Paper Group NANR 91
User expectations towards machine translation: A case study. The Romanian Corpus Annotated with Verbal Multiword Expressions. Contextual Recurrent Convolutional Model for Robust Visual Learning. Bootstrapping a Natural Language Interface to a Cyber Security Event Collection System using a Hybrid Translation Approach. Pre-editing Plus Neural Machine …
User expectations towards machine translation: A case study
| Title | User expectations towards machine translation: A case study |
| Authors | Barbara Heinisch, Vesna Lu{\v{s}}icky |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6707/ |
| https://www.aclweb.org/anthology/W19-6707 | |
| PWC | https://paperswithcode.com/paper/user-expectations-towards-machine-translation |
| Repo | |
| Framework | |
The Romanian Corpus Annotated with Verbal Multiword Expressions
| Title | The Romanian Corpus Annotated with Verbal Multiword Expressions |
| Authors | Verginica Barbu Mititelu, Mihaela Cristescu, Mihaela Onofrei |
| Abstract | This paper reports on the Romanian journalistic corpus annotated with verbal multiword expressions following the PARSEME guidelines. The corpus is sentence split, tokenized, part-of-speech tagged, lemmatized, syntactically annotated and verbal multiword expressions are identified and classified. It offers insights into the frequency of such Romanian word combinations and allows for their characterization. We offer data about the types of verbal multiword expressions in the corpus and some of their characteristics, such as internal structure, diversity in the corpus, average length, productivity of the verbs. This is a language resource that is important per se, as well as for the task of automatic multiword expressions identification, which can be further used in other systems. It was already used as training and test material in the shared tasks for the automatic identification of verbal multiword expressions organized by PARSEME. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5103/ |
| https://www.aclweb.org/anthology/W19-5103 | |
| PWC | https://paperswithcode.com/paper/the-romanian-corpus-annotated-with-verbal |
| Repo | |
| Framework | |
Contextual Recurrent Convolutional Model for Robust Visual Learning
| Title | Contextual Recurrent Convolutional Model for Robust Visual Learning |
| Authors | Siming Yan*, Bowen Xiao*, Yimeng Zhang, Tai Sing Lee |
| Abstract | Feedforward convolutional neural network has achieved a great success in many computer vision tasks. While it validly imitates the hierarchical structure of biological visual system, it still lacks one essential architectural feature: contextual recurrent connections with feedback, which widely exists in biological visual system. In this work, we designed a Contextual Recurrent Convolutional Network with this feature embedded in a standard CNN structure. We found that such feedback connections could enable lower layers to ``rethink” about their representations given the top-down contextual information. We carefully studied the components of this network, and showed its robustness and superiority over feedforward baselines in such tasks as noise image classification, partially occluded object recognition and fine-grained image classification. We believed this work could be an important step to help bridge the gap between computer vision models and real biological visual system. | |
| Tasks | Fine-Grained Image Classification, Image Classification, Object Recognition |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkzyX3CcFQ |
| https://openreview.net/pdf?id=HkzyX3CcFQ | |
| PWC | https://paperswithcode.com/paper/contextual-recurrent-convolutional-model-for |
| Repo | |
| Framework | |
Bootstrapping a Natural Language Interface to a Cyber Security Event Collection System using a Hybrid Translation Approach
| Title | Bootstrapping a Natural Language Interface to a Cyber Security Event Collection System using a Hybrid Translation Approach |
| Authors | Johann Roturier, Brian Schlatter, David Silva Schlatter |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6726/ |
| https://www.aclweb.org/anthology/W19-6726 | |
| PWC | https://paperswithcode.com/paper/bootstrapping-a-natural-language-interface-to |
| Repo | |
| Framework | |
Pre-editing Plus Neural Machine Translation for Subtitling: Effective Pre-editing Rules for Subtitling of TED Talks
| Title | Pre-editing Plus Neural Machine Translation for Subtitling: Effective Pre-editing Rules for Subtitling of TED Talks |
| Authors | Yusuke Hiraoka, Masaru Yamada |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6710/ |
| https://www.aclweb.org/anthology/W19-6710 | |
| PWC | https://paperswithcode.com/paper/pre-editing-plus-neural-machine-translation |
| Repo | |
| Framework | |
A step towards Torwali machine translation: an analysis of morphosyntactic challenges in a low-resource language
| Title | A step towards Torwali machine translation: an analysis of morphosyntactic challenges in a low-resource language |
| Authors | Naeem Uddin, Jalal Uddin |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6802/ |
| https://www.aclweb.org/anthology/W19-6802 | |
| PWC | https://paperswithcode.com/paper/a-step-towards-torwali-machine-translation-an |
| Repo | |
| Framework | |
Machine Translation for Crimean Tatar to Turkish
| Title | Machine Translation for Crimean Tatar to Turkish |
| Authors | Memduh G{"o}k{\i}rmak, Francis Tyers, Jonathan Washington |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6805/ |
| https://www.aclweb.org/anthology/W19-6805 | |
| PWC | https://paperswithcode.com/paper/machine-translation-for-crimean-tatar-to |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Multilingualism at the Intersection of Knowledge Bases and Machine Translation
| Title | Proceedings of the Second Workshop on Multilingualism at the Intersection of Knowledge Bases and Machine Translation |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7100/ |
| https://www.aclweb.org/anthology/W19-7100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-21 |
| Repo | |
| Framework | |
A folksonomy-based approach for profiling human perception on word similarity
| Title | A folksonomy-based approach for profiling human perception on word similarity |
| Authors | Guani Wu, Ker-Chau Li |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7413/ |
| https://www.aclweb.org/anthology/W19-7413 | |
| PWC | https://paperswithcode.com/paper/a-folksonomy-based-approach-for-profiling |
| Repo | |
| Framework | |
Unsupervised Compositional Translation of Multiword Expressions
| Title | Unsupervised Compositional Translation of Multiword Expressions |
| Authors | Pablo Gamallo, Marcos Garcia |
| Abstract | This article describes a dependency-based strategy that uses compositional distributional semantics and cross-lingual word embeddings to translate multiword expressions (MWEs). Our unsupervised approach performs translation as a process of word contextualization by taking into account lexico-syntactic contexts and selectional preferences. This strategy is suited to translate phraseological combinations and phrases whose constituent words are lexically restricted by each other. Several experiments in adjective-noun and verb-object compounds show that mutual contextualization (co-compositionality) clearly outperforms other compositional methods. The paper also contributes with a new freely available dataset of English-Spanish MWEs used to validate the proposed compositional strategy. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5106/ |
| https://www.aclweb.org/anthology/W19-5106 | |
| PWC | https://paperswithcode.com/paper/unsupervised-compositional-translation-of |
| Repo | |
| Framework | |
L2 Processing Advantages of Multiword Sequences: Evidence from Eye-Tracking
| Title | L2 Processing Advantages of Multiword Sequences: Evidence from Eye-Tracking |
| Authors | Elma Kerz, Arndt Heilmann, Stella Neumann |
| Abstract | A substantial body of research has demonstrated that native speakers are sensitive to the frequencies of multiword sequences (MWS). Here, we ask whether and to what extent intermediate-advanced L2 speakers of English can also develop the sensitivity to the statistics of MWS. To this end, we aimed to replicate the MWS frequency effects found for adult native language speakers based on evidence from self-paced reading and sentence recall tasks in an ecologically more valid eye-tracking study. L2 speakers{'} sensitivity to MWS frequency was evaluated using generalized linear mixed-effects regression with separate models fitted for each of the four dependent measures. Mixed-effects modeling revealed significantly faster processing of sentences containing MWS compared to sentences containing equivalent control items across all eyetracking measures. Taken together, these findings suggest that, in line with emergentist approaches, MWS are important building blocks of language and that similar mechanisms underlie both native and non-native language processing. |
| Tasks | Eye Tracking |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5108/ |
| https://www.aclweb.org/anthology/W19-5108 | |
| PWC | https://paperswithcode.com/paper/l2-processing-advantages-of-multiword |
| Repo | |
| Framework | |
ADIDA: Automatic Dialect Identification for Arabic
| Title | ADIDA: Automatic Dialect Identification for Arabic |
| Authors | Ossama Obeid, Mohammad Salameh, Houda Bouamor, Nizar Habash |
| Abstract | This demo paper describes ADIDA, a web-based system for automatic dialect identification for Arabic text. The system distinguishes among the dialects of 25 Arab cities (from Rabat to Muscat) in addition to Modern Standard Arabic. The results are presented with either a point map or a heat map visualizing the automatic identification probabilities over a geographical map of the Arab World. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4002/ |
| https://www.aclweb.org/anthology/N19-4002 | |
| PWC | https://paperswithcode.com/paper/adida-automatic-dialect-identification-for |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP
| Title | Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5900/ |
| https://www.aclweb.org/anthology/D19-5900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-15 |
| Repo | |
| Framework | |
Wasserstein Barycenter Model Ensembling
| Title | Wasserstein Barycenter Model Ensembling |
| Authors | Pierre Dognin*, Igor Melnyk*, Youssef Mroueh*, Jarret Ross*, Cicero Dos Santos*, Tom Sercu* |
| Abstract | In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters. Optimal transport metrics, such as the Wasserstein distance, allow incorporating semantic side information such as word embeddings. Using W. barycenters to find the consensus between models allows us to balance confidence and semantics in finding the agreement between the models. We show applications of Wasserstein ensembling in attribute-based classification, multilabel learning and image captioning generation. These results show that the W. ensembling is a viable alternative to the basic geometric or arithmetic mean ensembling. |
| Tasks | Image Captioning, Word Embeddings |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1g4k309F7 |
| https://openreview.net/pdf?id=H1g4k309F7 | |
| PWC | https://paperswithcode.com/paper/wasserstein-barycenter-model-ensembling |
| Repo | |
| Framework | |
Predicate Catenae: A Dependency Grammar Analysis of It-Clefts
| Title | Predicate Catenae: A Dependency Grammar Analysis of It-Clefts |
| Authors | Timothy Osborne |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7706/ |
| https://www.aclweb.org/anthology/W19-7706 | |
| PWC | https://paperswithcode.com/paper/predicate-catenae-a-dependency-grammar |
| Repo | |
| Framework | |
