Paper Group NANR 189
Mapping the Paraphrase Database to WordNet. Semantic Frame Labeling with Target-based Neural Model. 基於卷積類神經網路之廣播節目音訊事件偵測系統 (Automatic Audio Event Detection of Broadcast Radio Programs Based on Convolution Neural Networks) [In Chinese]. Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible. Autobank: a semi-au …
Mapping the Paraphrase Database to WordNet
| Title | Mapping the Paraphrase Database to WordNet |
| Authors | Anne Cocos, Marianna Apidianaki, Chris Callison-Burch |
| Abstract | WordNet has facilitated important research in natural language processing but its usefulness is somewhat limited by its relatively small lexical coverage. The Paraphrase Database (PPDB) covers 650 times more words, but lacks the semantic structure of WordNet that would make it more directly useful for downstream tasks. We present a method for mapping words from PPDB to WordNet synsets with 89{%} accuracy. The mapping also lays important groundwork for incorporating WordNet{'}s relations into PPDB so as to increase its utility for semantic reasoning in applications. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1009/ |
| https://www.aclweb.org/anthology/S17-1009 | |
| PWC | https://paperswithcode.com/paper/mapping-the-paraphrase-database-to-wordnet |
| Repo | |
| Framework | |
Semantic Frame Labeling with Target-based Neural Model
| Title | Semantic Frame Labeling with Target-based Neural Model |
| Authors | Yukun Feng, Dong Yu, Jian Xu, Chunhua Liu |
| Abstract | This paper explores the automatic learning of distributed representations of the target{'}s context for semantic frame labeling with target-based neural model. We constrain the whole sentence as the model{'}s input without feature extraction from the sentence. This is different from many previous works in which local feature extraction of the targets is widely used. This constraint makes the task harder, especially with long sentences, but also makes our model easily applicable to a range of resources and other similar tasks. We evaluate our model on several resources and get the state-of-the-art result on subtask 2 of SemEval 2015 task 15. Finally, we extend the task to word-sense disambiguation task and we also achieve a strong result in comparison to state-of-the-art work. |
| Tasks | Feature Engineering, Word Embeddings, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1010/ |
| https://www.aclweb.org/anthology/S17-1010 | |
| PWC | https://paperswithcode.com/paper/semantic-frame-labeling-with-target-based |
| Repo | |
| Framework | |
基於卷積類神經網路之廣播節目音訊事件偵測系統 (Automatic Audio Event Detection of Broadcast Radio Programs Based on Convolution Neural Networks) [In Chinese]
| Title | 基於卷積類神經網路之廣播節目音訊事件偵測系統 (Automatic Audio Event Detection of Broadcast Radio Programs Based on Convolution Neural Networks) [In Chinese] |
| Authors | Jhih-wei Chen, Wu-Hua Hsu, Yuan-Fu Liao |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1003/ |
| https://www.aclweb.org/anthology/O17-1003 | |
| PWC | https://paperswithcode.com/paper/ao14aceccc2e-a1ac-ce3e-aoaa-c3c-automatic |
| Repo | |
| Framework | |
Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible
| Title | Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible |
| Authors | Abhijeet Gupta, Gemma Boleda, Sebastian Pad{'o} |
| Abstract | Word embeddings are supposed to provide easy access to semantic relations such as {``}male of{''} (man{–}woman). While this claim has been investigated for concepts, little is known about the distributional behavior of relations of (Named) Entities. We describe two word embedding-based models that predict values for relational attributes of entities, and analyse them. The task is challenging, with major performance differences between relations. Contrary to many NLP tasks, high difficulty for a relation does not result from low frequency, but from (a) one-to-many mappings; and (b) lack of context patterns expressing the relation that are easy to pick up by word embeddings. | |
| Tasks | Knowledge Base Completion, Relation Extraction, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1012/ |
| https://www.aclweb.org/anthology/S17-1012 | |
| PWC | https://paperswithcode.com/paper/distributed-prediction-of-relations-for |
| Repo | |
| Framework | |
Autobank: a semi-automatic annotation tool for developing deep Minimalist Grammar treebanks
| Title | Autobank: a semi-automatic annotation tool for developing deep Minimalist Grammar treebanks |
| Authors | John Torr |
| Abstract | This paper presents Autobank, a prototype tool for constructing a wide-coverage Minimalist Grammar (MG) (Stabler 1997), and semi-automatically converting the Penn Treebank (PTB) into a deep Minimalist treebank. The front end of the tool is a graphical user interface which facilitates the rapid development of a seed set of MG trees via manual reannotation of PTB preterminals with MG lexical categories. The system then extracts various dependency mappings between the source and target trees, and uses these in concert with a non-statistical MG parser to automatically reannotate the rest of the corpus. Autobank thus enables deep treebank conversions (and subsequent modifications) without the need for complex transduction algorithms accompanied by cascades of ad hoc rules; instead, the locus of human effort falls directly on the task of grammar construction itself. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3021/ |
| https://www.aclweb.org/anthology/E17-3021 | |
| PWC | https://paperswithcode.com/paper/autobank-a-semi-automatic-annotation-tool-for |
| Repo | |
| Framework | |
The (too Many) Problems of Analogical Reasoning with Word Vectors
| Title | The (too Many) Problems of Analogical Reasoning with Word Vectors |
| Authors | Anna Rogers, Aleks Drozd, r, Bofang Li |
| Abstract | This paper explores the possibilities of analogical reasoning with vector space models. Given two pairs of words with the same relation (e.g. man:woman :: king:queen), it was proposed that the offset between one pair of the corresponding word vectors can be used to identify the unknown member of the other pair (king - man + woman = queen). We argue against such {``}linguistic regularities{''} as a model for linguistic relations in vector space models and as a benchmark, and we show that the vector offset (as well as two other, better-performing methods) suffers from dependence on vector similarity. | |
| Tasks | Word Embeddings, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1017/ |
| https://www.aclweb.org/anthology/S17-1017 | |
| PWC | https://paperswithcode.com/paper/the-too-many-problems-of-analogical-reasoning |
| Repo | |
| Framework | |
Semantic Frames and Visual Scenes: Learning Semantic Role Inventories from Image and Video Descriptions
| Title | Semantic Frames and Visual Scenes: Learning Semantic Role Inventories from Image and Video Descriptions |
| Authors | Ekaterina Shutova, Andreas Wundsam, Helen Yannakoudakis |
| Abstract | Frame-semantic parsing and semantic role labelling, that aim to automatically assign semantic roles to arguments of verbs in a sentence, have become an active strand of research in NLP. However, to date these methods have relied on a predefined inventory of semantic roles. In this paper, we present a method to automatically learn argument role inventories for verbs from large corpora of text, images and videos. We evaluate the method against manually constructed role inventories in FrameNet and show that the visual model outperforms the language-only model and operates with a high precision. |
| Tasks | Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1018/ |
| https://www.aclweb.org/anthology/S17-1018 | |
| PWC | https://paperswithcode.com/paper/semantic-frames-and-visual-scenes-learning |
| Repo | |
| Framework | |
Logical Metonymy in a Distributional Model of Sentence Comprehension
| Title | Logical Metonymy in a Distributional Model of Sentence Comprehension |
| Authors | Emmanuele Chersoni, Aless Lenci, ro, Philippe Blache |
| Abstract | In theoretical linguistics, logical metonymy is defined as the combination of an event-subcategorizing verb with an entity-denoting direct object (e.g., The author began the book), so that the interpretation of the VP requires the retrieval of a covert event (e.g., writing). Psycholinguistic studies have revealed extra processing costs for logical metonymy, a phenomenon generally explained with the introduction of new semantic structure. In this paper, we present a general distributional model for sentence comprehension inspired by the Memory, Unification and Control model by Hagoort (2013,2016). We show that our distributional framework can account for the extra processing costs of logical metonymy and can identify the covert event in a classification task. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1021/ |
| https://www.aclweb.org/anthology/S17-1021 | |
| PWC | https://paperswithcode.com/paper/logical-metonymy-in-a-distributional-model-of |
| Repo | |
| Framework | |
Liner2 — a Generic Framework for Named Entity Recognition
| Title | Liner2 — a Generic Framework for Named Entity Recognition |
| Authors | Micha{\l} Marci{'n}czuk, Jan Koco{'n}, Marcin Oleksy |
| Abstract | In the paper we present an adaptation of Liner2 framework to solve the BSNLP 2017 shared task on multilingual named entity recognition. The tool is tuned to recognize and lemmatize named entities for Polish. |
| Tasks | Morphological Analysis, Named Entity Recognition, Tokenization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1413/ |
| https://www.aclweb.org/anthology/W17-1413 | |
| PWC | https://paperswithcode.com/paper/liner2-a-a-generic-framework-for-named-entity |
| Repo | |
| Framework | |
Identifying Semantically Deviating Outlier Documents
| Title | Identifying Semantically Deviating Outlier Documents |
| Authors | Honglei Zhuang, Chi Wang, Fangbo Tao, Lance Kaplan, Jiawei Han |
| Abstract | A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus. Automatic identification of document outliers can be valuable in many applications, such as screening health records for medical mistakes. In this paper, we study the problem of mining semantically deviating document outliers in a given corpus. We develop a generative model to identify frequent and characteristic semantic regions in the word embedding space to represent the given corpus, and a robust outlierness measure which is resistant to noisy content in documents. Experiments conducted on two real-world textual data sets show that our method can achieve an up to 135{%} improvement over baselines in terms of recall at top-1{%} of the outlier ranking. |
| Tasks | Outlier Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1291/ |
| https://www.aclweb.org/anthology/D17-1291 | |
| PWC | https://paperswithcode.com/paper/identifying-semantically-deviating-outlier |
| Repo | |
| Framework | |
以語音能量特性發展即時語速偵測裝置-前導型研究 (Real-time monitoring device of phonation speed and volume based on speech energy: A pilot study) [In Chinese]
| Title | 以語音能量特性發展即時語速偵測裝置-前導型研究 (Real-time monitoring device of phonation speed and volume based on speech energy: A pilot study) [In Chinese] |
| Authors | Chi-Te Wang, Feng-Chuan Lin, Wei-Zhung Zheng, Shih-Hau Fang, Yu Tsao, Ying-Hui Lai |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1027/ |
| https://www.aclweb.org/anthology/O17-1027 | |
| PWC | https://paperswithcode.com/paper/aeae3e12ec1c14aa3eaea-ec12-aaac-c-real-time |
| Repo | |
| Framework | |
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity
| Title | SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity |
| Authors | Jose Camacho-Collados, Mohammad Taher Pilehvar, Nigel Collier, Roberto Navigli |
| Abstract | This paper introduces a new task on Multilingual and Cross-lingual SemanticThis paper introduces a new task on Multilingual and Cross-lingual Semantic Word Similarity which measures the semantic similarity of word pairs within and across five languages: English, Farsi, German, Italian and Spanish. High quality datasets were manually curated for the five languages with high inter-annotator agreements (consistently in the 0.9 ballpark). These were used for semi-automatic construction of ten cross-lingual datasets. 17 teams participated in the task, submitting 24 systems in subtask 1 and 14 systems in subtask 2. Results show that systems that combine statistical knowledge from text corpora, in the form of word embeddings, and external knowledge from lexical resources are best performers in both subtasks. More information can be found on the task website: \url{http://alt.qcri.org/semeval2017/task2/} |
| Tasks | Information Retrieval, Machine Translation, Question Answering, Representation Learning, Semantic Similarity, Semantic Textual Similarity, Text Summarization, Word Embeddings, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2002/ |
| https://www.aclweb.org/anthology/S17-2002 | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-2-multilingual-and-cross |
| Repo | |
| Framework | |
Identifying the Authors’ National Variety of English in Social Media Texts
| Title | Identifying the Authors’ National Variety of English in Social Media Texts |
| Authors | Vasiliki Simaki, Panagiotis Simakis, Carita Paradis, Andreas Kerren |
| Abstract | In this paper, we present a study for the identification of authors{'} national variety of English in texts from social media. In data from Facebook and Twitter, information about the author{'}s social profile is annotated, and the national English variety (US, UK, AUS, CAN, NNS) that each author uses is attributed. We tested four feature types: formal linguistic features, POS features, lexicon-based features related to the different varieties, and data-based features from each English variety. We used various machine learning algorithms for the classification experiments, and we implemented a feature selection process. The classification accuracy achieved, when the 31 highest ranked features were used, was up to 77.32{%}. The experimental results are evaluated, and the efficacy of the ranked features discussed. |
| Tasks | Feature Selection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1086/ |
| https://doi.org/10.26615/978-954-452-049-6_086 | |
| PWC | https://paperswithcode.com/paper/identifying-the-authors-national-variety-of |
| Repo | |
| Framework | |
FCICU at SemEval-2017 Task 1: Sense-Based Language Independent Semantic Textual Similarity Approach
| Title | FCICU at SemEval-2017 Task 1: Sense-Based Language Independent Semantic Textual Similarity Approach |
| Authors | Basma Hassan, Samir AbdelRahman, Reem Bahgat, Ibrahim Farag |
| Abstract | This paper describes FCICU team systems that participated in SemEval-2017 Semantic Textual Similarity task (Task1) for monolingual and cross-lingual sentence pairs. A sense-based language independent textual similarity approach is presented, in which a proposed alignment similarity method coupled with new usage of a semantic network (BabelNet) is used. Additionally, a previously proposed integration between sense-based and sur-face-based semantic textual similarity approach is applied together with our proposed approach. For all the tracks in Task1, Run1 is a string kernel with alignments metric and Run2 is a sense-based alignment similarity method. The first run is ranked 10th, and the second is ranked 12th in the primary track, with correlation 0.619 and 0.617 respectively |
| Tasks | Machine Translation, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2015/ |
| https://www.aclweb.org/anthology/S17-2015 | |
| PWC | https://paperswithcode.com/paper/fcicu-at-semeval-2017-task-1-sense-based |
| Repo | |
| Framework | |
What is it? Disambiguating the different readings of the pronoun `it’
| Title | What is it? Disambiguating the different readings of the pronoun `it’ | |
| Authors | Sharid Lo{'a}iciga, Liane Guillou, Christian Hardmeier |
| Abstract | In this paper, we address the problem of predicting one of three functions for the English pronoun {`}it{'}: anaphoric, event reference or pleonastic. This disambiguation is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models. | |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1137/ |
| https://www.aclweb.org/anthology/D17-1137 | |
| PWC | https://paperswithcode.com/paper/what-is-it-disambiguating-the-different |
| Repo | |
| Framework | |
