Paper Group NANR 144
Tensor Contraction & Regression Networks. Assessment of an Index for Measuring Pronunciation Difficulty. A Twitter Corpus for Hindi-English Code Mixed POS Tagging. From Fidelity to Fluency: Natural Language Processing for Translator Training. Connecting Supervised and Unsupervised Sentence Embeddings. deepSA2018 at SemEval-2018 Task 1: Multi-task L …
Tensor Contraction & Regression Networks
| Title | Tensor Contraction & Regression Networks |
| Authors | Jean Kossaifi, Zack Chase Lipton, Aran Khanna, Tommaso Furlanello, Anima Anandkumar |
| Abstract | Convolution neural networks typically consist of many convolutional layers followed by several fully-connected layers. While convolutional layers map between high-order activation tensors, the fully-connected layers operate on flattened activation vectors. Despite its success, this approach has notable drawbacks. Flattening discards the multi-dimensional structure of the activations, and the fully-connected layers require a large number of parameters. We present two new techniques to address these problems. First, we introduce tensor contraction layers which can replace the ordinary fully-connected layers in a neural network. Second, we introduce tensor regression layers, which express the output of a neural network as a low-rank multi-linear mapping from a high-order activation tensor to the softmax layer. Both the contraction and regression weights are learned end-to-end by backpropagation. By imposing low rank on both, we use significantly fewer parameters. Experiments on the ImageNet dataset show that applied to the popular VGG and ResNet architectures, our methods significantly reduce the number of parameters in the fully connected layers (about 65% space savings) while negligibly impacting accuracy. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=S16FPMgRZ |
| https://openreview.net/pdf?id=S16FPMgRZ | |
| PWC | https://paperswithcode.com/paper/tensor-contraction-regression-networks |
| Repo | |
| Framework | |
Assessment of an Index for Measuring Pronunciation Difficulty
| Title | Assessment of an Index for Measuring Pronunciation Difficulty |
| Authors | Katsunori Kotani, Takehiko Yoshimi |
| Abstract | This study assesses an index for measur-ing the pronunciation difficulty of sen-tences (henceforth, pronounceability) based on the normalized edit distance from a reference sentence to a transcrip-tion of learners{'} pronunciation. Pro-nounceability should be examined when language teachers use a computer-assisted language learning system for pronunciation learning to maintain the motivation of learners. However, unlike the evaluation of learners{'} pronunciation performance, previous research did not focus on pronounceability not only for English but also for Asian languages. This study found that the normalized edit distance was reliable but not valid. The lack of validity appeared to be because of an English test used for determining the proficiency of learners. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3717/ |
| https://www.aclweb.org/anthology/W18-3717 | |
| PWC | https://paperswithcode.com/paper/assessment-of-an-index-for-measuring |
| Repo | |
| Framework | |
A Twitter Corpus for Hindi-English Code Mixed POS Tagging
| Title | A Twitter Corpus for Hindi-English Code Mixed POS Tagging |
| Authors | Kushagra Singh, Indira Sen, Ponnurangam Kumaraguru |
| Abstract | Code-mixing is a linguistic phenomenon where multiple languages are used in the same occurrence that is increasingly common in multilingual societies. Code-mixed content on social media is also on the rise, prompting the need for tools to automatically understand such content. Automatic Parts-of-Speech (POS) tagging is an essential step in any Natural Language Processing (NLP) pipeline, but there is a lack of annotated data to train such models. In this work, we present a unique language tagged and POS-tagged dataset of code-mixed English-Hindi tweets related to five incidents in India that led to a lot of Twitter activity. Our dataset is unique in two dimensions: (i) it is larger than previous annotated datasets and (ii) it closely resembles typical real-world tweets. Additionally, we present a POS tagging model that is trained on this dataset to provide an example of how this dataset can be used. The model also shows the efficacy of our dataset in enabling the creation of code-mixed social media POS taggers. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3503/ |
| https://www.aclweb.org/anthology/W18-3503 | |
| PWC | https://paperswithcode.com/paper/a-twitter-corpus-for-hindi-english-code-mixed |
| Repo | |
| Framework | |
From Fidelity to Fluency: Natural Language Processing for Translator Training
| Title | From Fidelity to Fluency: Natural Language Processing for Translator Training |
| Authors | Oi Yee Kwong |
| Abstract | This study explores the use of natural language processing techniques to enhance bilingual lexical access beyond simple equivalents, to enable translators to navigate along a wider cross-lingual lexical space and more examples showing different translation strategies, which is essential for them to learn to produce not only faithful but also fluent translations. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3719/ |
| https://www.aclweb.org/anthology/W18-3719 | |
| PWC | https://paperswithcode.com/paper/from-fidelity-to-fluency-natural-language |
| Repo | |
| Framework | |
Connecting Supervised and Unsupervised Sentence Embeddings
| Title | Connecting Supervised and Unsupervised Sentence Embeddings |
| Authors | Gil Levi |
| Abstract | Representing sentences as numerical vectors while capturing their semantic context is an important and useful intermediate step in natural language processing. Representations that are both general and discriminative can serve as a tool for tackling various NLP tasks. While common sentence representation methods are unsupervised in nature, recently, an approach for learning universal sentence representation in a supervised setting was presented in (Conneau et al.,2017). We argue that although promising results were obtained, an improvement can be reached by adding various unsupervised constraints that are motivated by auto-encoders and by language models. We show that by adding such constraints, superior sentence embeddings can be achieved. We compare our method with the original implementation and show improvements in several tasks. |
| Tasks | Denoising, Natural Language Inference, Representation Learning, Sentence Embedding, Sentence Embeddings, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3010/ |
| https://www.aclweb.org/anthology/W18-3010 | |
| PWC | https://paperswithcode.com/paper/connecting-supervised-and-unsupervised |
| Repo | |
| Framework | |
deepSA2018 at SemEval-2018 Task 1: Multi-task Learning of Different Label for Affect in Tweets
| Title | deepSA2018 at SemEval-2018 Task 1: Multi-task Learning of Different Label for Affect in Tweets |
| Authors | Zi-Yuan Gao, Chia-Ping Chen |
| Abstract | This paper describes our system implementation for subtask V-oc of SemEval-2018 Task 1: affect in tweets. We use multi-task learning method to learn shared representation, then learn the features for each task. There are five classification models in the proposed multi-task learning approach. These classification models are trained sequentially to learn different features for different classification tasks. In addition to the data released for SemEval-2018, we use datasets from previous SemEvals during system construction. Our Pearson correlation score is 0.638 on the official SemEval-2018 Task 1 test set. |
| Tasks | Multi-Task Learning, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1034/ |
| https://www.aclweb.org/anthology/S18-1034 | |
| PWC | https://paperswithcode.com/paper/deepsa2018-at-semeval-2018-task-1-multi-task |
| Repo | |
| Framework | |
Using Embeddings to Compare FrameNet Frames Across Languages
| Title | Using Embeddings to Compare FrameNet Frames Across Languages |
| Authors | Jennifer Sikos, Sebastian Pad{'o} |
| Abstract | Much interest in Frame Semantics is fueled by the substantial extent of its applicability across languages. At the same time, lexicographic studies have found that the applicability of individual frames can be diminished by cross-lingual divergences regarding polysemy, syntactic valency, and lexicalization. Due to the large effort involved in manual investigations, there are so far no broad-coverage resources with {``}problematic{''} frames for any language pair. Our study investigates to what extent multilingual vector representations of frames learned from manually annotated corpora can address this need by serving as a wide coverage source for such divergences. We present a case study for the language pair English {—} German using the FrameNet and SALSA corpora and find that inferences can be made about cross-lingual frame applicability using a vector space model. | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3813/ |
| https://www.aclweb.org/anthology/W18-3813 | |
| PWC | https://paperswithcode.com/paper/using-embeddings-to-compare-framenet-frames |
| Repo | |
| Framework | |
AX Semantics’ Submission to the Surface Realization Shared Task 2018
| Title | AX Semantics’ Submission to the Surface Realization Shared Task 2018 |
| Authors | Andreas Madsack, Johanna Heininger, Nyamsuren Davaasambuu, Vitaliia Voronik, Michael K{"a}ufl, Robert Wei{\ss}graeber |
| Abstract | In this paper we describe our system and experimental results on the development set of the Surface Realisation Shared Task. Our system is an entry for the Shallow-Task, with two different models based on deep-learning implementations for building the sentence combined with a rule-based morphology component. |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3607/ |
| https://www.aclweb.org/anthology/W18-3607 | |
| PWC | https://paperswithcode.com/paper/ax-semantics-submission-to-the-surface |
| Repo | |
| Framework | |
Trouble on the Road: Finding Reasons for Commuter Stress from Tweets
| Title | Trouble on the Road: Finding Reasons for Commuter Stress from Tweets |
| Authors | Reshmi Gopalakrishna Pillai, Mike Thelwall, Constantin Orasan |
| Abstract | |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6705/ |
| https://www.aclweb.org/anthology/W18-6705 | |
| PWC | https://paperswithcode.com/paper/trouble-on-the-road-finding-reasons-for |
| Repo | |
| Framework | |
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning
| Title | KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning |
| Authors | Florian Dessloch, Thanh-Le Ha, Markus M{"u}ller, Jan Niehues, Thai-Son Nguyen, Ngoc-Quan Pham, Elizabeth Salesky, Matthias Sperber, Sebastian St{"u}ker, Thomas Zenkel, Alex Waibel, er |
| Abstract | In today{'}s globalized world we have the ability to communicate with people across the world. However, in many situations the language barrier still presents a major issue. For example, many foreign students coming to KIT to study are initially unable to follow a lecture in German. Therefore, we offer an automatic simultaneous interpretation service for students. To fulfill this task, we have developed a low-latency translation system that is adapted to lectures and covers several language pairs. While the switch from traditional Statistical Machine Translation to Neural Machine Translation (NMT) significantly improved performance, to integrate NMT into the speech translation framework required several adjustments. We have addressed the run-time constraints and different types of input. Furthermore, we utilized one-shot learning to easily add new topic-specific terms to the system. Besides better performance, NMT also enabled us increase our covered languages through multilingual NMT. {%} Combining these techniques, we are able to provide an adapted speech translation system for several European languages. |
| Tasks | Machine Translation, One-Shot Learning, Speech Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2020/ |
| https://www.aclweb.org/anthology/C18-2020 | |
| PWC | https://paperswithcode.com/paper/kit-lecture-translator-multilingual-speech |
| Repo | |
| Framework | |
Explicit Retrofitting of Distributional Word Vectors
| Title | Explicit Retrofitting of Distributional Word Vectors |
| Authors | Goran Glava{\v{s}}, Ivan Vuli{'c} |
| Abstract | Semantic specialization of distributional word vectors, referred to as retrofitting, is a process of fine-tuning word vectors using external lexical knowledge in order to better embed some semantic relation. Existing retrofitting models integrate linguistic constraints directly into learning objectives and, consequently, specialize only the vectors of words from the constraints. In this work, in contrast, we transform external lexico-semantic relations into training examples which we use to learn an explicit retrofitting model (ER). The ER model allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well. We report large gains over original distributional vector spaces in (1) intrinsic word similarity evaluation and on (2) two downstream tasks − lexical simplification and dialog state tracking. Finally, we also successfully specialize vector spaces of new languages (i.e., unseen in the training data) by coupling ER with shared multilingual distributional vector spaces. |
| Tasks | Lexical Simplification, Semantic Textual Similarity, Text Simplification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1004/ |
| https://www.aclweb.org/anthology/P18-1004 | |
| PWC | https://paperswithcode.com/paper/explicit-retrofitting-of-distributional-word |
| Repo | |
| Framework | |
Identifying Analogies Across Domains
| Title | Identifying Analogies Across Domains |
| Authors | Yedid Hoshen, Lior Wolf |
| Abstract | Identifying analogies across domains without supervision is a key task for artificial intelligence. Recent advances in cross domain image mapping have concentrated on translating images across domains. Although the progress made is impressive, the visual fidelity many times does not suffice for identifying the matching sample from the other domain. In this paper, we tackle this very task of finding exact analogies between datasets i.e. for every image from domain A find an analogous image in domain B. We present a matching-by-synthesis approach: AN-GAN, and show that it outperforms current techniques. We further show that the cross-domain mapping task can be broken into two parts: domain alignment and learning the mapping function. The tasks can be iteratively solved, and as the alignment is improved, the unsupervised translation function reaches quality comparable to full supervision. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BkN_r2lR- |
| https://openreview.net/pdf?id=BkN_r2lR- | |
| PWC | https://paperswithcode.com/paper/identifying-analogies-across-domains |
| Repo | |
| Framework | |
輔助建立混合性系統之自然語言處理系統深度評估平台 — 以評估依存關係分析器為例 (The Platform providing NLP System Deep Comparative Evaluation and Auxiliary Information for Hybrid NLP System Building: Trial on Dependency Parser Evaluation) [In Chinese]
| Title | 輔助建立混合性系統之自然語言處理系統深度評估平台 — 以評估依存關係分析器為例 (The Platform providing NLP System Deep Comparative Evaluation and Auxiliary Information for Hybrid NLP System Building: Trial on Dependency Parser Evaluation) [In Chinese] |
| Authors | Yi-siang Wang |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1024/ |
| https://www.aclweb.org/anthology/O18-1024 | |
| PWC | https://paperswithcode.com/paper/e14aaocac3ca1eaceae-ecc3caoea14a13a-a |
| Repo | |
| Framework | |
Political discourse classification in social networks using context sensitive convolutional neural networks
| Title | Political discourse classification in social networks using context sensitive convolutional neural networks |
| Authors | Aritz Bilbao-Jayo, Aitor Almeida |
| Abstract | In this study we propose a new approach to analyse the political discourse in on-line social networks such as Twitter. To do so, we have built a discourse classifier using Convolutional Neural Networks. Our model has been trained using election manifestos annotated manually by political scientists following the Regional Manifestos Project (RMP) methodology. In total, it has been trained with more than 88,000 sentences extracted from more that 100 annotated manifestos. Our approach takes into account the context of the phrase in order to classify it, like what was previously said and the political affiliation of the transmitter. To improve the classification results we have used a simplified political message taxonomy developed within the Electronic Regional Manifestos Project (E-RMP). Using this taxonomy, we have validated our approach analysing the Twitter activity of the main Spanish political parties during 2015 and 2016 Spanish general election and providing a study of their discourse. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3513/ |
| https://www.aclweb.org/anthology/W18-3513 | |
| PWC | https://paperswithcode.com/paper/political-discourse-classification-in-social |
| Repo | |
| Framework | |
Can Rumour Stance Alone Predict Veracity?
| Title | Can Rumour Stance Alone Predict Veracity? |
| Authors | Sebastian Dungs, Ahmet Aker, Norbert Fuhr, Kalina Bontcheva |
| Abstract | Prior manual studies of rumours suggested that crowd stance can give insights into the actual rumour veracity. Even though numerous studies of automatic veracity classification of social media rumours have been carried out, none explored the effectiveness of leveraging crowd stance to determine veracity. We use stance as an additional feature to those commonly used in earlier studies. We also model the veracity of a rumour using variants of Hidden Markov Models (HMM) and the collective stance information. This paper demonstrates that HMMs that use stance and tweets{'} times as the only features for modelling true and false rumours achieve F1 scores in the range of 80{%}, outperforming those approaches where stance is used jointly with content and user based features. |
| Tasks | Rumour Detection |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1284/ |
| https://www.aclweb.org/anthology/C18-1284 | |
| PWC | https://paperswithcode.com/paper/can-rumour-stance-alone-predict-veracity |
| Repo | |
| Framework | |
