Paper Group NANR 43
Modeling Context-sensitive Selectional Preference with Distributed Representations. Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts. SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task. A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations. Persian Proposition Bank. …
Modeling Context-sensitive Selectional Preference with Distributed Representations
| Title | Modeling Context-sensitive Selectional Preference with Distributed Representations |
| Authors | Naoya Inoue, Yuichiroh Matsubayashi, Masayuki Ono, Naoaki Okazaki, Kentaro Inui |
| Abstract | This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP). CSP models the narrative consistency between the predicate and preceding contexts of its arguments, in addition to the conventional SP based on semantic types. Furthermore, we present a novel CSP model that extends the neural SP model (Van de Cruys, 2014) to incorporate contextual information into the distributed representations of arguments. Experimental results demonstrate that the proposed CSP model successfully learns CSP and outperforms the conventional SP model in coreference cluster ranking. |
| Tasks | Semantic Role Labeling |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1266/ |
| https://www.aclweb.org/anthology/C16-1266 | |
| PWC | https://paperswithcode.com/paper/modeling-context-sensitive-selectional |
| Repo | |
| Framework | |
Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts
| Title | Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts |
| Authors | Jun Araki, Dheeraj Rajagopal, Sreecharan Sankaranarayanan, Susan Holm, Yukari Yamakawa, Teruko Mitamura |
| Abstract | We present a novel approach to automated question generation that improves upon prior work both from a technology perspective and from an assessment perspective. Our system is aimed at engaging language learners by generating multiple-choice questions which utilize specific inference steps over multiple sentences, namely coreference resolution and paraphrase detection. The system also generates correct answers and semantically-motivated phrase-level distractors as answer choices. Evaluation by human annotators indicates that our approach requires a larger number of inference steps, which necessitate deeper semantic understanding of texts than a traditional single-sentence approach. |
| Tasks | Coreference Resolution, Question Generation, Reading Comprehension |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1107/ |
| https://www.aclweb.org/anthology/C16-1107 | |
| PWC | https://paperswithcode.com/paper/generating-questions-and-multiple-choice |
| Repo | |
| Framework | |
SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task
| Title | SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task |
| Authors | Rosa Gaudio, Gorka Labaka, Eneko Agirre, Petya Osenova, Kiril Simov, Martin Popel, Dieke Oele, Gertjan van Noord, Lu{'\i}s Gomes, Jo{~a}o Ant{'o}nio Rodrigues, Steven Neale, Jo{~a}o Silva, Andreia Querido, Nuno Rendeiro, Ant{'o}nio Branco |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2332/ |
| https://www.aclweb.org/anthology/W16-2332 | |
| PWC | https://paperswithcode.com/paper/smt-and-hybrid-systems-of-the-qtleap-project |
| Repo | |
| Framework | |
A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations
| Title | A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations |
| Authors | Jonathon Read, Erik Velldal, Marc Cavazza, Gersende Georg |
| Abstract | In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations. Recommendations are labelled with an author-provided indicator of their strength of importance. As data was drawn from many disparate authors, we define a unified scheme of importance labels, and provide a mapping for each guideline. We demonstrate the utility of the corpus and its annotations in some initial measurements investigating the type of language constructions associated with strong and weak recommendations, and experiments into promising features for recommendation classification, both with respect to strong and weak labels, and to all labels of the unified scheme. An error analysis indicates that, while there is a strong relationship between lexical choices and strength labels, there can be substantial variance in the choices made by different authors. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1272/ |
| https://www.aclweb.org/anthology/L16-1272 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-clinical-practice-guidelines |
| Repo | |
| Framework | |
Persian Proposition Bank
| Title | Persian Proposition Bank |
| Authors | Azadeh Mirzaei, Amirsaeid Moloodi |
| Abstract | This paper describes the procedure of semantic role labeling and the development of the first manually annotated Persian Proposition Bank (PerPB) which added a layer of predicate-argument information to the syntactic structures of Persian Dependency Treebank (known as PerDT). Through the process of annotating, the annotators could see the syntactic information of all the sentences and so they annotated 29982 sentences with more than 9200 unique verbs. In the annotation procedure, the direct syntactic dependents of the verbs were the first candidates for being annotated. So we did not annotate the other indirect dependents unless their phrasal heads were propositional and had their own arguments or adjuncts. Hence besides the semantic role labeling of verbs, the argument structure of 1300 unique propositional nouns and 300 unique propositional adjectives were annotated in the sentences, too. The accuracy of annotation process was measured by double annotation of the data at two separate stages and finally the data was prepared in the CoNLL dependency format. |
| Tasks | Semantic Role Labeling |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1606/ |
| https://www.aclweb.org/anthology/L16-1606 | |
| PWC | https://paperswithcode.com/paper/persian-proposition-bank |
| Repo | |
| Framework | |
Weak Semi-Markov CRFs for Noun Phrase Chunking in Informal Text
| Title | Weak Semi-Markov CRFs for Noun Phrase Chunking in Informal Text |
| Authors | Aldrian Obaja Muis, Wei Lu |
| Abstract | |
| Tasks | Chunking |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1085/ |
| https://www.aclweb.org/anthology/N16-1085 | |
| PWC | https://paperswithcode.com/paper/weak-semi-markov-crfs-for-noun-phrase |
| Repo | |
| Framework | |
Searching in the Penn Discourse Treebank Using the PML-Tree Query
| Title | Searching in the Penn Discourse Treebank Using the PML-Tree Query |
| Authors | Ji{\v{r}}{'\i} M{'\i}rovsk{'y}, Lucie Pol{'a}kov{'a}, Jan {\v{S}}t{\v{e}}p{'a}nek |
| Abstract | The PML-Tree Query is a general, powerful and user-friendly system for querying richly linguistically annotated treebanks. The paper shows how the PML-Tree Query can be used for searching for discourse relations in the Penn Discourse Treebank 2.0 mapped onto the syntactic annotation of the Penn Treebank. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1278/ |
| https://www.aclweb.org/anthology/L16-1278 | |
| PWC | https://paperswithcode.com/paper/searching-in-the-penn-discourse-treebank |
| Repo | |
| Framework | |
PIC a Different Word: A Simple Model for Lexical Substitution in Context
| Title | PIC a Different Word: A Simple Model for Lexical Substitution in Context |
| Authors | Stephen Roller, Katrin Erk |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1131/ |
| https://www.aclweb.org/anthology/N16-1131 | |
| PWC | https://paperswithcode.com/paper/pic-a-different-word-a-simple-model-for |
| Repo | |
| Framework | |
Modeling the Non-Substitutability of Multiword Expressions with Distributional Semantics and a Log-Linear Model
| Title | Modeling the Non-Substitutability of Multiword Expressions with Distributional Semantics and a Log-Linear Model |
| Authors | Meghdad Farahmand, James Henderson |
| Abstract | |
| Tasks | Language Acquisition, Machine Translation, Opinion Mining, Text Generation, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W16-1809/w16-1809 |
| https://www.aclweb.org/anthology/W16-1809 | |
| PWC | https://paperswithcode.com/paper/modeling-the-non-substitutability-of |
| Repo | |
| Framework | |
RTM at SemEval-2016 Task 1: Predicting Semantic Similarity with Referential Translation Machines and Related Statistics
| Title | RTM at SemEval-2016 Task 1: Predicting Semantic Similarity with Referential Translation Machines and Related Statistics |
| Authors | Ergun Bicici |
| Abstract | |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/papers/S16-1117/s16-1117 |
| https://www.aclweb.org/anthology/S16-1117v2 | |
| PWC | https://paperswithcode.com/paper/rtm-at-semeval-2016-task-1-predicting |
| Repo | |
| Framework | |
IUCL at SemEval-2016 Task 6: An Ensemble Model for Stance Detection in Twitter
| Title | IUCL at SemEval-2016 Task 6: An Ensemble Model for Stance Detection in Twitter |
| Authors | Can Liu, Wen Li, Bradford Demarest, Yue Chen, Sara Couture, Daniel Dakota, Nikita Haduong, Noah Kaufman, Andrew Lamont, Manan Pancholi, Kenneth Steimel, S K{"u}bler, ra |
| Abstract | |
| Tasks | Sentiment Analysis, Stance Detection, Tokenization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1064/ |
| https://www.aclweb.org/anthology/S16-1064 | |
| PWC | https://paperswithcode.com/paper/iucl-at-semeval-2016-task-6-an-ensemble-model |
| Repo | |
| Framework | |
UWB at SemEval-2016 Task 6: Stance Detection
| Title | UWB at SemEval-2016 Task 6: Stance Detection |
| Authors | Peter Krejzl, Josef Steinberger |
| Abstract | |
| Tasks | Natural Language Inference, Opinion Mining, Sentiment Analysis, Stance Detection, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1066/ |
| https://www.aclweb.org/anthology/S16-1066 | |
| PWC | https://paperswithcode.com/paper/uwb-at-semeval-2016-task-6-stance-detection |
| Repo | |
| Framework | |
CU-GWU Perspective at SemEval-2016 Task 6: Ideological Stance Detection in Informal Text
| Title | CU-GWU Perspective at SemEval-2016 Task 6: Ideological Stance Detection in Informal Text |
| Authors | Heba Elfardy, Mona Diab |
| Abstract | |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1070/ |
| https://www.aclweb.org/anthology/S16-1070 | |
| PWC | https://paperswithcode.com/paper/cu-gwu-perspective-at-semeval-2016-task-6 |
| Repo | |
| Framework | |
The ACQDIV Database: Min(d)ing the Ambient Language
| Title | The ACQDIV Database: Min(d)ing the Ambient Language |
| Authors | Steven Moran |
| Abstract | One of the most pressing questions in cognitive science remains unanswered: what cognitive mechanisms enable children to learn any of the world{'}s 7000 or so languages? Much discovery has been made with regard to specific learning mechanisms in specific languages, however, given the remarkable diversity of language structures (Evans and Levinson 2009, Bickel 2014) the burning question remains: what are the underlying processes that make language acquisition possible, despite substantial cross-linguistic variation in phonology, morphology, syntax, etc.? To investigate these questions, a comprehensive cross-linguistic database of longitudinal child language acquisition corpora from maximally diverse languages has been built. |
| Tasks | Language Acquisition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1700/ |
| https://www.aclweb.org/anthology/L16-1700 | |
| PWC | https://paperswithcode.com/paper/the-acqdiv-database-minding-the-ambient |
| Repo | |
| Framework | |
Large-scale Multi-class and Hierarchical Product Categorization for an E-commerce Giant
| Title | Large-scale Multi-class and Hierarchical Product Categorization for an E-commerce Giant |
| Authors | Ali Cevahir, Koji Murakami |
| Abstract | In order to organize the large number of products listed in e-commerce sites, each product is usually assigned to one of the multi-level categories in the taxonomy tree. It is a time-consuming and difficult task for merchants to select proper categories within thousands of options for the products they sell. In this work, we propose an automatic classification tool to predict the matching category for a given product title and description. We used a combination of two different neural models, i.e., deep belief nets and deep autoencoders, for both titles and descriptions. We implemented a selective reconstruction approach for the input layer during the training of the deep neural networks, in order to scale-out for large-sized sparse feature vectors. GPUs are utilized in order to train neural networks in a reasonable time. We have trained our models for around 150 million products with a taxonomy tree with at most 5 levels that contains 28,338 leaf categories. Tests with millions of products show that our first predictions matches 81{%} of merchants{'} assignments, when {``}others{''} categories are excluded. | |
| Tasks | Product Categorization, Text Classification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1051/ |
| https://www.aclweb.org/anthology/C16-1051 | |
| PWC | https://paperswithcode.com/paper/large-scale-multi-class-and-hierarchical |
| Repo | |
| Framework | |
