Paper Group NANR 17
Context-enhanced Adaptive Entity Linking. Langforia: Language Pipelines for Annotating Large Collections of Documents. New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian. UtahBMI at SemEval-2016 Task 12: Extracting Temporal Information from Clinical Text. Morphological Complexity Influence …
Context-enhanced Adaptive Entity Linking
| Title | Context-enhanced Adaptive Entity Linking |
| Authors | Filip Ilievski, Giuseppe Rizzo, Marieke van Erp, Julien Plu, Rapha{"e}l Troncy |
| Abstract | More and more knowledge bases are publicly available as linked data. Since these knowledge bases contain structured descriptions of real-world entities, they can be exploited by entity linking systems that anchor entity mentions from text to the most relevant resources describing those entities. In this paper, we investigate adaptation of the entity linking task using contextual knowledge. The key intuition is that entity linking can be customized depending on the textual content, as well as on the application that would make use of the extracted information. We present an adaptive approach that relies on contextual knowledge from text to enhance the performance of ADEL, a hybrid linguistic and graph-based entity linking system. We evaluate our approach on a domain-specific corpus consisting of annotated WikiNews articles. |
| Tasks | Entity Linking |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1086/ |
| https://www.aclweb.org/anthology/L16-1086 | |
| PWC | https://paperswithcode.com/paper/context-enhanced-adaptive-entity-linking |
| Repo | |
| Framework | |
Langforia: Language Pipelines for Annotating Large Collections of Documents
| Title | Langforia: Language Pipelines for Annotating Large Collections of Documents |
| Authors | Marcus Klang, Pierre Nugues |
| Abstract | In this paper, we describe \textbf{Langforia}, a multilingual processing pipeline to annotate texts with multiple layers: formatting, parts of speech, named entities, dependencies, semantic roles, and entity links. Langforia works as a web service, where the server hosts the language processing components and the client, the input and result visualization. To annotate a text or a Wikipedia page, the user chooses an NLP pipeline and enters the text in the interface or selects the page URL. Once processed, the results are returned to the client, where the user can select the annotation layers s/he wants to visualize. We designed Langforia with a specific focus for Wikipedia, although it can process any type of text. Wikipedia has become an essential encyclopedic corpus used in many NLP projects. However, processing articles and visualizing the annotations are nontrivial tasks that require dealing with multiple markup variants, encodings issues, and tool incompatibilities across the language versions. This motivated the development of a new architecture. A demonstration of Langforia is available for six languages: English, French, German, Spanish, Russian, and Swedish at \url{http://vilde.cs.lth.se:9000/} as well as a web API: \url{http://vilde.cs.lth.se:9000/api}. Langforia is also provided as a standalone library and is compatible with cluster computing. |
| Tasks | Dependency Parsing, Entity Linking, Question Answering, Semantic Role Labeling, Tokenization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2016/ |
| https://www.aclweb.org/anthology/C16-2016 | |
| PWC | https://paperswithcode.com/paper/langforia-language-pipelines-for-annotating |
| Repo | |
| Framework | |
New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian
| Title | New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian |
| Authors | Nikola Ljube{\v{s}}i{'c}, Filip Klubi{\v{c}}ka, {\v{Z}}eljko Agi{'c}, Ivo-Pavao Jazbec |
| Abstract | In this paper we present newly developed inflectional lexcions and manually annotated corpora of Croatian and Serbian. We introduce hrLex and srLex - two freely available inflectional lexicons of Croatian and Serbian - and describe the process of building these lexicons, supported by supervised machine learning techniques for lemma and paradigm prediction. Furthermore, we introduce hr500k, a manually annotated corpus of Croatian, 500 thousand tokens in size. We showcase the three newly developed resources on the task of morphosyntactic annotation of both languages by using a recently developed CRF tagger. We achieve best results yet reported on the task for both languages, beating the HunPos baseline trained on the same datasets by a wide margin. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1676/ |
| https://www.aclweb.org/anthology/L16-1676 | |
| PWC | https://paperswithcode.com/paper/new-inflectional-lexicons-and-training |
| Repo | |
| Framework | |
UtahBMI at SemEval-2016 Task 12: Extracting Temporal Information from Clinical Text
| Title | UtahBMI at SemEval-2016 Task 12: Extracting Temporal Information from Clinical Text |
| Authors | Abdulrahman Khalifa, Sumithra Velupillai, Stephane Meystre |
| Abstract | |
| Tasks | Decision Making, Temporal Information Extraction |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1195/ |
| https://www.aclweb.org/anthology/S16-1195 | |
| PWC | https://paperswithcode.com/paper/utahbmi-at-semeval-2016-task-12-extracting |
| Repo | |
| Framework | |
Morphological Complexity Influences Verb-Object Order in Swedish Sign Language
| Title | Morphological Complexity Influences Verb-Object Order in Swedish Sign Language |
| Authors | Johannes Bjerva, Carl B{"o}rstell |
| Abstract | Computational linguistic approaches to sign languages could benefit from investigating how complexity influences structure. We investigate whether morphological complexity has an effect on the order of Verb (V) and Object (O) in Swedish Sign Language (SSL), on the basis of elicited data from five Deaf signers. We find a significant difference in the distribution of the orderings OV vs. VO, based on an analysis of morphological weight. While morphologically heavy verbs exhibit a general preference for OV, humanness seems to affect the ordering in the opposite direction, with [+human] Objects pushing towards a preference for VO. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4116/ |
| https://www.aclweb.org/anthology/W16-4116 | |
| PWC | https://paperswithcode.com/paper/morphological-complexity-influences-verb |
| Repo | |
| Framework | |
CENTAL at SemEval-2016 Task 12: a linguistically fed CRF model for medical and temporal information extraction
| Title | CENTAL at SemEval-2016 Task 12: a linguistically fed CRF model for medical and temporal information extraction |
| Authors | Charlotte Hansart, Damien De Meyere, Patrick Watrin, Andr{'e} Bittar, C{'e}drick Fairon |
| Abstract | |
| Tasks | Part-Of-Speech Tagging, Temporal Information Extraction |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1200/ |
| https://www.aclweb.org/anthology/S16-1200 | |
| PWC | https://paperswithcode.com/paper/cental-at-semeval-2016-task-12-a |
| Repo | |
| Framework | |
IRIS: English-Irish Machine Translation System
| Title | IRIS: English-Irish Machine Translation System |
| Authors | Mihael Arcan, Caoilfhionn Lane, Eoin {'O} Droighne{'a}in, Paul Buitelaar |
| Abstract | We describe IRIS, a statistical machine translation (SMT) system for translating from English into Irish and vice versa. Since Irish is considered an under-resourced language with a limited amount of machine-readable text, building a machine translation system that produces reasonable translations is rather challenging. As translation is a difficult task, current research in SMT focuses on obtaining statistics either from a large amount of parallel, monolingual or other multilingual resources. Nevertheless, we collected available English-Irish data and developed an SMT system aimed at supporting human translators and enabling cross-lingual language technology tasks. |
| Tasks | Machine Translation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1090/ |
| https://www.aclweb.org/anthology/L16-1090 | |
| PWC | https://paperswithcode.com/paper/iris-english-irish-machine-translation-system |
| Repo | |
| Framework | |
A Computational Analysis of Mahabharata
| Title | A Computational Analysis of Mahabharata |
| Authors | Debarati Das, Bhaskarjyoti Das, Kavi Mahesh |
| Abstract | |
| Tasks | Emotion Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6328/ |
| https://www.aclweb.org/anthology/W16-6328 | |
| PWC | https://paperswithcode.com/paper/a-computational-analysis-of-mahabharata |
| Repo | |
| Framework | |
It Takes Three to Tango: Triangulation Approach to Answer Ranking in Community Question Answering
| Title | It Takes Three to Tango: Triangulation Approach to Answer Ranking in Community Question Answering |
| Authors | Preslav Nakov, Llu{'\i}s M{`a}rquez, Francisco Guzm{'a}n |
| Abstract | |
| Tasks | Community Question Answering, Question Answering |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1165/ |
| https://www.aclweb.org/anthology/D16-1165 | |
| PWC | https://paperswithcode.com/paper/it-takes-three-to-tango-triangulation |
| Repo | |
| Framework | |
Cancer Hallmark Text Classification Using Convolutional Neural Networks
| Title | Cancer Hallmark Text Classification Using Convolutional Neural Networks |
| Authors | Simon Baker, Anna Korhonen, Sampo Pyysalo |
| Abstract | Methods based on deep learning approaches have recently achieved state-of-the-art performance in a range of machine learning tasks and are increasingly applied to natural language processing (NLP). Despite strong results in various established NLP tasks involving general domain texts, there is only limited work applying these models to biomedical NLP. In this paper, we consider a Convolutional Neural Network (CNN) approach to biomedical text classification. Evaluation using a recently introduced cancer domain dataset involving the categorization of documents according to the well-established hallmarks of cancer shows that a basic CNN model can achieve a level of performance competitive with a Support Vector Machine (SVM) trained using complex manually engineered features optimized to the task. We further show that simple modifications to the CNN hyperparameters, initialization, and training process allow the model to notably outperform the SVM, establishing a new state of the art result at this task. We make all of the resources and tools introduced in this study available under open licenses from \url{https://cambridgeltl.github.io/cancer-hallmark-cnn/}. |
| Tasks | Text Classification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5101/ |
| https://www.aclweb.org/anthology/W16-5101 | |
| PWC | https://paperswithcode.com/paper/cancer-hallmark-text-classification-using |
| Repo | |
| Framework | |
Global Inference to Chinese Temporal Relation Extraction
| Title | Global Inference to Chinese Temporal Relation Extraction |
| Authors | Peifeng Li, Qiaoming Zhu, Guodong Zhou, Hongling Wang |
| Abstract | Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences. In this paper, we propose a discourse-level global inference model to mine those temporal relations between event mentions in document-level, especially in nonadjacent sentences. Moreover, we provide various kinds of discourse-level constraints, which derived from event semantics, to further improve our global inference model. Evaluation on a Chinese corpus justifies the effectiveness of our discourse-level global inference model over two strong baselines. |
| Tasks | Question Answering, Relation Extraction, Text Generation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1137/ |
| https://www.aclweb.org/anthology/C16-1137 | |
| PWC | https://paperswithcode.com/paper/global-inference-to-chinese-temporal-relation |
| Repo | |
| Framework | |
NUIG-UNLP at SemEval-2016 Task 13: A Simple Word Embedding-based Approach for Taxonomy Extraction
| Title | NUIG-UNLP at SemEval-2016 Task 13: A Simple Word Embedding-based Approach for Taxonomy Extraction |
| Authors | Joel Pocostales |
| Abstract | |
| Tasks | Natural Language Inference, Question Answering, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1202/ |
| https://www.aclweb.org/anthology/S16-1202 | |
| PWC | https://paperswithcode.com/paper/nuig-unlp-at-semeval-2016-task-13-a-simple |
| Repo | |
| Framework | |
On Why Coarse Class Classification is Bottleneck in Noun Compound Interpretation
| Title | On Why Coarse Class Classification is Bottleneck in Noun Compound Interpretation |
| Authors | Girishkumar Ponkiya, Pushpak Bhattacharyya, Girish K. Palshikar |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6336/ |
| https://www.aclweb.org/anthology/W16-6336 | |
| PWC | https://paperswithcode.com/paper/on-why-coarse-class-classification-is |
| Repo | |
| Framework | |
Verbframator:Semi-Automatic Verb Frame Annotator Tool with Special Reference to Marathi
| Title | Verbframator:Semi-Automatic Verb Frame Annotator Tool with Special Reference to Marathi |
| Authors | Hanumant Redkar, S Singh, hya, N Ghag, ini, Jai Paranjape, Nilesh Joshi, Malhar Kulkarni, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Machine Translation, Text Generation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6337/ |
| https://www.aclweb.org/anthology/W16-6337 | |
| PWC | https://paperswithcode.com/paper/verbframatorsemi-automatic-verb-frame |
| Repo | |
| Framework | |
UMNDuluth at SemEval-2016 Task 14: WordNet’s Missing Lemmas
| Title | UMNDuluth at SemEval-2016 Task 14: WordNet’s Missing Lemmas |
| Authors | Jon Rusert, Ted Pedersen |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1211/ |
| https://www.aclweb.org/anthology/S16-1211 | |
| PWC | https://paperswithcode.com/paper/umnduluth-at-semeval-2016-task-14-wordnets |
| Repo | |
| Framework | |
