Paper Group NANR 148
Building Web-Interfaces for Vector Semantic Models with the WebVectors Toolkit. Evaluating Low-Level Speech Features Against Human Perceptual Data. 使用查詢意向探索與類神經網路於語音文件檢索之研究 (Exploring Query Intent and Neural Network modeling Techniques for Spoken Document Retrieval) [In Chinese]. Exploring Soft-Clustering for German (Particle) Verbs across Frequenc …
Building Web-Interfaces for Vector Semantic Models with the WebVectors Toolkit
| Title | Building Web-Interfaces for Vector Semantic Models with the WebVectors Toolkit |
| Authors | Andrey Kutuzov, Elizaveta Kuzmenko |
| Abstract | In this demo we present WebVectors, a free and open-source toolkit helping to deploy web services which demonstrate and visualize distributional semantic models (widely known as word embeddings). WebVectors can be useful in a very common situation when one has trained a distributional semantics model for one{'}s particular corpus or language (tools for this are now widespread and simple to use), but then there is a need to demonstrate the results to general public over the Web. We show its abilities on the example of the living web services featuring distributional models for English, Norwegian and Russian. |
| Tasks | Machine Translation, Named Entity Recognition, Sentiment Analysis, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3025/ |
| https://www.aclweb.org/anthology/E17-3025 | |
| PWC | https://paperswithcode.com/paper/building-web-interfaces-for-vector-semantic |
| Repo | |
| Framework | |
Evaluating Low-Level Speech Features Against Human Perceptual Data
| Title | Evaluating Low-Level Speech Features Against Human Perceptual Data |
| Authors | Caitlin Richter, Naomi H. Feldman, Harini Salgado, Aren Jansen |
| Abstract | We introduce a method for measuring the correspondence between low-level speech features and human perception, using a cognitive model of speech perception implemented directly on speech recordings. We evaluate two speaker normalization techniques using this method and find that in both cases, speech features that are normalized across speakers predict human data better than unnormalized speech features, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a new framework for evaluating low-level representations of speech on their match to human perception, and lays the groundwork for creating more ecologically valid models of speech perception. |
| Tasks | Representation Learning, Speech Recognition |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1030/ |
| https://www.aclweb.org/anthology/Q17-1030 | |
| PWC | https://paperswithcode.com/paper/evaluating-low-level-speech-features-against |
| Repo | |
| Framework | |
使用查詢意向探索與類神經網路於語音文件檢索之研究 (Exploring Query Intent and Neural Network modeling Techniques for Spoken Document Retrieval) [In Chinese]
| Title | 使用查詢意向探索與類神經網路於語音文件檢索之研究 (Exploring Query Intent and Neural Network modeling Techniques for Spoken Document Retrieval) [In Chinese] |
| Authors | Tien-Hong Lo, Ying-Wen Chen, Berlin Chen, Kuan-Yu Chen, Hsin-Min Wang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1015/ |
| https://www.aclweb.org/anthology/O17-1015 | |
| PWC | https://paperswithcode.com/paper/a12c-eac-eeccc2e-14eae3aac-a1c-c-exploring |
| Repo | |
| Framework | |
Exploring Soft-Clustering for German (Particle) Verbs across Frequency Ranges
| Title | Exploring Soft-Clustering for German (Particle) Verbs across Frequency Ranges |
| Authors | Moritz Wittmann, Maximilian K{"o}per, Sabine Schulte im Walde |
| Abstract | |
| Tasks | Machine Translation, Word Sense Disambiguation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6942/ |
| https://www.aclweb.org/anthology/W17-6942 | |
| PWC | https://paperswithcode.com/paper/exploring-soft-clustering-for-german-particle |
| Repo | |
| Framework | |
Utterance Intent Classification of a Spoken Dialogue System with Efficiently Untied Recursive Autoencoders
| Title | Utterance Intent Classification of a Spoken Dialogue System with Efficiently Untied Recursive Autoencoders |
| Authors | Tsuneo Kato, Atsushi Nagai, Naoki Noda, Ryosuke Sumitomo, Jianming Wu, Seiichi Yamamoto |
| Abstract | Recursive autoencoders (RAEs) for compositionality of a vector space model were applied to utterance intent classification of a smartphone-based Japanese-language spoken dialogue system. Though the RAEs express a nonlinear operation on the vectors of child nodes, the operation is considered to be different intrinsically depending on types of child nodes. To relax the difference, a data-driven untying of autoencoders (AEs) is proposed. The experimental result of the utterance intent classification showed an improved accuracy with the proposed method compared with the basic tied RAE and untied RAE based on a manual rule. |
| Tasks | Intent Classification, Slot Filling, Speech Recognition, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5508/ |
| https://www.aclweb.org/anthology/W17-5508 | |
| PWC | https://paperswithcode.com/paper/utterance-intent-classification-of-a-spoken |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
| Title | Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0900/ |
| https://www.aclweb.org/anthology/W17-0900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-linking |
| Repo | |
| Framework | |
Semantic Similarity Analysis for Paraphrase Identification in Arabic Texts
| Title | Semantic Similarity Analysis for Paraphrase Identification in Arabic Texts |
| Authors | Adnen Mahmoud, Mounir Zrigui |
| Abstract | |
| Tasks | Paraphrase Identification, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1037/ |
| https://www.aclweb.org/anthology/Y17-1037 | |
| PWC | https://paperswithcode.com/paper/semantic-similarity-analysis-for-paraphrase |
| Repo | |
| Framework | |
Proceedings of the Workshop on Speech-Centric Natural Language Processing
| Title | Proceedings of the Workshop on Speech-Centric Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4600/ |
| https://www.aclweb.org/anthology/W17-4600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-speech-centric |
| Repo | |
| Framework | |
Breaking Locality Accelerates Block Gauss-Seidel
| Title | Breaking Locality Accelerates Block Gauss-Seidel |
| Authors | Stephen Tu, Shivaram Venkataraman, Ashia C. Wilson, Alex Gittens, Michael I. Jordan, Benjamin Recht |
| Abstract | Recent work by Nesterov and Stich (2016) showed that momentum can be used to accelerate the rate of convergence for block Gauss-Seidel in the setting where a fixed partitioning of the coordinates is chosen ahead of time. We show that this setting is too restrictive, constructing instances where breaking locality by running non-accelerated Gauss-Seidel with randomly sampled coordinates substantially outperforms accelerated Gauss-Seidel with any fixed partitioning. Motivated by this finding, we analyze the accelerated block Gauss-Seidel algorithm in the random coordinate sampling setting. Our analysis captures the benefit of acceleration with a new data-dependent parameter which is well behaved when the matrix sub-blocks are well-conditioned. Empirically, we show that accelerated Gauss-Seidel with random coordinate sampling provides speedups for large scale machine learning tasks when compared to non-accelerated Gauss-Seidel and the classical conjugate-gradient algorithm. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=502 |
| http://proceedings.mlr.press/v70/tu17a/tu17a.pdf | |
| PWC | https://paperswithcode.com/paper/breaking-locality-accelerates-block-gauss |
| Repo | |
| Framework | |
Hashtag Sense Clustering Based on Temporal Similarity
| Title | Hashtag Sense Clustering Based on Temporal Similarity |
| Authors | Giovanni Stilo, Paola Velardi |
| Abstract | Hashtags are creative labels used in micro-blogs to characterize the topic of a message/discussion. Regardless of the use for which they were originally intended, hashtags cannot be used as a means to cluster messages with similar content. First, because hashtags are created in a spontaneous and highly dynamic way by users in multiple languages, the same topic can be associated with different hashtags, and conversely, the same hashtag may refer to different topics in different time periods. Second, contrary to common words, hashtag disambiguation is complicated by the fact that no sense catalogs (e.g., Wikipedia or WordNet) are available; and, furthermore, hashtag labels are difficult to analyze, as they often consist of acronyms, concatenated words, and so forth. A common way to determine the meaning of hashtags has been to analyze their context, but, as we have just pointed out, hashtags can have multiple and variable meanings. In this article, we propose a temporal sense clustering algorithm based on the idea that semantically related hashtags have similar and synchronous usage patterns. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/J17-1005/ |
| https://www.aclweb.org/anthology/J17-1005 | |
| PWC | https://paperswithcode.com/paper/hashtag-sense-clustering-based-on-temporal |
| Repo | |
| Framework | |
bleu2vec: the Painfully Familiar Metric on Continuous Vector Space Steroids
| Title | bleu2vec: the Painfully Familiar Metric on Continuous Vector Space Steroids |
| Authors | Andre T{"a}ttar, Mark Fishel |
| Abstract | |
| Tasks | Lemmatization, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4771/ |
| https://www.aclweb.org/anthology/W17-4771 | |
| PWC | https://paperswithcode.com/paper/bleu2vec-the-painfully-familiar-metric-on |
| Repo | |
| Framework | |
Identify the Nash Equilibrium in Static Games with Random Payoffs
| Title | Identify the Nash Equilibrium in Static Games with Random Payoffs |
| Authors | Yichi Zhou, Jialian Li, Jun Zhu |
| Abstract | We study the problem on how to learn the pure Nash Equilibrium of a two-player zero-sum static game with random payoffs under unknown distributions via efficient payoff queries. We introduce a multi-armed bandit model to this problem due to its ability to find the best arm efficiently among random arms and propose two algorithms for this problem—LUCB-G based on the confidence bounds and a racing algorithm based on successive action elimination. We provide an analysis on the sample complexity lower bound when the Nash Equilibrium exists. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=681 |
| http://proceedings.mlr.press/v70/zhou17b/zhou17b.pdf | |
| PWC | https://paperswithcode.com/paper/identify-the-nash-equilibrium-in-static-games |
| Repo | |
| Framework | |
Improving the generation of personalised descriptions
| Title | Improving the generation of personalised descriptions |
| Authors | Thiago Castro Ferreira, Iv Paraboni, r{'e} |
| Abstract | Referring expression generation (REG) models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly. In this work we propose a simple personalised method for this task, in which speakers are grouped into profiles according to their referential behaviour. Intrinsic evaluation shows that the use of speaker{'}s profiles generally outperforms the personalised method found in previous work. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3536/ |
| https://www.aclweb.org/anthology/W17-3536 | |
| PWC | https://paperswithcode.com/paper/improving-the-generation-of-personalised |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Abusive Language Online
| Title | Proceedings of the First Workshop on Abusive Language Online |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3000/ |
| https://www.aclweb.org/anthology/W17-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-abusive |
| Repo | |
| Framework | |
RAMBLE ON: Tracing Movements of Popular Historical Figures
| Title | RAMBLE ON: Tracing Movements of Popular Historical Figures |
| Authors | Stefano Menini, Rachele Sprugnoli, Giovanni Moretti, Enrico Bignotti, Sara Tonelli, Bruno Lepri |
| Abstract | We present RAMBLE ON, an application integrating a pipeline for frame-based information extraction and an interface to track and display movement trajectories. The code of the extraction pipeline and a navigator are freely available; moreover we display in a demonstrator the outcome of a case study carried out on trajectories of notable persons of the XX Century. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3020/ |
| https://www.aclweb.org/anthology/E17-3020 | |
| PWC | https://paperswithcode.com/paper/ramble-on-tracing-movements-of-popular |
| Repo | |
| Framework | |
