Paper Group NANR 108
Feature Exploration for Cross-Lingual Pronoun Prediction. Jointly Learning Grounded Task Structures from Language Instruction and Visual Demonstration. A Sentence Interaction Network for Modeling Dependence between Sentences. Modeling Diachronic Change in Scientific Writing with Information Density. Combining Lexical and Semantic-based Features for …
Feature Exploration for Cross-Lingual Pronoun Prediction
| Title | Feature Exploration for Cross-Lingual Pronoun Prediction |
| Authors | Sara Stymne |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2355/ |
| https://www.aclweb.org/anthology/W16-2355 | |
| PWC | https://paperswithcode.com/paper/feature-exploration-for-cross-lingual-pronoun |
| Repo | |
| Framework | |
Jointly Learning Grounded Task Structures from Language Instruction and Visual Demonstration
| Title | Jointly Learning Grounded Task Structures from Language Instruction and Visual Demonstration |
| Authors | Changsong Liu, Shaohua Yang, Sari Saba-Sadiya, Nishant Shukla, Yunzhong He, Song-Chun Zhu, Joyce Chai |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1155/ |
| https://www.aclweb.org/anthology/D16-1155 | |
| PWC | https://paperswithcode.com/paper/jointly-learning-grounded-task-structures |
| Repo | |
| Framework | |
A Sentence Interaction Network for Modeling Dependence between Sentences
| Title | A Sentence Interaction Network for Modeling Dependence between Sentences |
| Authors | Biao Liu, Minlie Huang |
| Abstract | |
| Tasks | Answer Selection, Feature Engineering, Sentence Embedding, Sentence Pair Modeling |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1053/ |
| https://www.aclweb.org/anthology/P16-1053 | |
| PWC | https://paperswithcode.com/paper/a-sentence-interaction-network-for-modeling |
| Repo | |
| Framework | |
Modeling Diachronic Change in Scientific Writing with Information Density
| Title | Modeling Diachronic Change in Scientific Writing with Information Density |
| Authors | Raphael Rubino, Stefania Degaetano-Ortlieb, Elke Teich, Josef van Genabith |
| Abstract | Previous linguistic research on scientific writing has shown that language use in the scientific domain varies considerably in register and style over time. In this paper we investigate the introduction of information theory inspired features to study long term diachronic change on three levels: lexis, part-of-speech and syntax. Our approach is based on distinguishing between sentences from 19th and 20th century scientific abstracts using supervised classification models. To the best of our knowledge, the introduction of information theoretic features to this task is novel. We show that these features outperform more traditional features, such as token or character n-grams, while leading to more compact models. We present a detailed analysis of feature informativeness in order to gain a better understanding of diachronic change on different linguistic levels. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1072/ |
| https://www.aclweb.org/anthology/C16-1072 | |
| PWC | https://paperswithcode.com/paper/modeling-diachronic-change-in-scientific |
| Repo | |
| Framework | |
Combining Lexical and Semantic-based Features for Answer Sentence Selection
| Title | Combining Lexical and Semantic-based Features for Answer Sentence Selection |
| Authors | Jing Shi, Jiaming Xu, Yiqun Yao, Suncong Zheng, Bo Xu |
| Abstract | Question answering is always an attractive and challenging task in natural language processing area. There are some open domain question answering systems, such as IBM Waston, which take the unstructured text data as input, in some ways of humanlike thinking process and a mode of artificial intelligence. At the conference on Natural Language Processing and Chinese Computing (NLPCC) 2016, China Computer Federation hosted a shared task evaluation about Open Domain Question Answering. We achieve the 2nd place at the document-based subtask. In this paper, we present our solution, which consists of feature engineering in lexical and semantic aspects and model training methods. As the result of the evaluation shows, our solution provides a valuable and brief model which could be used in modelling question answering or sentence semantic relevance. We hope our solution would contribute to this vast and significant task with some heuristic thinking. |
| Tasks | Feature Engineering, Open-Domain Question Answering, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4404/ |
| https://www.aclweb.org/anthology/W16-4404 | |
| PWC | https://paperswithcode.com/paper/combining-lexical-and-semantic-based-features |
| Repo | |
| Framework | |
UniMelb at SemEval-2016 Task 3: Identifying Similar Questions by combining a CNN with String Similarity Measures
| Title | UniMelb at SemEval-2016 Task 3: Identifying Similar Questions by combining a CNN with String Similarity Measures |
| Authors | Timothy Baldwin, Huizhi Liang, Bahar Salehi, Doris Hoogeveen, Yitong Li, Long Duong |
| Abstract | |
| Tasks | Community Question Answering, Machine Translation, Natural Language Inference, Question Answering, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1131/ |
| https://www.aclweb.org/anthology/S16-1131 | |
| PWC | https://paperswithcode.com/paper/unimelb-at-semeval-2016-task-3-identifying |
| Repo | |
| Framework | |
UFRGS&LIF at SemEval-2016 Task 10: Rule-Based MWE Identification and Predominant-Supersense Tagging
| Title | UFRGS&LIF at SemEval-2016 Task 10: Rule-Based MWE Identification and Predominant-Supersense Tagging |
| Authors | Silvio Cordeiro, Carlos Ramisch, Aline Villavicencio |
| Abstract | |
| Tasks | Machine Translation, Tokenization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1140/ |
| https://www.aclweb.org/anthology/S16-1140 | |
| PWC | https://paperswithcode.com/paper/ufrgslif-at-semeval-2016-task-10-rule-based |
| Repo | |
| Framework | |
Negation and Modality in Machine Translation
| Title | Negation and Modality in Machine Translation |
| Authors | Preslav Nakov |
| Abstract | Negation and modality are two important grammatical phenomena that have attracted recent research attention as they can contribute to extra-propositional meaning aspects, among with factuality, attribution, irony and sarcasm. These aspects go beyond analysis such as semantic role labeling, and modeling them is important as a step towards a higher level of language understanding, which is needed for practical applications such as sentiment analysis. In this talk, I will go beyond English, and I will discuss how negation and modality are expressed in other languages. I will also go beyond sentiment analysis and I will present some challenges that the two phenomena pose for machine translation (MT). In particular, I will demonstrate how contemporary MT systems fail on them, and I will discuss some possible solutions. |
| Tasks | Machine Translation, Semantic Role Labeling, Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5005/ |
| https://www.aclweb.org/anthology/W16-5005 | |
| PWC | https://paperswithcode.com/paper/negation-and-modality-in-machine-translation |
| Repo | |
| Framework | |
Studying the Temporal Dynamics of Word Co-occurrences: An Application to Event Detection
| Title | Studying the Temporal Dynamics of Word Co-occurrences: An Application to Event Detection |
| Authors | Daniel Preo{\c{t}}iuc-Pietro, P. K. Srijith, Mark Hepple, Trevor Cohn |
| Abstract | Streaming media provides a number of unique challenges for computational linguistics. This paper studies the temporal variation in word co-occurrence statistics, with application to event detection. We develop a spectral clustering approach to find groups of mutually informative terms occurring in discrete time frames. Experiments on large datasets of tweets show that these groups identify key real world events as they occur in time, despite no explicit supervision. The performance of our method rivals state-of-the-art methods for event detection on F-score, obtaining higher recall at the expense of precision. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1694/ |
| https://www.aclweb.org/anthology/L16-1694 | |
| PWC | https://paperswithcode.com/paper/studying-the-temporal-dynamics-of-word-co |
| Repo | |
| Framework | |
Argument Identification in Chinese Editorials
| Title | Argument Identification in Chinese Editorials |
| Authors | Marisa Chow |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-2003/ |
| https://www.aclweb.org/anthology/N16-2003 | |
| PWC | https://paperswithcode.com/paper/argument-identification-in-chinese-editorials |
| Repo | |
| Framework | |
English-French Document Alignment Based on Keywords and Statistical Translation
| Title | English-French Document Alignment Based on Keywords and Statistical Translation |
| Authors | Marek Medve{\v{d}}, Milo{\v{s}} Jakub{'\i}{\v{c}}ek, Vojtech Kov{'a}{\v{r}} |
| Abstract | |
| Tasks | Boundary Detection, Keyword Extraction, Lemmatization, Machine Translation, Morphological Analysis, Tokenization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2374/ |
| https://www.aclweb.org/anthology/W16-2374 | |
| PWC | https://paperswithcode.com/paper/english-french-document-alignment-based-on |
| Repo | |
| Framework | |
Detecting Annotation Scheme Variation in Out-of-Domain Treebanks
| Title | Detecting Annotation Scheme Variation in Out-of-Domain Treebanks |
| Authors | Yannick Versley, Julius Steen |
| Abstract | To ensure portability of NLP systems across multiple domains, existing treebanks are often extended by adding trees from interesting domains that were not part of the initial annotation effort. In this paper, we will argue that it is both useful from an application viewpoint and enlightening from a linguistic viewpoint to detect and reduce divergence in annotation schemes between extant and new parts in a set of treebanks that is to be used in evaluation experiments. The results of our correction and harmonization efforts will be made available to the public as a test suite for the evaluation of constituent parsing. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1373/ |
| https://www.aclweb.org/anthology/L16-1373 | |
| PWC | https://paperswithcode.com/paper/detecting-annotation-scheme-variation-in-out |
| Repo | |
| Framework | |
Star-net: A spatial attention residue network for scene text recognition.
| Title | Star-net: A spatial attention residue network for scene text recognition. |
| Authors | W. Liu, C. Chen, K.-Y. K. Wong, Z. Su, and J. Han. |
| Abstract | In this paper, we present a novel SpaTial Attention Residue Network (STAR-Net) for recognising scene texts. Our STAR-Net is equipped with a spatial attention mechanism which employs a spatial transformer to remove the distortions of texts in natural images. This allows the subsequent feature extractor to focus on the rectified text region without being sidetracked by the distortions. Our STAR-Net also exploits residue convolutional blocks to build a very deep feature extractor, which is essential to the successful extraction of discriminative text features for this fine grained recognition task. Combining the spatial attention mechanism with the residue convolutional blocks, our STAR-Net is the deepest end-to-end trainable neural network for scene text recognition. Experiments have been conducted on five public benchmark datasets. Experimental results show that our STAR-Net can achieve a performance comparable to state-of-the-art methods for scene texts with little distortions, and outperform these methods for scene texts with considerable distortions. |
| Tasks | Scene Text Recognition |
| Published | 2016-09-20 |
| URL | http://www.bmva.org/bmvc/2016/papers/paper043/paper043.pdf |
| http://www.bmva.org/bmvc/2016/papers/paper043/paper043.pdf | |
| PWC | https://paperswithcode.com/paper/star-net-a-spatial-attention-residue-network |
| Repo | |
| Framework | |
Regularized Nonlinear Acceleration
| Title | Regularized Nonlinear Acceleration |
| Authors | Damien Scieur, Alexandre D’Aspremont, Francis Bach |
| Abstract | We describe a convergence acceleration technique for generic optimization problems. Our scheme computes estimates of the optimum from a nonlinear average of the iterates produced by any optimization method. The weights in this average are computed via a simple and small linear system, whose solution can be updated online. This acceleration scheme runs in parallel to the base algorithm, providing improved estimates of the solution on the fly, while the original optimization method is running. Numerical experiments are detailed on classical classification problems. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6267-regularized-nonlinear-acceleration |
| http://papers.nips.cc/paper/6267-regularized-nonlinear-acceleration.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-nonlinear-acceleration |
| Repo | |
| Framework | |
A non-expert Kaldi recipe for Vietnamese Speech Recognition System
| Title | A non-expert Kaldi recipe for Vietnamese Speech Recognition System |
| Authors | Hieu-Thi Luong, Hai-Quan Vu |
| Abstract | In this paper we describe a non-expert setup for Vietnamese speech recognition system using Kaldi toolkit. We collected a speech corpus over fifteen hours from about fifty Vietnamese native speakers and using it to test the feasibility of our setup. The essential linguistic components for the Automatic Speech Recognition (ASR) system was prepared basing on the written form of the language instead of expertise knowledge on linguistic and phonology as commonly seen in rich resource languages like English. The modeling of tones by integrating them into the phoneme and using the phonetic decision tree is also discussed. Experimental results showed this setup for ASR systems does yield competitive results while still have potentials for further improvements. |
| Tasks | Speech Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5207/ |
| https://www.aclweb.org/anthology/W16-5207 | |
| PWC | https://paperswithcode.com/paper/a-non-expert-kaldi-recipe-for-vietnamese |
| Repo | |
| Framework | |
