Paper Group NANR 33
Control vs. Raising in English. A Dependency Grammar Account. Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding. Querying Multi-word Expressions Annotation with CQL. Towards Harnessing Memory Networks for Coreference Resolution. Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems …
Control vs. Raising in English. A Dependency Grammar Account
| Title | Control vs. Raising in English. A Dependency Grammar Account |
| Authors | Timothy Osborne, Matthew Reeve |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6521/ |
| https://www.aclweb.org/anthology/W17-6521 | |
| PWC | https://paperswithcode.com/paper/control-vs-raising-in-english-a-dependency |
| Repo | |
| Framework | |
Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding
| Title | Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding |
| Authors | Arya Mazumdar, Soumyabrata Pal |
| Abstract | Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semisupervised clustering is equivalent to locally encodable source coding. In this model, the task is to perform multiclass labeling of unlabeled elements. At the beginning, we can ask in parallel a set of simple queries to an oracle who provides (possibly erroneous) binary answers to the queries. The queries cannot involve more than two (or a fixed constant number $\Delta$ of) elements. Now the labeling of all the elements (or clustering) must be performed based on the (noisy) query answers. The goal is to recover all the correct labelings while minimizing the number of such queries. The equivalence to locally encodable source codes leads us to find lower bounds on the number of queries required in variety of scenarios. We are also able to show fundamental limitations of pairwise `same cluster’ queries - and propose pairwise AND queries, that provably performs better in many situations. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7227-semisupervised-clustering-and-queries-and-locally-encodable-source-coding |
| http://papers.nips.cc/paper/7227-semisupervised-clustering-and-queries-and-locally-encodable-source-coding.pdf | |
| PWC | https://paperswithcode.com/paper/semisupervised-clustering-and-queries-and |
| Repo | |
| Framework | |
Querying Multi-word Expressions Annotation with CQL
| Title | Querying Multi-word Expressions Annotation with CQL |
| Authors | Natalia Klyueva, Anna Vernerov{'a}, Behrang Qasemizadeh |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7611/ |
| https://www.aclweb.org/anthology/W17-7611 | |
| PWC | https://paperswithcode.com/paper/querying-multi-word-expressions-annotation |
| Repo | |
| Framework | |
Towards Harnessing Memory Networks for Coreference Resolution
| Title | Towards Harnessing Memory Networks for Coreference Resolution |
| Authors | Joe Cheri, Pushpak Bhattacharyya |
| Abstract | Coreference resolution task demands comprehending a discourse, especially for anaphoric mentions which require semantic information for resolving antecedents. We investigate into how memory networks can be helpful for coreference resolution when posed as question answering problem. The comprehension capability of memory networks assists coreference resolution, particularly for the mentions that require semantic and context information. We experiment memory networks for coreference resolution, with 4 synthetic datasets generated for coreference resolution with varying difficulty levels. Our system{'}s performance is compared with a traditional coreference resolution system to show why memory network can be promising for coreference resolution. |
| Tasks | Coreference Resolution, Question Answering, Representation Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2605/ |
| https://www.aclweb.org/anthology/W17-2605 | |
| PWC | https://paperswithcode.com/paper/towards-harnessing-memory-networks-for |
| Repo | |
| Framework | |
Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems
| Title | Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems |
| Authors | Wang Ling, Dani Yogatama, Chris Dyer, Phil Blunsom |
| Abstract | Solving algebraic word problems requires executing a series of arithmetic operations{—}a program{—}to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs. |
| Tasks | Decision Making |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1015/ |
| https://www.aclweb.org/anthology/P17-1015 | |
| PWC | https://paperswithcode.com/paper/program-induction-by-rationale-generation-1 |
| Repo | |
| Framework | |
Vowel and Consonant Classification through Spectral Decomposition
| Title | Vowel and Consonant Classification through Spectral Decomposition |
| Authors | Patricia Thaine, Gerald Penn |
| Abstract | We consider two related problems in this paper. Given an undeciphered alphabetic writing system or mono-alphabetic cipher, determine: (1) which of its letters are vowels and which are consonants; and (2) whether the writing system is a vocalic alphabet or an abjad. We are able to show that a very simple spectral decomposition based on character co-occurrences provides nearly perfect performance with respect to answering both question types. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4112/ |
| https://www.aclweb.org/anthology/W17-4112 | |
| PWC | https://paperswithcode.com/paper/vowel-and-consonant-classification-through |
| Repo | |
| Framework | |
All that is English may be Hindi: Enhancing language identification through automatic ranking of the likeliness of word borrowing in social media
| Title | All that is English may be Hindi: Enhancing language identification through automatic ranking of the likeliness of word borrowing in social media |
| Authors | Jasabanta Patro, Bidisha Samanta, Saurabh Singh, Abhipsa Basu, Prithwish Mukherjee, Monojit Choudhury, Animesh Mukherjee |
| Abstract | n this paper, we present a set of computational methods to identify the likeliness of a word being borrowed, based on the signals from social media. In terms of Spearman{'}s correlation values, our methods perform more than two times better (∼ 0.62) in predicting the borrowing likeliness compared to the best performing baseline (∼ 0.26) reported in literature. Based on this likeliness estimate we asked annotators to re-annotate the language tags of foreign words in predominantly native contexts. In 88{%} of cases the annotators felt that the foreign language tag should be replaced by native language tag, thus indicating a huge scope for improvement of automatic language identification systems. |
| Tasks | Language Identification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1240/ |
| https://www.aclweb.org/anthology/D17-1240 | |
| PWC | https://paperswithcode.com/paper/all-that-is-english-may-be-hindi-enhancing-1 |
| Repo | |
| Framework | |
Mama Edha at SemEval-2017 Task 8: Stance Classification with CNN and Rules
| Title | Mama Edha at SemEval-2017 Task 8: Stance Classification with CNN and Rules |
| Authors | Marianela Garc{'\i}a Lozano, Hanna Lilja, Edward Tj{"o}rnhammar, Maja Karasalo |
| Abstract | For the competition SemEval-2017 we investigated the possibility of performing stance classification (support, deny, query or comment) for messages in Twitter conversation threads related to rumours. Stance classification is interesting since it can provide a basis for rumour veracity assessment. Our ensemble classification approach of combining convolutional neural networks with both automatic rule mining and manually written rules achieved a final accuracy of 74.9{%} on the competition{'}s test data set for Task 8A. To improve classification we also experimented with data relabeling and using the grammatical structure of the tweet contents for classification. |
| Tasks | Rumour Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2084/ |
| https://www.aclweb.org/anthology/S17-2084 | |
| PWC | https://paperswithcode.com/paper/mama-edha-at-semeval-2017-task-8-stance |
| Repo | |
| Framework | |
Word Representations in Factored Neural Machine Translation
| Title | Word Representations in Factored Neural Machine Translation |
| Authors | Franck Burlot, Mercedes Garc{'\i}a-Mart{'\i}nez, Lo{"\i}c Barrault, Fethi Bougares, Fran{\c{c}}ois Yvon |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4703/ |
| https://www.aclweb.org/anthology/W17-4703 | |
| PWC | https://paperswithcode.com/paper/word-representations-in-factored-neural |
| Repo | |
| Framework | |
SemEval-2017 Task 11: End-User Development using Natural Language
| Title | SemEval-2017 Task 11: End-User Development using Natural Language |
| Authors | Juliano Sales, H, Siegfried schuh, Andr{'e} Freitas |
| Abstract | This task proposes a challenge to support the interaction between users and applications, micro-services and software APIs using natural language. The task aims for supporting the evaluation and evolution of the discussions surrounding the natural language processing approaches within the context of end-user natural language programming, under scenarios of high semantic heterogeneity/gap. |
| Tasks | Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2092/ |
| https://www.aclweb.org/anthology/S17-2092 | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-11-end-user-development |
| Repo | |
| Framework | |
An Eye-tracking Study of Named Entity Annotation
| Title | An Eye-tracking Study of Named Entity Annotation |
| Authors | Takenobu Tokunaga, Hitoshi Nishikawa, Tomoya Iwakura |
| Abstract | Utilising effective features in machine learning-based natural language processing (NLP) is crucial in achieving good performance for a given NLP task. The paper describes a pilot study on the analysis of eye-tracking data during named entity (NE) annotation, aiming at obtaining insights into effective features for the NE recognition task. The eye gaze data were collected from 10 annotators and analysed regarding working time and fixation distribution. The results of the preliminary qualitative analysis showed that human annotators tend to look at broader contexts around the target NE than recent state-of-the-art automatic NE recognition systems and to use predicate argument relations to identify the NE categories. |
| Tasks | Active Learning, Coreference Resolution, Eye Tracking, Named Entity Recognition, Sentence Compression, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1097/ |
| https://doi.org/10.26615/978-954-452-049-6_097 | |
| PWC | https://paperswithcode.com/paper/an-eye-tracking-study-of-named-entity |
| Repo | |
| Framework | |
The representation and extraction of qunatitative information
| Title | The representation and extraction of qunatitative information |
| Authors | Tianyong Hao, Yunyan We, Jiaqi Qiang, Haitao Wang, Kiyong Lee |
| Abstract | |
| Tasks | Information Retrieval, Question Answering |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7408/ |
| https://www.aclweb.org/anthology/W17-7408 | |
| PWC | https://paperswithcode.com/paper/the-representation-and-extraction-of |
| Repo | |
| Framework | |
Affine-Invariant Online Optimization and the Low-rank Experts Problem
| Title | Affine-Invariant Online Optimization and the Low-rank Experts Problem |
| Authors | Tomer Koren, Roi Livni |
| Abstract | We present a new affine-invariant optimization algorithm called Online Lazy Newton. The regret of Online Lazy Newton is independent of conditioning: the algorithm’s performance depends on the best possible preconditioning of the problem in retrospect and on its \emph{intrinsic} dimensionality. As an application, we show how Online Lazy Newton can be used to achieve an optimal regret of order $\sqrt{rT}$ for the low-rank experts problem, improving by a $\sqrt{r}$ factor over the previously best known bound and resolving an open problem posed by Hazan et al (2016). |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7060-affine-invariant-online-optimization-and-the-low-rank-experts-problem |
| http://papers.nips.cc/paper/7060-affine-invariant-online-optimization-and-the-low-rank-experts-problem.pdf | |
| PWC | https://paperswithcode.com/paper/affine-invariant-online-optimization-and-the |
| Repo | |
| Framework | |
Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data
| Title | Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data |
| Authors | Tommaso Pasini, Roberto Navigli |
| Abstract | Annotating large numbers of sentences with senses is the heaviest requirement of current Word Sense Disambiguation. We present Train-O-Matic, a language-independent method for generating millions of sense-annotated training instances for virtually all meanings of words in a language{'}s vocabulary. The approach is fully automatic: no human intervention is required and the only type of human knowledge used is a WordNet-like resource. Train-O-Matic achieves consistently state-of-the-art performance across gold standard datasets and languages, while at the same time removing the burden of manual annotation. All the training data is available for research purposes at \url{http://trainomatic.org}. |
| Tasks | Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1008/ |
| https://www.aclweb.org/anthology/D17-1008 | |
| PWC | https://paperswithcode.com/paper/train-o-matic-large-scale-supervised-word |
| Repo | |
| Framework | |
Language Technologies in Teaching Bugarian at Primary and Secondary School Level: the NBU Platform of Language Teaching (PLT)
| Title | Language Technologies in Teaching Bugarian at Primary and Secondary School Level: the NBU Platform of Language Teaching (PLT) |
| Authors | Maria Stambolieva, Valentina Ivanova, Mariana Raykova, Milka Hadjikoteva, Mariya Neykova |
| Abstract | The NBU Language Teaching Platform (PLT) was initially designed for teaching foreign languages for specific purposes; at a second stage, some of its functionalities were extended to answer the needs of teaching general foreign language. New functionalities have now been created for the purpose of providing e-support for Bulgarian language and literature teaching at primary and secondary school level. The article presents the general structure of the platform and the functionalities specifically developed to match the standards and expected results set by the Ministry of Education. The E-platform integrates: 1/ an environment for creating, organizing and maintaining electronic text archives, for extracting text corpora and aligning corpora; 2/ a linguistic database; 3/ a concordancer; 4/ a set of modules for the generation and editing of practice exercises for each text or corpus; 5/ functionalities for export from the platform and import to other educational platforms. For Moodle, modules were created for test generation, performance assessment and feedback. The PLT allows centralized presentation of abundant teaching content, control of the educational process, fast and reliable feedback on performance. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8105/ |
| http://doi.org/10.26615/978-954-452-046-5_005 | |
| PWC | https://paperswithcode.com/paper/language-technologies-in-teaching-bugarian-at |
| Repo | |
| Framework | |
