-lingual Annotation and Alignment |
| Authors | Hongzheng Li, Philippe Langlais, Yaohong Jin |
| Abstract | Implicit discourse connectives and relations are distributed more widely in Chinese texts, when translating into English, such connectives are usually translated explicitly. Towards Chinese-English MT, in this paper we describe cross-lingual annotation and alignment of dis-course connectives in a parallel corpus, describing related surveys and findings. We then conduct some evaluation experiments to testify the translation of implicit connectives and whether representing implicit connectives explicitly in source language can improve the final translation performance significantly. Preliminary results show it has little improvement by just inserting explicit connectives for implicit relations. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4812/ |
| https://www.aclweb.org/anthology/W17-4812 | |
| PWC | https://paperswithcode.com/paper/translating-implicit-discourse-connectives |
| Repo | |
| Framework | |
Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization
| Title | Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization |
| Authors | Tobias Falke, Christian M. Meyer, Iryna Gurevych |
| Abstract | Concept-map-based multi-document summarization is a variant of traditional summarization that produces structured summaries in the form of concept maps. In this work, we propose a new model for the task that addresses several issues in previous methods. It learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming. It is also computationally more efficient than previous methods, allowing us to summarize larger document sets. We evaluate the model on two datasets, finding that it outperforms several approaches from previous work. |
| Tasks | Coreference Resolution, Document Summarization, Multi-Document Summarization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1081/ |
| https://www.aclweb.org/anthology/I17-1081 | |
| PWC | https://paperswithcode.com/paper/concept-map-based-multi-document |
| Repo | |
| Framework | |
Modeling Answering Strategies for the Polar Questions across Languages
| Title | Modeling Answering Strategies for the Polar Questions across Languages |
| Authors | Jong-Bok Kim |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1001/ |
| https://www.aclweb.org/anthology/Y17-1001 | |
| PWC | https://paperswithcode.com/paper/modeling-answering-strategies-for-the-polar |
| Repo | |
| Framework | |
NRC Machine Translation System for WMT 2017
| Title | NRC Machine Translation System for WMT 2017 |
| Authors | Chi-kiu Lo, Boxing Chen, Colin Cherry, George Foster, Samuel Larkin, Darlene Stewart, Rol Kuhn, |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4732/ |
| https://www.aclweb.org/anthology/W17-4732 | |
| PWC | https://paperswithcode.com/paper/nrc-machine-translation-system-for-wmt-2017 |
| Repo | |
| Framework | |
A Local Detection Approach for Named Entity Recognition and Mention Detection
| Title | A Local Detection Approach for Named Entity Recognition and Mention Detection |
| Authors | Mingbin Xu, Hui Jiang, Sedtawut Watcharawittayakul |
| Abstract | In this paper, we study a novel approach for named entity recognition (NER) and mention detection (MD) in natural language processing. Instead of treating NER as a sequence labeling problem, we propose a new local detection approach, which relies on the recent fixed-size ordinally forgetting encoding (FOFE) method to fully encode each sentence fragment and its left/right contexts into a fixed-size representation. Subsequently, a simple feedforward neural network (FFNN) is learned to either reject or predict entity label for each individual text fragment. The proposed method has been evaluated in several popular NER and MD tasks, including CoNLL 2003 NER task and TAC-KBP2015 and TAC-KBP2016 Tri-lingual Entity Discovery and Linking (EDL) tasks. Our method has yielded pretty strong performance in all of these examined tasks. This local detection approach has shown many advantages over the traditional sequence labeling methods. |
| Tasks | Feature Engineering, Image Classification, Named Entity Recognition, Speech Recognition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1114/ |
| https://www.aclweb.org/anthology/P17-1114 | |
| PWC | https://paperswithcode.com/paper/a-local-detection-approach-for-named-entity |
| Repo | |
| Framework | |
Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework
| Title | Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework |
| Authors | Michal Busta, Lukas Neumann, Jiri Matas |
| Abstract | A method for scene text localization and recognition is proposed. The novelties include: training of both text detection and recognition in a single end-to-end pass, the structure of the recognition CNN and the geometry of its input layer that preserves the aspect of the text and adapts its resolution to the data. The proposed method achieves state-of-the-art accuracy in the end-to-end text recognition on two standard datasets - ICDAR 2013 and ICDAR 2015, whilst being an order of magnitude faster than competing methods - the whole pipeline runs at 10 frames per second on an NVidia K80 GPU. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Busta_Deep_TextSpotter_An_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Busta_Deep_TextSpotter_An_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-textspotter-an-end-to-end-trainable |
| Repo | |
| Framework | |
Grounding Language by Continuous Observation of Instruction Following
| Title | Grounding Language by Continuous Observation of Instruction Following |
| Authors | Ting Han, David Schlangen |
| Abstract | Grounded semantics is typically learnt from utterance-level meaning representations (e.g., successful database retrievals, denoted objects in images, moves in a game). We explore learning word and utterance meanings by continuous observation of the actions of an instruction follower (IF). While an instruction giver (IG) provided a verbal description of a configuration of objects, IF recreated it using a GUI. Aligning these GUI actions to sub-utterance chunks allows a simple maximum entropy model to associate them as chunk meaning better than just providing it with the utterance-final configuration. This shows that semantics useful for incremental (word-by-word) application, as required in natural dialogue, might also be better acquired from incremental settings. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2079/ |
| https://www.aclweb.org/anthology/E17-2079 | |
| PWC | https://paperswithcode.com/paper/grounding-language-by-continuous-observation |
| Repo | |
| Framework | |
