Paper Group NANR 195
Interactively Learning Visually Grounded Word Meanings from a Human Tutor. Faking Intelligent CALL: The Irish context and the road ahead. Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification. Japanese Text Normalization with Encoder-Decoder Model. ASU: An Experimental Study on Applying Deep Learning in …
Interactively Learning Visually Grounded Word Meanings from a Human Tutor
| Title | Interactively Learning Visually Grounded Word Meanings from a Human Tutor |
| Authors | Yanchao Yu, Arash Eshghi, Oliver Lemon |
| Abstract | |
| Tasks | Object Classification, Semantic Parsing |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-3206/ |
| https://www.aclweb.org/anthology/W16-3206 | |
| PWC | https://paperswithcode.com/paper/interactively-learning-visually-grounded-word |
| Repo | |
| Framework | |
Faking Intelligent CALL: The Irish context and the road ahead
| Title | Faking Intelligent CALL: The Irish context and the road ahead |
| Authors | Neasa N{'\i} Chiar{'a}in, Ailbhe N{'\i} Chasaide |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-6508/ |
| https://www.aclweb.org/anthology/W16-6508 | |
| PWC | https://paperswithcode.com/paper/faking-intelligent-call-the-irish-context-and |
| Repo | |
| Framework | |
Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification
| Title | Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification |
| Authors | Dominikus Wetzel |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2357/ |
| https://www.aclweb.org/anthology/W16-2357 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-pronoun-prediction-for-english |
| Repo | |
| Framework | |
Japanese Text Normalization with Encoder-Decoder Model
| Title | Japanese Text Normalization with Encoder-Decoder Model |
| Authors | Taishi Ikeda, Hiroyuki Shindo, Yuji Matsumoto |
| Abstract | Text normalization is the task of transforming lexical variants to their canonical forms. We model the problem of text normalization as a character-level sequence to sequence learning problem and present a neural encoder-decoder model for solving it. To train the encoder-decoder model, many sentences pairs are generally required. However, Japanese non-standard canonical pairs are scarce in the form of parallel corpora. To address this issue, we propose a method of data augmentation to increase data size by converting existing resources into synthesized non-standard forms using handcrafted rules. We conducted an experiment to demonstrate that the synthesized corpus contributes to stably train an encoder-decoder model and improve the performance of Japanese text normalization. |
| Tasks | Data Augmentation, Machine Translation, Morphological Analysis, Part-Of-Speech Tagging |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3918/ |
| https://www.aclweb.org/anthology/W16-3918 | |
| PWC | https://paperswithcode.com/paper/japanese-text-normalization-with-encoder |
| Repo | |
| Framework | |
ASU: An Experimental Study on Applying Deep Learning in Twitter Named Entity Recognition.
| Title | ASU: An Experimental Study on Applying Deep Learning in Twitter Named Entity Recognition. |
| Authors | Michel Naim Gerguis, Cherif Salama, M. Watheq El-Kharashi |
| Abstract | This paper describes the ASU system submitted in the COLING W-NUT 2016 Twitter Named Entity Recognition (NER) task. We present an experimental study on applying deep learning to extracting named entities (NEs) from tweets. We built two Long Short-Term Memory (LSTM) models for the task. The first model was built to extract named entities without types while the second model was built to extract and then classify them into 10 fine-grained entity classes. In this effort, we show detailed experimentation results on the effectiveness of word embeddings, brown clusters, part-of-speech (POS) tags, shape features, gazetteers, and local context for the tweet input vector representation to the LSTM model. Also, we present a set of experiments, to better design the network parameters for the Twitter NER task. Our system was ranked the fifth out of ten participants with a final f1-score for the typed classes of 39{%} and 55{%} for the non typed ones. |
| Tasks | Entity Extraction, Named Entity Recognition, Opinion Mining, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3925/ |
| https://www.aclweb.org/anthology/W16-3925 | |
| PWC | https://paperswithcode.com/paper/asu-an-experimental-study-on-applying-deep |
| Repo | |
| Framework | |
Cross-Lingual Image Caption Generation
| Title | Cross-Lingual Image Caption Generation |
| Authors | Takashi Miyazaki, Nobuyuki Shimizu |
| Abstract | |
| Tasks | Dependency Parsing, Image Captioning, Information Retrieval, Named Entity Recognition, Sentiment Analysis, Transfer Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1168/ |
| https://www.aclweb.org/anthology/P16-1168 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-image-caption-generation |
| Repo | |
| Framework | |
Identifying Content Types of Messages Related to Open Source Software Projects
| Title | Identifying Content Types of Messages Related to Open Source Software Projects |
| Authors | Yannis Korkontzelos, Paul Thompson, Sophia Ananiadou |
| Abstract | Assessing the suitability of an Open Source Software project for adoption requires not only an analysis of aspects related to the code, such as code quality, frequency of updates and new version releases, but also an evaluation of the quality of support offered in related online forums and issue trackers. Understanding the content types of forum messages and issue trackers can provide information about the extent to which requests are being addressed and issues are being resolved, the percentage of issues that are not being fixed, the cases where the user acknowledged that the issue was successfully resolved, etc. These indicators can provide potential adopters of the OSS with estimates about the level of available support. We present a detailed hierarchy of content types of online forum messages and issue tracker comments and a corpus of messages annotated accordingly. We discuss our experiments to classify forum messages and issue tracker comments into content-related classes, i.e.{\textasciitilde}to assign them to nodes of the hierarchy. The results are very encouraging. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1290/ |
| https://www.aclweb.org/anthology/L16-1290 | |
| PWC | https://paperswithcode.com/paper/identifying-content-types-of-messages-related |
| Repo | |
| Framework | |
The SemDaX Corpus ― Sense Annotations with Scalable Sense Inventories
| Title | The SemDaX Corpus ― Sense Annotations with Scalable Sense Inventories |
| Authors | Bolette Pedersen, Anna Braasch, Anders Johannsen, H{'e}ctor Mart{'\i}nez Alonso, Sanni Nimb, Sussi Olsen, Anders S{\o}gaard, Nicolai Hartvig S{\o}rensen |
| Abstract | We launch the SemDaX corpus which is a recently completed Danish human-annotated corpus available through a CLARIN academic license. The corpus includes approx. 90,000 words, comprises six textual domains, and is annotated with sense inventories of different granularity. The aim of the developed corpus is twofold: i) to assess the reliability of the different sense annotation schemes for Danish measured by qualitative analyses and annotation agreement scores, and ii) to serve as training and test data for machine learning algorithms with the practical purpose of developing sense taggers for Danish. To these aims, we take a new approach to human-annotated corpus resources by double annotating a much larger part of the corpus than what is normally seen: for the all-words task we double annotated 60{%} of the material and for the lexical sample task 100{%}. We include in the corpus not only the adjucated files, but also the diverging annotations. In other words, we consider not all disagreement to be noise, but rather to contain valuable linguistic information that can help us improve our annotation schemes and our learning algorithms. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1136/ |
| https://www.aclweb.org/anthology/L16-1136 | |
| PWC | https://paperswithcode.com/paper/the-semdax-corpus-a-sense-annotations-with |
| Repo | |
| Framework | |
DOCAL - Vicomtech’s Participation in the WMT16 Shared Task on Bilingual Document Alignment
| Title | DOCAL - Vicomtech’s Participation in the WMT16 Shared Task on Bilingual Document Alignment |
| Authors | Andoni Azpeitia, Thierry Etchegoyhen |
| Abstract | |
| Tasks | Machine Translation, Semantic Textual Similarity |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2364/ |
| https://www.aclweb.org/anthology/W16-2364 | |
| PWC | https://paperswithcode.com/paper/docal-vicomtechs-participation-in-the-wmt16 |
| Repo | |
| Framework | |
Antecedent Prediction Without a Pipeline
| Title | Antecedent Prediction Without a Pipeline |
| Authors | Sam Wiseman, Alex Rush, er M., Stuart Shieber |
| Abstract | |
| Tasks | Coreference Resolution |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0708/ |
| https://www.aclweb.org/anthology/W16-0708 | |
| PWC | https://paperswithcode.com/paper/antecedent-prediction-without-a-pipeline |
| Repo | |
| Framework | |
You and me… in a vector space: modelling individual speakers with distributional semantics
| Title | You and me… in a vector space: modelling individual speakers with distributional semantics |
| Authors | Aur{'e}lie Herbelot, Behrang QasemiZadeh |
| Abstract | |
| Tasks | Information Retrieval, Language Acquisition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/S16-2023/ |
| https://www.aclweb.org/anthology/S16-2023 | |
| PWC | https://paperswithcode.com/paper/you-and-me-in-a-vector-space-modelling |
| Repo | |
| Framework | |
First Steps Towards Coverage-Based Document Alignment
| Title | First Steps Towards Coverage-Based Document Alignment |
| Authors | Lu{'\i}s Gomes, Gabriel Pereira Lopes |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2369/ |
| https://www.aclweb.org/anthology/W16-2369 | |
| PWC | https://paperswithcode.com/paper/first-steps-towards-coverage-based-document |
| Repo | |
| Framework | |
Network Motifs May Improve Quality Assessment of Text Documents
| Title | Network Motifs May Improve Quality Assessment of Text Documents |
| Authors | Thomas Arnold, Karsten Weihe |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1404/ |
| https://www.aclweb.org/anthology/W16-1404 | |
| PWC | https://paperswithcode.com/paper/network-motifs-may-improve-quality-assessment |
| Repo | |
| Framework | |
Finding Non-Arbitrary Form-Meaning Systematicity Using String-Metric Learning for Kernel Regression
| Title | Finding Non-Arbitrary Form-Meaning Systematicity Using String-Metric Learning for Kernel Regression |
| Authors | E.Dario Guti{'e}rrez, Roger Levy, Benjamin Bergen |
| Abstract | |
| Tasks | Metric Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1225/ |
| https://www.aclweb.org/anthology/P16-1225 | |
| PWC | https://paperswithcode.com/paper/finding-non-arbitrary-form-meaning |
| Repo | |
| Framework | |
Proceedings of the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL)
| Title | Proceedings of the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL) |
| Authors | |
| Abstract | |
| Tasks | Information Retrieval, Question Answering |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1500/ |
| https://www.aclweb.org/anthology/W16-1500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-joint-workshop-on-3 |
| Repo | |
| Framework | |
