Paper Group NANR 196
Word Clustering Approach to Bilingual Document Alignment (WMT 2016 Shared Task). SHEF-MIME: Word-level Quality Estimation Using Imitation Learning. Word Alignment without NULL Words. Interactive-Predictive Translation Based on Multiple Word-Segments. UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation. Intrinsic Evaluation of Wor …
Word Clustering Approach to Bilingual Document Alignment (WMT 2016 Shared Task)
| Title | Word Clustering Approach to Bilingual Document Alignment (WMT 2016 Shared Task) |
| Authors | Vadim Shchukin, Dmitry Khristich, Irina Galinskaya |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2376/ |
| https://www.aclweb.org/anthology/W16-2376 | |
| PWC | https://paperswithcode.com/paper/word-clustering-approach-to-bilingual |
| Repo | |
| Framework | |
SHEF-MIME: Word-level Quality Estimation Using Imitation Learning
| Title | SHEF-MIME: Word-level Quality Estimation Using Imitation Learning |
| Authors | Daniel Beck, Andreas Vlachos, Gustavo Paetzold, Lucia Specia |
| Abstract | |
| Tasks | Feature Engineering, Imitation Learning, Machine Translation, Part-Of-Speech Tagging, Structured Prediction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2381/ |
| https://www.aclweb.org/anthology/W16-2381 | |
| PWC | https://paperswithcode.com/paper/shef-mime-word-level-quality-estimation-using |
| Repo | |
| Framework | |
Word Alignment without NULL Words
| Title | Word Alignment without NULL Words |
| Authors | Philip Schulz, Wilker Aziz, Khalil Sima{'}an |
| Abstract | |
| Tasks | Language Modelling, Word Alignment |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2028/ |
| https://www.aclweb.org/anthology/P16-2028 | |
| PWC | https://paperswithcode.com/paper/word-alignment-without-null-words |
| Repo | |
| Framework | |
Interactive-Predictive Translation Based on Multiple Word-Segments
| Title | Interactive-Predictive Translation Based on Multiple Word-Segments |
| Authors | Miguel Domingo, Alvaro Peris, Francisco Casacuberta |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3415/ |
| https://www.aclweb.org/anthology/W16-3415 | |
| PWC | https://paperswithcode.com/paper/interactive-predictive-translation-based-on |
| Repo | |
| Framework | |
UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation
| Title | UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation |
| Authors | Arda Tezcan, V{'e}ronique Hoste, Lieve Macken |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2393/ |
| https://www.aclweb.org/anthology/W16-2393 | |
| PWC | https://paperswithcode.com/paper/ugent-lt3-scate-submission-for-wmt16-shared |
| Repo | |
| Framework | |
Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance
| Title | Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance |
| Authors | Billy Chiu, Anna Korhonen, Sampo Pyysalo |
| Abstract | |
| Tasks | Named Entity Recognition, Part-Of-Speech Tagging, Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2501/ |
| https://www.aclweb.org/anthology/W16-2501 | |
| PWC | https://paperswithcode.com/paper/intrinsic-evaluation-of-word-vectors-fails-to |
| Repo | |
| Framework | |
The UU Submission to the Machine Translation Quality Estimation Task
| Title | The UU Submission to the Machine Translation Quality Estimation Task |
| Authors | Oscar Sagemo, Sara Stymne |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2390/ |
| https://www.aclweb.org/anthology/W16-2390 | |
| PWC | https://paperswithcode.com/paper/the-uu-submission-to-the-machine-translation |
| Repo | |
| Framework | |
A Latent Concept Topic Model for Robust Topic Inference Using Word Embeddings
| Title | A Latent Concept Topic Model for Robust Topic Inference Using Word Embeddings |
| Authors | Weihua Hu, Jun{'}ichi Tsujii |
| Abstract | |
| Tasks | Topic Models, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2062/ |
| https://www.aclweb.org/anthology/P16-2062 | |
| PWC | https://paperswithcode.com/paper/a-latent-concept-topic-model-for-robust-topic |
| Repo | |
| Framework | |
Dependency Annotation Choices: Assessing Theoretical and Practical Issues of Universal Dependencies
| Title | Dependency Annotation Choices: Assessing Theoretical and Practical Issues of Universal Dependencies |
| Authors | Kim Gerdes, Sylvain Kahane |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1715/ |
| https://www.aclweb.org/anthology/W16-1715 | |
| PWC | https://paperswithcode.com/paper/dependency-annotation-choices-assessing |
| Repo | |
| Framework | |
Learning Kernels with Random Features
| Title | Learning Kernels with Random Features |
| Authors | Aman Sinha, John C. Duchi |
| Abstract | Randomized features provide a computationally efficient way to approximate kernel machines in machine learning tasks. However, such methods require a user-defined kernel as input. We extend the randomized-feature approach to the task of learning a kernel (via its associated random features). Specifically, we present an efficient optimization problem that learns a kernel in a supervised manner. We prove the consistency of the estimated kernel as well as generalization bounds for the class of estimators induced by the optimized kernel, and we experimentally evaluate our technique on several datasets. Our approach is efficient and highly scalable, and we attain competitive results with a fraction of the training cost of other techniques. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6180-learning-kernels-with-random-features |
| http://papers.nips.cc/paper/6180-learning-kernels-with-random-features.pdf | |
| PWC | https://paperswithcode.com/paper/learning-kernels-with-random-features |
| Repo | |
| Framework | |
Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen
| Title | Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen |
| Authors | Aleks Drozd, r, Anna Gladkova, Satoshi Matsuoka |
| Abstract | Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as \textit{king}:\textit{man} :: \textit{woman}:\textit{queen}) are indicative of the quality of the embedding. We question this assumption by showing that the information not detected by linear offset may still be recoverable by a more sophisticated search method, and thus is actually encoded in the embedding. The general problem with linear offset is its sensitivity to the idiosyncrasies of individual words. We show that simple averaging over multiple word pairs improves over the state-of-the-art. A further improvement in accuracy (up to 30{%} for some embeddings and relations) is achieved by combining cosine similarity with an estimation of the extent to which a candidate answer belongs to the correct word class. In addition to this practical contribution, this work highlights the problem of the interaction between word embeddings and analogy retrieval algorithms, and its implications for the evaluation of word embeddings and the use of analogies in extrinsic tasks. |
| Tasks | Morphological Analysis, Word Embeddings, Word Sense Disambiguation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1332/ |
| https://www.aclweb.org/anthology/C16-1332 | |
| PWC | https://paperswithcode.com/paper/word-embeddings-analogies-and-machine |
| Repo | |
| Framework | |
HHU at SemEval-2016 Task 1: Multiple Approaches to Measuring Semantic Textual Similarity
| Title | HHU at SemEval-2016 Task 1: Multiple Approaches to Measuring Semantic Textual Similarity |
| Authors | Matthias Liebeck, Philipp Pollack, Pashutan Modaresi, Stefan Conrad |
| Abstract | |
| Tasks | Lemmatization, Named Entity Recognition, Part-Of-Speech Tagging, Semantic Textual Similarity, Text Summarization, Tokenization, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1090/ |
| https://www.aclweb.org/anthology/S16-1090 | |
| PWC | https://paperswithcode.com/paper/hhu-at-semeval-2016-task-1-multiple |
| Repo | |
| Framework | |
Impact of MWE Resources on Multiword Recognition
| Title | Impact of MWE Resources on Multiword Recognition |
| Authors | Martin Riedl, Chris Biemann |
| Abstract | |
| Tasks | Named Entity Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1816/ |
| https://www.aclweb.org/anthology/W16-1816 | |
| PWC | https://paperswithcode.com/paper/impact-of-mwe-resources-on-multiword |
| Repo | |
| Framework | |
Learning Tree Structured Potential Games
| Title | Learning Tree Structured Potential Games |
| Authors | Vikas Garg, Tommi Jaakkola |
| Abstract | Many real phenomena, including behaviors, involve strategic interactions that can be learned from data. We focus on learning tree structured potential games where equilibria are represented by local maxima of an underlying potential function. We cast the learning problem within a max margin setting and show that the problem is NP-hard even when the strategic interactions form a tree. We develop a variant of dual decomposition to estimate the underlying game and demonstrate with synthetic and real decision/voting data that the game theoretic perspective (carving out local maxima) enables meaningful recovery. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6152-learning-tree-structured-potential-games |
| http://papers.nips.cc/paper/6152-learning-tree-structured-potential-games.pdf | |
| PWC | https://paperswithcode.com/paper/learning-tree-structured-potential-games |
| Repo | |
| Framework | |
Intrinsic Evaluations of Word Embeddings: What Can We Do Better?
| Title | Intrinsic Evaluations of Word Embeddings: What Can We Do Better? |
| Authors | Anna Gladkova, Aleks Drozd, r |
| Abstract | |
| Tasks | Named Entity Recognition, Semantic Role Labeling, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2507/ |
| https://www.aclweb.org/anthology/W16-2507 | |
| PWC | https://paperswithcode.com/paper/intrinsic-evaluations-of-word-embeddings-what |
| Repo | |
| Framework | |
