Paper Group NANR 225
Deeper syntax for better semantic parsing. Determining the Multiword Expression Inventory of a Surprise Language. The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.. The Multiple Quantile Graphical Model. Using Graphs of Classifiers to Impose Constraints on Semi-supervised Rela …
Deeper syntax for better semantic parsing
| Title | Deeper syntax for better semantic parsing |
| Authors | Olivier Michalon, Corentin Ribeyre, C, Marie ito, Alexis Nasr |
| Abstract | Syntax plays an important role in the task of predicting the semantic structure of a sentence. But syntactic phenomena such as alternations, control and raising tend to obfuscate the relation between syntax and semantics. In this paper we predict the semantic structure of a sentence using a deeper syntax than what is usually done. This deep syntactic representation abstracts away from purely syntactic phenomena and proposes a structural organization of the sentence that is closer to the semantic representation. Experiments conducted on a French corpus annotated with semantic frames showed that a semantic parser reaches better performances with such a deep syntactic input. |
| Tasks | Semantic Parsing, Semantic Role Labeling |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1040/ |
| https://www.aclweb.org/anthology/C16-1040 | |
| PWC | https://paperswithcode.com/paper/deeper-syntax-for-better-semantic-parsing |
| Repo | |
| Framework | |
Determining the Multiword Expression Inventory of a Surprise Language
| Title | Determining the Multiword Expression Inventory of a Surprise Language |
| Authors | Bahar Salehi, Paul Cook, Timothy Baldwin |
| Abstract | Much previous research on multiword expressions (MWEs) has focused on the token- and type-level tasks of MWE identification and extraction, respectively. Such studies typically target known prevalent MWE types in a given language. This paper describes the first attempt to learn the MWE inventory of a {``}surprise{''} language for which we have no explicit prior knowledge of MWE patterns, certainly no annotated MWE data, and not even a parallel corpus. Our proposed model is trained on a treebank with MWE relations of a source language, and can be applied to the monolingual corpus of the surprise language to identify its MWE construction types. | |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1046/ |
| https://www.aclweb.org/anthology/C16-1046 | |
| PWC | https://paperswithcode.com/paper/determining-the-multiword-expression |
| Repo | |
| Framework | |
The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.
| Title | The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data. |
| Authors | Miguel Matos, Alberto Abad, Ant{'o}nio Serralheiro |
| Abstract | In this paper, we describe a new corpus -named DIRHA-L2F RealCorpus- composed of typical home automation speech interactions in European Portuguese that has been recorded by the INESC-ID{'}s Spoken Language Systems Laboratory (L2F) to support the activities of the Distant-speech Interaction for Robust Home Applications (DIRHA) EU-funded project. The corpus is a multi-microphone and multi-room database of real continuous audio sequences containing read phonetically rich sentences, read and spontaneous keyword activation sentences, and read and spontaneous home automation commands. The background noise conditions are controlled and randomly recreated with noises typically found in home environments. Experimental validation on this corpus is reported in comparison with the results obtained on a simulated corpus using a fully automated speech processing pipeline for two fundamental automatic speech recognition tasks of typical {`}always-listening{'} home-automation scenarios: system activation and voice command recognition. Attending to results on both corpora, the presence of overlapping voice-like noise is shown as the main problem: simulated sequences contain concurrent speakers that result in general in a more challenging corpus, while real sequences performance drops drastically when TV or radio is on. | |
| Tasks | Speech Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1633/ |
| https://www.aclweb.org/anthology/L16-1633 | |
| PWC | https://paperswithcode.com/paper/the-dirha-portuguese-corpus-a-comparison-of |
| Repo | |
| Framework | |
The Multiple Quantile Graphical Model
| Title | The Multiple Quantile Graphical Model |
| Authors | Alnur Ali, J. Zico Kolter, Ryan J. Tibshirani |
| Abstract | We introduce the Multiple Quantile Graphical Model (MQGM), which extends the neighborhood selection approach of Meinshausen and Buhlmann for learning sparse graphical models. The latter is defined by the basic subproblem of modeling the conditional mean of one variable as a sparse function of all others. Our approach models a set of conditional quantiles of one variable as a sparse function of all others, and hence offers a much richer, more expressive class of conditional distribution estimates. We establish that, under suitable regularity conditions, the MQGM identifies the exact conditional independencies with probability tending to one as the problem size grows, even outside of the usual homoskedastic Gaussian data model. We develop an efficient algorithm for fitting the MQGM using the alternating direction method of multipliers. We also describe a strategy for sampling from the joint distribution that underlies the MQGM estimate. Lastly, we present detailed experiments that demonstrate the flexibility and effectiveness of the MQGM in modeling hetereoskedastic non-Gaussian data. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6092-the-multiple-quantile-graphical-model |
| http://papers.nips.cc/paper/6092-the-multiple-quantile-graphical-model.pdf | |
| PWC | https://paperswithcode.com/paper/the-multiple-quantile-graphical-model |
| Repo | |
| Framework | |
Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction
| Title | Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction |
| Authors | Lidong Bing, William Cohen, Bhuwan Dhingra, Richard Wang |
| Abstract | |
| Tasks | Relation Extraction |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1301/ |
| https://www.aclweb.org/anthology/W16-1301 | |
| PWC | https://paperswithcode.com/paper/using-graphs-of-classifiers-to-impose-1 |
| Repo | |
| Framework | |
What Makes Word-level Neural Machine Translation Hard: A Case Study on English-German Translation
| Title | What Makes Word-level Neural Machine Translation Hard: A Case Study on English-German Translation |
| Authors | Fabian Hirschmann, Jinseok Nam, Johannes F{"u}rnkranz |
| Abstract | Traditional machine translation systems often require heavy feature engineering and the combination of multiple techniques for solving different subproblems. In recent years, several end-to-end learning architectures based on recurrent neural networks have been proposed. Unlike traditional systems, Neural Machine Translation (NMT) systems learn the parameters of the model and require only minimal preprocessing. Memory and time constraints allow to take only a fixed number of words into account, which leads to the out-of-vocabulary (OOV) problem. In this work, we analyze why the OOV problem arises and why it is considered a serious problem in German. We study the effectiveness of compound word splitters for alleviating the OOV problem, resulting in a 2.5+ BLEU points improvement over a baseline on the WMT{'}14 German-to-English translation task. For English-to-German translation, we use target-side compound splitting through a special syntax during training that allows the model to merge compound words and gain 0.2 BLEU points. |
| Tasks | Feature Engineering, Machine Translation, Tokenization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1301/ |
| https://www.aclweb.org/anthology/C16-1301 | |
| PWC | https://paperswithcode.com/paper/what-makes-word-level-neural-machine |
| Repo | |
| Framework | |
Coordinate-wise Power Method
| Title | Coordinate-wise Power Method |
| Authors | Qi Lei, Kai Zhong, Inderjit S. Dhillon |
| Abstract | In this paper, we propose a coordinate-wise version of the power method from an optimization viewpoint. The vanilla power method simultaneously updates all the coordinates of the iterate, which is essential for its convergence analysis. However, different coordinates converge to the optimal value at different speeds. Our proposed algorithm, which we call coordinate-wise power method, is able to select and update the most important k coordinates in O(kn) time at each iteration, where n is the dimension of the matrix and k <= n is the size of the active set. Inspired by the ‘‘greedy’’ nature of our method, we further propose a greedy coordinate descent algorithm applied on a non-convex objective function specialized for symmetric matrices. We provide convergence analyses for both methods. Experimental results on both synthetic and real data show that our methods achieve up to 20 times speedup over the basic power method. Meanwhile, due to their coordinate-wise nature, our methods are very suitable for the important case when data cannot fit into memory. Finally, we introduce how the coordinate-wise mechanism could be applied to other iterative methods that are used in machine learning. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6103-coordinate-wise-power-method |
| http://papers.nips.cc/paper/6103-coordinate-wise-power-method.pdf | |
| PWC | https://paperswithcode.com/paper/coordinate-wise-power-method |
| Repo | |
| Framework | |
Information-based Modeling of Diachronic Linguistic Change: from Typicality to Productivity
| Title | Information-based Modeling of Diachronic Linguistic Change: from Typicality to Productivity |
| Authors | Stefania Degaetano-Ortlieb, Elke Teich |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2121/ |
| https://www.aclweb.org/anthology/W16-2121 | |
| PWC | https://paperswithcode.com/paper/information-based-modeling-of-diachronic |
| Repo | |
| Framework | |
String Kernels for Native Language Identification: Insights from Behind the Curtains
| Title | String Kernels for Native Language Identification: Insights from Behind the Curtains |
| Authors | Radu Tudor Ionescu, Marius Popescu, Aoife Cahill |
| Abstract | |
| Tasks | Language Identification, Native Language Identification |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/J16-3005/ |
| https://www.aclweb.org/anthology/J16-3005 | |
| PWC | https://paperswithcode.com/paper/string-kernels-for-native-language |
| Repo | |
| Framework | |
Overfitting at SemEval-2016 Task 3: Detecting Semantically Similar Questions in Community Question Answering Forums with Word Embeddings
| Title | Overfitting at SemEval-2016 Task 3: Detecting Semantically Similar Questions in Community Question Answering Forums with Word Embeddings |
| Authors | Hujie Wang, Pascal Poupart |
| Abstract | |
| Tasks | Community Question Answering, Question Answering, Question Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1133/ |
| https://www.aclweb.org/anthology/S16-1133 | |
| PWC | https://paperswithcode.com/paper/overfitting-at-semeval-2016-task-3-detecting |
| Repo | |
| Framework | |
Ranking Automatically Generated Questions Using Common Human Queries
| Title | Ranking Automatically Generated Questions Using Common Human Queries |
| Authors | Yllias Chali, Sina Golestanirad |
| Abstract | |
| Tasks | Question Answering, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6635/ |
| https://www.aclweb.org/anthology/W16-6635 | |
| PWC | https://paperswithcode.com/paper/ranking-automatically-generated-questions |
| Repo | |
| Framework | |
DAG-Structured Long Short-Term Memory for Semantic Compositionality
| Title | DAG-Structured Long Short-Term Memory for Semantic Compositionality |
| Authors | Xiaodan Zhu, Parinaz Sobhani, Hongyu Guo |
| Abstract | |
| Tasks | Machine Translation, Semantic Composition, Sentiment Analysis, Speech Recognition |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1106/ |
| https://www.aclweb.org/anthology/N16-1106 | |
| PWC | https://paperswithcode.com/paper/dag-structured-long-short-term-memory-for |
| Repo | |
| Framework | |
What topic do you want to hear about? A bilingual talking robot using English and Japanese Wikipedias
| Title | What topic do you want to hear about? A bilingual talking robot using English and Japanese Wikipedias |
| Authors | Graham Wilcock, Kristiina Jokinen, Seiichi Yamamoto |
| Abstract | We demonstrate a bilingual robot application, WikiTalk, that can talk fluently in both English and Japanese about almost any topic using information from English and Japanese Wikipedias. The English version of the system has been demonstrated previously, but we now present a live demo with a Nao robot that speaks English and Japanese and switches language on request. The robot supports the verbal interaction with face-tracking, nodding and communicative gesturing. One of the key features of the WikiTalk system is that the robot can switch from the current topic to related topics during the interaction in order to navigate around Wikipedia following the user{'}s individual interests. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2025/ |
| https://www.aclweb.org/anthology/C16-2025 | |
| PWC | https://paperswithcode.com/paper/what-topic-do-you-want-to-hear-about-a |
| Repo | |
| Framework | |
Overview of the 3rd Workshop on Asian Translation
| Title | Overview of the 3rd Workshop on Asian Translation |
| Authors | Toshiaki Nakazawa, Chenchen Ding, Hideya Mino, Isao Goto, Graham Neubig, Sadao Kurohashi |
| Abstract | This paper presents the results of the shared tasks from the 3rd workshop on Asian translation (WAT2016) including J ↔ E, J ↔ C scientific paper translation subtasks, C ↔ J, K ↔ J, E ↔ J patent translation subtasks, I ↔ E newswire subtasks and H ↔ E, H ↔ J mixed domain subtasks. For the WAT2016, 15 institutions participated in the shared tasks. About 500 translation results have been submitted to the automatic evaluation server, and selected submissions were manually evaluated. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4601/ |
| https://www.aclweb.org/anthology/W16-4601 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-3rd-workshop-on-asian |
| Repo | |
| Framework | |
Evaluating Argumentative and Narrative Essays using Graphs
| Title | Evaluating Argumentative and Narrative Essays using Graphs |
| Authors | Swapna Somasundaran, Brian Riordan, Binod Gyawali, Su-Youn Yoon |
| Abstract | This work investigates whether the development of ideas in writing can be captured by graph properties derived from the text. Focusing on student essays, we represent the essay as a graph, and encode a variety of graph properties including PageRank as features for modeling essay scores related to quality of development. We demonstrate that our approach improves on a state-of-the-art system on the task of holistic scoring of persuasive essays and on the task of scoring narrative essays along the development dimension. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1148/ |
| https://www.aclweb.org/anthology/C16-1148 | |
| PWC | https://paperswithcode.com/paper/evaluating-argumentative-and-narrative-essays |
| Repo | |
| Framework | |
