Paper Group NANR 121
Whitepaper of NEWS 2016 Shared Task on Machine Transliteration. A comparison of Named-Entity Disambiguation and Word Sense Disambiguation. Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection. Incremental Prediction of Sentence-final Verbs: Humans versus Machines. Semantic Annotation of the ACL …
Whitepaper of NEWS 2016 Shared Task on Machine Transliteration
| Title | Whitepaper of NEWS 2016 Shared Task on Machine Transliteration |
| Authors | Xiangyu Duan, Min Zhang, Haizhou Li, Rafael Banchs, A Kumaran |
| Abstract | |
| Tasks | Machine Translation, Transliteration |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2708/ |
| https://www.aclweb.org/anthology/W16-2708 | |
| PWC | https://paperswithcode.com/paper/whitepaper-of-news-2016-shared-task-on |
| Repo | |
| Framework | |
A comparison of Named-Entity Disambiguation and Word Sense Disambiguation
| Title | A comparison of Named-Entity Disambiguation and Word Sense Disambiguation |
| Authors | Angel Chang, Valentin I. Spitkovsky, Christopher D. Manning, Eneko Agirre |
| Abstract | Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia-derived resources like DBpedia. This task is closely related to word-sense disambiguation (WSD), where the mention of an open-class word is linked to a concept in a knowledge-base, typically WordNet. This paper analyzes the relation between two annotated datasets on NED and WSD, highlighting the commonalities and differences. We detail the methods to construct a NED system following the WSD word-expert approach, where we need a dictionary and one classifier is built for each target entity mention string. Constructing a dictionary for NED proved challenging, and although similarity and ambiguity are higher for NED, the results are also higher due to the larger number of training data, and the more crisp and skewed meaning differences. |
| Tasks | Entity Disambiguation, Word Sense Disambiguation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1139/ |
| https://www.aclweb.org/anthology/L16-1139 | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-named-entity-disambiguation |
| Repo | |
| Framework | |
Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection
| Title | Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection |
| Authors | Yuki Igarashi, Hiroya Komatsu, Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui |
| Abstract | |
| Tasks | Stance Detection, Text Classification, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1065/ |
| https://www.aclweb.org/anthology/S16-1065 | |
| PWC | https://paperswithcode.com/paper/tohoku-at-semeval-2016-task-6-feature-based |
| Repo | |
| Framework | |
Incremental Prediction of Sentence-final Verbs: Humans versus Machines
| Title | Incremental Prediction of Sentence-final Verbs: Humans versus Machines |
| Authors | Alvin Grissom II, Naho Orita, Jordan Boyd-Graber |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-1010/ |
| https://www.aclweb.org/anthology/K16-1010 | |
| PWC | https://paperswithcode.com/paper/incremental-prediction-of-sentence-final |
| Repo | |
| Framework | |
Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature
| Title | Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature |
| Authors | Kata G{'a}bor, Ha{"\i}fa Zargayouna, Davide Buscaldi, Isabelle Tellier, Thierry Charnois |
| Abstract | This paper describes the process of creating a corpus annotated for concepts and semantic relations in the scientific domain. A part of the ACL Anthology Corpus was selected for annotation, but the annotation process itself is not specific to the computational linguistics domain and could be applied to any scientific corpora. Concepts were identified and annotated fully automatically, based on a combination of terminology extraction and available ontological resources. A typology of semantic relations between concepts is also proposed. This typology, consisting of 18 domain-specific and 3 generic relations, is the result of a corpus-based investigation of the text sequences occurring between concepts in sentences. A sample of 500 abstracts from the corpus is currently being manually annotated with these semantic relations. Only explicit relations are taken into account, so that the data could serve to train or evaluate pattern-based semantic relation classification systems. |
| Tasks | Relation Classification |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1586/ |
| https://www.aclweb.org/anthology/L16-1586 | |
| PWC | https://paperswithcode.com/paper/semantic-annotation-of-the-acl-anthology |
| Repo | |
| Framework | |
Inference by Reparameterization in Neural Population Codes
| Title | Inference by Reparameterization in Neural Population Codes |
| Authors | Rajkumar Vasudeva Raju, Zachary Pitkow |
| Abstract | Behavioral experiments on humans and animals suggest that the brain performs probabilistic inference to interpret its environment. Here we present a new general-purpose, biologically-plausible neural implementation of approximate inference. The neural network represents uncertainty using Probabilistic Population Codes (PPCs), which are distributed neural representations that naturally encode probability distributions, and support marginalization and evidence integration in a biologically-plausible manner. By connecting multiple PPCs together as a probabilistic graphical model, we represent multivariate probability distributions. Approximate inference in graphical models can be accomplished by message-passing algorithms that disseminate local information throughout the graph. An attractive and often accurate example of such an algorithm is Loopy Belief Propagation (LBP), which uses local marginalization and evidence integration operations to perform approximate inference efficiently even for complex models. Unfortunately, a subtle feature of LBP renders it neurally implausible. However, LBP can be elegantly reformulated as a sequence of Tree-based Reparameterizations (TRP) of the graphical model. We re-express the TRP updates as a nonlinear dynamical system with both fast and slow timescales, and show that this produces a neurally plausible solution. By combining all of these ideas, we show that a network of PPCs can represent multivariate probability distributions and implement the TRP updates to perform probabilistic inference. Simulations with Gaussian graphical models demonstrate that the neural network inference quality is comparable to the direct evaluation of LBP and robust to noise, and thus provides a promising mechanism for general probabilistic inference in the population codes of the brain. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6476-inference-by-reparameterization-in-neural-population-codes |
| http://papers.nips.cc/paper/6476-inference-by-reparameterization-in-neural-population-codes.pdf | |
| PWC | https://paperswithcode.com/paper/inference-by-reparameterization-in-neural |
| Repo | |
| Framework | |
Cost-Effectiveness in Building a Low-Resource Morphological Analyzer for Learner Language
| Title | Cost-Effectiveness in Building a Low-Resource Morphological Analyzer for Learner Language |
| Authors | Scott Ledbetter, Markus Dickinson |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0523/ |
| https://www.aclweb.org/anthology/W16-0523 | |
| PWC | https://paperswithcode.com/paper/cost-effectiveness-in-building-a-low-resource |
| Repo | |
| Framework | |
Event-Driven Emotion Cause Extraction with Corpus Construction
| Title | Event-Driven Emotion Cause Extraction with Corpus Construction |
| Authors | Lin Gui, Dongyin Wu, Ruifeng Xu, Qin Lu, Yu Zhou |
| Abstract | |
| Tasks | Emotion Classification, Emotion Recognition |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1170/ |
| https://www.aclweb.org/anthology/D16-1170 | |
| PWC | https://paperswithcode.com/paper/event-driven-emotion-cause-extraction-with |
| Repo | |
| Framework | |
First Steps Towards Coverage-Based Sentence Alignment
| Title | First Steps Towards Coverage-Based Sentence Alignment |
| Authors | Lu{'\i}s Gomes, Gabriel Pereira Lopes |
| Abstract | In this paper, we introduce a coverage-based scoring function that discriminates between parallel and non-parallel sentences. When plugged into Bleualign, a state-of-the-art sentence aligner, our function improves both precision and recall of alignments over the originally proposed BLEU score. Furthermore, since our scoring function uses Moses phrase tables directly we avoid the need to translate the texts to be aligned, which is time-consuming and a potential source of alignment errors. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1354/ |
| https://www.aclweb.org/anthology/L16-1354 | |
| PWC | https://paperswithcode.com/paper/first-steps-towards-coverage-based-sentence |
| Repo | |
| Framework | |
Clustering for Simultaneous Extraction of Aspects and Features from Reviews
| Title | Clustering for Simultaneous Extraction of Aspects and Features from Reviews |
| Authors | Lu Chen, Justin Martineau, Doreen Cheng, Amit Sheth |
| Abstract | |
| Tasks | Topic Models |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1093/ |
| https://www.aclweb.org/anthology/N16-1093 | |
| PWC | https://paperswithcode.com/paper/clustering-for-simultaneous-extraction-of |
| Repo | |
| Framework | |
Illinois Math Solver: Math Reasoning on the Web
| Title | Illinois Math Solver: Math Reasoning on the Web |
| Authors | Subhro Roy, Dan Roth |
| Abstract | |
| Tasks | Math Word Problem Solving |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-3011/ |
| https://www.aclweb.org/anthology/N16-3011 | |
| PWC | https://paperswithcode.com/paper/illinois-math-solver-math-reasoning-on-the |
| Repo | |
| Framework | |
Coordination in Minimalist Grammars: Excorporation and Across the Board (Head) Movement
| Title | Coordination in Minimalist Grammars: Excorporation and Across the Board (Head) Movement |
| Authors | John Torr, Edward P. Stabler |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-3301/ |
| https://www.aclweb.org/anthology/W16-3301 | |
| PWC | https://paperswithcode.com/paper/coordination-in-minimalist-grammars |
| Repo | |
| Framework | |
構建一個中文國小數學文字問題語料庫(Building a Corpus for Developing the Chinese Elementary School Math Word Problem Solver)[In Chinese]
| Title | 構建一個中文國小數學文字問題語料庫(Building a Corpus for Developing the Chinese Elementary School Math Word Problem Solver)[In Chinese] |
| Authors | Shen-Yun Miao, Su-Chu Lin, Wei-Yun Ma, Keh-Yih Su |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1031/ |
| https://www.aclweb.org/anthology/O16-1031 | |
| PWC | https://paperswithcode.com/paper/aoa-aa-aa-a-aaeeaaobuilding-a-corpus-for |
| Repo | |
| Framework | |
多通道之多重音頻串流方法之研究(Multi-channel Source Clustering of Polyphonic Music) [In Chinese]
| Title | 多通道之多重音頻串流方法之研究(Multi-channel Source Clustering of Polyphonic Music) [In Chinese] |
| Authors | Chih Yi Kuan, Li Su, Yu Hao Chin, Jia-Ching Wang |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1014/ |
| https://www.aclweb.org/anthology/O16-1014 | |
| PWC | https://paperswithcode.com/paper/aeea1aee3e-a-213a1c-cmulti-channel-source |
| Repo | |
| Framework | |
Using BabelNet to Improve OOV Coverage in SMT
| Title | Using BabelNet to Improve OOV Coverage in SMT |
| Authors | Jinhua Du, Andy Way, Andrzej Zydron |
| Abstract | Out-of-vocabulary words (OOVs) are a ubiquitous and difficult problem in statistical machine translation (SMT). This paper studies different strategies of using BabelNet to alleviate the negative impact brought about by OOVs. BabelNet is a multilingual encyclopedic dictionary and a semantic network, which not only includes lexicographic and encyclopedic terms, but connects concepts and named entities in a very large network of semantic relations. By taking advantage of the knowledge in BabelNet, three different methods ― using direct training data, domain-adaptation techniques and the BabelNet API ― are proposed in this paper to obtain translations for OOVs to improve system performance. Experimental results on English―Polish and English―Chinese language pairs show that domain adaptation can better utilize BabelNet knowledge and performs better than other methods. The results also demonstrate that BabelNet is a really useful tool for improving translation performance of SMT systems. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1002/ |
| https://www.aclweb.org/anthology/L16-1002 | |
| PWC | https://paperswithcode.com/paper/using-babelnet-to-improve-oov-coverage-in-smt |
| Repo | |
| Framework | |
