Paper Group NANR 81
BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora. Word Sense Disambiguation for Malayalam in a Conditional Random Field Framework. KILLE: a Framework for Situated Agents for Learning Language Through Interaction. Incremental Graph-based Neural Dependency Parsing. Stack-based Multi-layer Attention for Transition-b …
BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora
| Title | BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora |
| Authors | Sainik Mahata, Dipankar Das, B, Sivaji yopadhyay |
| Abstract | A Statistical Machine Translation (SMT) system is always trained using large parallel corpus to produce effective translation. Not only is the corpus scarce, it also involves a lot of manual labor and cost. Parallel corpus can be prepared by employing comparable corpora where a pair of corpora is in two different languages pointing to the same domain. In the present work, we try to build a parallel corpus for French-English language pair from a given comparable corpus. The data and the problem set are provided as part of the shared task organized by BUCC 2017. We have proposed a system that first translates the sentences by heavily relying on Moses and then group the sentences based on sentence length similarity. Finally, the one to one sentence selection was done based on Cosine Similarity algorithm. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2511/ |
| https://www.aclweb.org/anthology/W17-2511 | |
| PWC | https://paperswithcode.com/paper/bucc2017-a-hybrid-approach-for-identifying |
| Repo | |
| Framework | |
Word Sense Disambiguation for Malayalam in a Conditional Random Field Framework
| Title | Word Sense Disambiguation for Malayalam in a Conditional Random Field Framework |
| Authors | Junaida M K, Jisha P Jayan, Elizabeth Sherly |
| Abstract | |
| Tasks | Word Sense Disambiguation |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7560/ |
| https://www.aclweb.org/anthology/W17-7560 | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-for-malayalam-in-a |
| Repo | |
| Framework | |
KILLE: a Framework for Situated Agents for Learning Language Through Interaction
| Title | KILLE: a Framework for Situated Agents for Learning Language Through Interaction |
| Authors | Simon Dobnik, Erik de Graaf |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0219/ |
| https://www.aclweb.org/anthology/W17-0219 | |
| PWC | https://paperswithcode.com/paper/kille-a-framework-for-situated-agents-for |
| Repo | |
| Framework | |
Incremental Graph-based Neural Dependency Parsing
| Title | Incremental Graph-based Neural Dependency Parsing |
| Authors | Xiaoqing Zheng |
| Abstract | Very recently, some studies on neural dependency parsers have shown advantage over the traditional ones on a wide variety of languages. However, for graph-based neural dependency parsing systems, they either count on the long-term memory and attention mechanism to implicitly capture the high-order features or give up the global exhaustive inference algorithms in order to harness the features over a rich history of parsing decisions. The former might miss out the important features for specific headword predictions without the help of the explicit structural information, and the latter may suffer from the error propagation as false early structural constraints are used to create features when making future predictions. We explore the feasibility of explicitly taking high-order features into account while remaining the main advantage of global inference and learning for graph-based parsing. The proposed parser first forms an initial parse tree by head-modifier predictions based on the first-order factorization. High-order features (such as grandparent, sibling, and uncle) then can be defined over the initial tree, and used to refine the parse tree in an iterative fashion. Experimental results showed that our model (called INDP) archived competitive performance to existing benchmark parsers on both English and Chinese datasets. |
| Tasks | Dependency Parsing, Transition-Based Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1173/ |
| https://www.aclweb.org/anthology/D17-1173 | |
| PWC | https://paperswithcode.com/paper/incremental-graph-based-neural-dependency |
| Repo | |
| Framework | |
Stack-based Multi-layer Attention for Transition-based Dependency Parsing
| Title | Stack-based Multi-layer Attention for Transition-based Dependency Parsing |
| Authors | Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou, Enhong Chen |
| Abstract | Although sequence-to-sequence (seq2seq) network has achieved significant success in many NLP tasks such as machine translation and text summarization, simply applying this approach to transition-based dependency parsing cannot yield a comparable performance gain as in other state-of-the-art methods, such as stack-LSTM and head selection. In this paper, we propose a stack-based multi-layer attention model for seq2seq learning to better leverage structural linguistics information. In our method, two binary vectors are used to track the decoding stack in transition-based parsing, and multi-layer attention is introduced to capture multiple word dependencies in partial trees. We conduct experiments on PTB and CTB datasets, and the results show that our proposed model achieves state-of-the-art accuracy and significant improvement in labeled precision with respect to the baseline seq2seq model. |
| Tasks | Dependency Parsing, Language Modelling, Machine Translation, Text Summarization, Transition-Based Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1175/ |
| https://www.aclweb.org/anthology/D17-1175 | |
| PWC | https://paperswithcode.com/paper/stack-based-multi-layer-attention-for |
| Repo | |
| Framework | |
Multi-View Decision Processes: The Helper-AI Problem
| Title | Multi-View Decision Processes: The Helper-AI Problem |
| Authors | Christos Dimitrakakis, David C. Parkes, Goran Radanovic, Paul Tylkin |
| Abstract | We consider a two-player sequential game in which agents have the same reward function but may disagree on the transition probabilities of an underlying Markovian model of the world. By committing to play a specific policy, the agent with the correct model can steer the behavior of the other agent, and seek to improve utility. We model this setting as a multi-view decision process, which we use to formally analyze the positive effect of steering policies. Furthermore, we develop an algorithm for computing the agents’ achievable joint policy, and we experimentally show that it can lead to a large utility increase when the agents’ models diverge. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7128-multi-view-decision-processes-the-helper-ai-problem |
| http://papers.nips.cc/paper/7128-multi-view-decision-processes-the-helper-ai-problem.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-decision-processes-the-helper-ai |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Subword and Character Level Models in NLP
| Title | Proceedings of the First Workshop on Subword and Character Level Models in NLP |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4100/ |
| https://www.aclweb.org/anthology/W17-4100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-subword |
| Repo | |
| Framework | |
Identification of Multiword Expressions for Latvian and Lithuanian: Hybrid Approach
| Title | Identification of Multiword Expressions for Latvian and Lithuanian: Hybrid Approach |
| Authors | M, Justina ravickait{.e}, Tomas Krilavi{\v{c}}ius |
| Abstract | We discuss an experiment on automatic identification of bi-gram multi-word expressions in parallel Latvian and Lithuanian corpora. Raw corpora, lexical association measures (LAMs) and supervised machine learning (ML) are used due to deficit and quality of lexical resources (e.g., POS-tagger, parser) and tools. While combining LAMs with ML is rather effective for other languages, it has shown some nice results for Lithuanian and Latvian as well. Combining LAMs with ML we have achieved 92,4{%} precision and 52,2{%} recall for Latvian and 95,1{%} precision and 77,8{%} recall for Lithuanian. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1712/ |
| https://www.aclweb.org/anthology/W17-1712 | |
| PWC | https://paperswithcode.com/paper/identification-of-multiword-expressions-for |
| Repo | |
| Framework | |
Gradient Coding: Avoiding Stragglers in Distributed Learning
| Title | Gradient Coding: Avoiding Stragglers in Distributed Learning |
| Authors | Rashish Tandon, Qi Lei, Alexandros G. Dimakis, Nikos Karampatziakis |
| Abstract | We propose a novel coding theoretic framework for mitigating stragglers in distributed learning. We show how carefully replicating data blocks and coding across gradients can provide tolerance to failures and stragglers for synchronous Gradient Descent. We implement our schemes in python (using MPI) to run on Amazon EC2, and show how we compare against baseline approaches in running time and generalization error. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=851 |
| http://proceedings.mlr.press/v70/tandon17a/tandon17a.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-coding-avoiding-stragglers-in |
| Repo | |
| Framework | |
Convolutional Phase Retrieval
| Title | Convolutional Phase Retrieval |
| Authors | Qing Qu, Yuqian Zhang, Yonina Eldar, John Wright |
| Abstract | We study the convolutional phase retrieval problem, which asks us to recover an unknown signal ${\mathbf x} $ of length $n$ from $m$ measurements consisting of the magnitude of its cyclic convolution with a known kernel $\mathbf a$ of length $m$. This model is motivated by applications to channel estimation, optics, and underwater acoustic communication, where the signal of interest is acted on by a given channel/filter, and phase information is difficult or impossible to acquire. We show that when $\mathbf a$ is random and $m \geq \Omega(\frac{ \ \mathbf C_{\mathbf x}^2}{ \mathbf x^2 } n \mathrm{poly} \log n)$, $\mathbf x$ can be efficiently recovered up to a global phase using a combination of spectral initialization and generalized gradient descent. The main challenge is coping with dependencies in the measurement operator; we overcome this challenge by using ideas from decoupling theory, suprema of chaos processes and the restricted isometry property of random circulant matrices, and recent analysis for alternating minimizing methods. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7189-convolutional-phase-retrieval |
| http://papers.nips.cc/paper/7189-convolutional-phase-retrieval.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-phase-retrieval |
| Repo | |
| Framework | |
Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017
| Title | Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017 |
| Authors | Kalliopi Zervanou, Petya Osenova, Austria Eveline Wandl-Vogt, Austrian Academy of Sciences, Romania Dan Cristea, “Alexandru Ioan Cuza” University of Iasi |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-7800/w17-7800 |
| https://www.aclweb.org/anthology/W17-7800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-knowledge |
| Repo | |
| Framework | |
Learning and Knowledge Transfer with Memory Networks for Machine Comprehension
| Title | Learning and Knowledge Transfer with Memory Networks for Machine Comprehension |
| Authors | Mohit Yadav, Lovekesh Vig, Gautam Shroff |
| Abstract | Enabling machines to read and comprehend unstructured text remains an unfulfilled goal for NLP research. Recent research efforts on the {``}machine comprehension{''} task have managed to achieve close to ideal performance on simulated data. However, achieving similar levels of performance on small real world datasets has proved difficult; major challenges stem from the large vocabulary size, complex grammar, and, the frequent ambiguities in linguistic structure. On the other hand, the requirement of human generated annotations for training, in order to ensure a sufficiently diverse set of questions is prohibitively expensive. Motivated by these practical issues, we propose a novel curriculum inspired training procedure for Memory Networks to improve the performance for machine comprehension with relatively small volumes of training data. Additionally, we explore various training regimes for Memory Networks to allow knowledge transfer from a closely related domain having larger volumes of labelled data. We also suggest the use of a loss function to incorporate the asymmetric nature of knowledge transfer. Our experiments demonstrate improvements on Dailymail, CNN, and MCTest datasets. | |
| Tasks | Question Answering, Reading Comprehension, Transfer Learning |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1080/ |
| https://www.aclweb.org/anthology/E17-1080 | |
| PWC | https://paperswithcode.com/paper/learning-and-knowledge-transfer-with-memory |
| Repo | |
| Framework | |
Differentiable Learning of Submodular Models
| Title | Differentiable Learning of Submodular Models |
| Authors | Josip Djolonga, Andreas Krause |
| Abstract | Can we incorporate discrete optimization algorithms within modern machine learning models? For example, is it possible to use in deep architectures a layer whose output is the minimal cut of a parametrized graph? Given that these models are trained end-to-end by leveraging gradient information, the introduction of such layers seems very challenging due to their non-continuous output. In this paper we focus on the problem of submodular minimization, for which we show that such layers are indeed possible. The key idea is that we can continuously relax the output without sacrificing guarantees. We provide an easily computable approximation to the Jacobian complemented with a complete theoretical analysis. Finally, these contributions let us experimentally learn probabilistic log-supermodular models via a bi-level variational inference formulation. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6702-differentiable-learning-of-submodular-models |
| http://papers.nips.cc/paper/6702-differentiable-learning-of-submodular-models.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-learning-of-submodular-models |
| Repo | |
| Framework | |
Breaking Sentiment Analysis of Movie Reviews
| Title | Breaking Sentiment Analysis of Movie Reviews |
| Authors | Ieva Stali{=u}nait{.e}, Ben Bonfil |
| Abstract | The current paper covers several strategies we used to {`}break{'} predictions of sentiment analysis systems participating in the BLGNLP2017 workshop. Specifically, we identify difficulties of participating systems in understanding modals, subjective judgments, world-knowledge based references and certain differences in syntax and perspective. | |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5410/ |
| https://www.aclweb.org/anthology/W17-5410 | |
| PWC | https://paperswithcode.com/paper/breaking-sentiment-analysis-of-movie-reviews |
| Repo | |
| Framework | |
The similarity and Mutual Intelligibility between Amharic and Tigrigna Varieties
| Title | The similarity and Mutual Intelligibility between Amharic and Tigrigna Varieties |
| Authors | Tekabe Legesse Feleke |
| Abstract | The present study has examined the similarity and the mutual intelligibility between Amharic and Tigrigna using three tools namely Levenshtein distance, intelligibility test and questionnaires. The study has shown that both Tigrigna varieties have almost equal phonetic and lexical distances from Amharic. The study also indicated that Amharic speakers understand less than 50{%} of the two varieties. Furthermore, the study showed that Amharic speakers are more positive about the Ethiopian Tigrigna variety than the Eritrean Variety. However, their attitude towards the two varieties does not have an impact on their intelligibility. The Amharic speakers{'} familiarity to the Tigrigna varieties is largely dependent on the genealogical relation between Amharic and the two Tigrigna varieties. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1206/ |
| https://www.aclweb.org/anthology/W17-1206 | |
| PWC | https://paperswithcode.com/paper/the-similarity-and-mutual-intelligibility |
| Repo | |
| Framework | |
