Paper Group NANR 88
Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media. Verb Replacer: An English Verb Error Correction System. Investigating Diatopic Variation in a Historical Corpus. A simple model of recognition and recall memory. Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework. …
Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media
| Title | Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1100/ |
| https://www.aclweb.org/anthology/W17-1100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fifth-international |
| Repo | |
| Framework | |
Verb Replacer: An English Verb Error Correction System
| Title | Verb Replacer: An English Verb Error Correction System |
| Authors | Yu-Hsuan Wu, Jhih-Jie Chen, Jason Chang |
| Abstract | According to the analysis of Cambridge Learner Corpus, using a wrong verb is the most common type of grammatical errors. This paper describes Verb Replacer, a system for detecting and correcting potential verb errors in a given sentence. In our approach, alternative verbs are considered to replace the verb based on an error-annotated corpus and verb-object collocations. The method involves applying regression on channel models, parsing the sentence, identifying the verbs, retrieving a small set of alternative verbs, and evaluating each alternative. Our method combines and improves channel and language models, resulting in high recall of detecting and correcting verb misuse. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3013/ |
| https://www.aclweb.org/anthology/I17-3013 | |
| PWC | https://paperswithcode.com/paper/verb-replacer-an-english-verb-error |
| Repo | |
| Framework | |
Investigating Diatopic Variation in a Historical Corpus
| Title | Investigating Diatopic Variation in a Historical Corpus |
| Authors | Stefanie Dipper, S Waldenberger, ra |
| Abstract | This paper investigates diatopic variation in a historical corpus of German. Based on equivalent word forms from different language areas, replacement rules and mappings are derived which describe the relations between these word forms. These rules and mappings are then interpreted as reflections of morphological, phonological or graphemic variation. Based on sample rules and mappings, we show that our approach can replicate results from historical linguistics. While previous studies were restricted to predefined word lists, or confined to single authors or texts, our approach uses a much wider range of data available in historical corpora. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1204/ |
| https://www.aclweb.org/anthology/W17-1204 | |
| PWC | https://paperswithcode.com/paper/investigating-diatopic-variation-in-a |
| Repo | |
| Framework | |
A simple model of recognition and recall memory
| Title | A simple model of recognition and recall memory |
| Authors | Nisheeth Srivastava, Edward Vul |
| Abstract | We show that several striking differences in memory performance between recognition and recall tasks are explained by an ecological bias endemic in classic memory experiments - that such experiments universally involve more stimuli than retrieval cues. We show that while it is sensible to think of recall as simply retrieving items when probed with a cue - typically the item list itself - it is better to think of recognition as retrieving cues when probed with items. To test this theory, by manipulating the number of items and cues in a memory experiment, we show a crossover effect in memory performance within subjects such that recognition performance is superior to recall performance when the number of items is greater than the number of cues and recall performance is better than recognition when the converse holds. We build a simple computational model around this theory, using sampling to approximate an ideal Bayesian observer encoding and retrieving situational co-occurrence frequencies of stimuli and retrieval cues. This model robustly reproduces a number of dissociations in recognition and recall previously used to argue for dual-process accounts of declarative memory. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6633-a-simple-model-of-recognition-and-recall-memory |
| http://papers.nips.cc/paper/6633-a-simple-model-of-recognition-and-recall-memory.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-model-of-recognition-and-recall |
| Repo | |
| Framework | |
Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework
| Title | Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework |
| Authors | Aaron Steven White, Pushpendre Rastogi, Kevin Duh, Benjamin Van Durme |
| Abstract | We propose to unify a variety of existing semantic classification tasks, such as semantic role labeling, anaphora resolution, and paraphrase detection, under the heading of Recognizing Textual Entailment (RTE). We present a general strategy to automatically generate one or more sentential hypotheses based on an input sentence and pre-existing manual semantic annotations. The resulting suite of datasets enables us to probe a statistical RTE model{'}s performance on different aspects of semantics. We demonstrate the value of this approach by investigating the behavior of a popular neural network RTE model. |
| Tasks | Image Captioning, Natural Language Inference, Semantic Role Labeling |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1100/ |
| https://www.aclweb.org/anthology/I17-1100 | |
| PWC | https://paperswithcode.com/paper/inference-is-everything-recasting-semantic |
| Repo | |
| Framework | |
Towards Debate Automation: a Recurrent Model for Predicting Debate Winners
| Title | Towards Debate Automation: a Recurrent Model for Predicting Debate Winners |
| Authors | Peter Potash, Anna Rumshisky |
| Abstract | In this paper we introduce a practical first step towards the creation of an automated debate agent: a state-of-the-art recurrent predictive model for predicting debate winners. By having an accurate predictive model, we are able to objectively rate the quality of a statement made at a specific turn in a debate. The model is based on a recurrent neural network architecture with attention, which allows the model to effectively account for the entire debate when making its prediction. Our model achieves state-of-the-art accuracy on a dataset of debate transcripts annotated with audience favorability of the debate teams. Finally, we discuss how future work can leverage our proposed model for the creation of an automated debate agent. We accomplish this by determining the model input that will maximize audience favorability toward a given side of a debate at an arbitrary turn. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1261/ |
| https://www.aclweb.org/anthology/D17-1261 | |
| PWC | https://paperswithcode.com/paper/towards-debate-automation-a-recurrent-model |
| Repo | |
| Framework | |
ADAPT Centre Cone Team at IJCNLP-2017 Task 5: A Similarity-Based Logistic Regression Approach to Multi-choice Question Answering in an Examinations Shared Task
| Title | ADAPT Centre Cone Team at IJCNLP-2017 Task 5: A Similarity-Based Logistic Regression Approach to Multi-choice Question Answering in an Examinations Shared Task |
| Authors | Daria Dzendzik, Alberto Poncelas, Carl Vogel, Qun Liu |
| Abstract | We describe the work of a team from the ADAPT Centre in Ireland in addressing automatic answer selection for the Multi-choice Question Answering in Examinations shared task. The system is based on a logistic regression over the string similarities between question, answer, and additional text. We obtain the highest grade out of six systems: 48.7{%} accuracy on a validation set (vs. a baseline of 29.45{%}) and 45.6{%} on a test set. |
| Tasks | Answer Selection, Question Answering |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4010/ |
| https://www.aclweb.org/anthology/I17-4010 | |
| PWC | https://paperswithcode.com/paper/adapt-centre-cone-team-at-ijcnlp-2017-task-5 |
| Repo | |
| Framework | |
Conjunctive Categorial Grammars
| Title | Conjunctive Categorial Grammars |
| Authors | Stepan Kuznetsov, Alex Okhotin, er |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3414/ |
| https://www.aclweb.org/anthology/W17-3414 | |
| PWC | https://paperswithcode.com/paper/conjunctive-categorial-grammars |
| Repo | |
| Framework | |
DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison
| Title | DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison |
| Authors | Christos Baziotis, Nikos Pelekis, Christos Doulkeridis |
| Abstract | In this paper we present a deep-learning system that competed at SemEval-2017 Task 6 ‘'{#}HashtagWars: Learning a Sense of Humor{''}. We participated in Subtask A, in which the goal was, given two Twitter messages, to identify which one is funnier. We propose a Siamese architecture with bidirectional Long Short-Term Memory (LSTM) networks, augmented with an attention mechanism. Our system works on the token-level, leveraging word embeddings trained on a big collection of unlabeled Twitter messages. We ranked 2nd in 7 teams. A post-completion improvement of our model, achieves state-of-the-art results on {#}HashtagWars dataset. |
| Tasks | Feature Engineering, Humor Detection, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2065/ |
| https://www.aclweb.org/anthology/S17-2065 | |
| PWC | https://paperswithcode.com/paper/datastories-at-semeval-2017-task-6-siamese |
| Repo | |
| Framework | |
Adullam at SemEval-2017 Task 4: Sentiment Analyzer Using Lexicon Integrated Convolutional Neural Networks with Attention
| Title | Adullam at SemEval-2017 Task 4: Sentiment Analyzer Using Lexicon Integrated Convolutional Neural Networks with Attention |
| Authors | Joosung Yoon, Kigon Lyu, Hyeoncheol Kim |
| Abstract | We propose a sentiment analyzer for the prediction of document-level sentiments of English micro-blog messages from Twitter. The proposed method is based on lexicon integrated convolutional neural networks with attention (LCA). Its performance was evaluated using the datasets provided by SemEval competition (Task 4). The proposed sentiment analyzer obtained an average F1 of 55.2{%}, an average recall of 58.9{%} and an accuracy of 61.4{%}. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2123/ |
| https://www.aclweb.org/anthology/S17-2123 | |
| PWC | https://paperswithcode.com/paper/adullam-at-semeval-2017-task-4-sentiment |
| Repo | |
| Framework | |
Word-Context Character Embeddings for Chinese Word Segmentation
| Title | Word-Context Character Embeddings for Chinese Word Segmentation |
| Authors | Hao Zhou, Zhenting Yu, Yue Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen |
| Abstract | Neural parsers have benefited from automatically labeled data via dependency-context word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method improves state-of-the-art neural word segmentation models significantly, beating tri-training baselines for leveraging auto-segmented data. |
| Tasks | Chinese Word Segmentation, Domain Adaptation, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1079/ |
| https://www.aclweb.org/anthology/D17-1079 | |
| PWC | https://paperswithcode.com/paper/word-context-character-embeddings-for-chinese |
| Repo | |
| Framework | |
Lexical Disambiguation of Igbo using Diacritic Restoration
| Title | Lexical Disambiguation of Igbo using Diacritic Restoration |
| Authors | Ignatius Ezeani, Mark Hepple, Ikechukwu Onyenwe |
| Abstract | Properly written texts in Igbo, a low-resource African language, are rich in both orthographic and tonal diacritics. Diacritics are essential in capturing the distinctions in pronunciation and meaning of words, as well as in lexical disambiguation. Unfortunately, most electronic texts in diacritic languages are written without diacritics. This makes diacritic restoration a necessary step in corpus building and language processing tasks for languages with diacritics. In our previous work, we built some n-gram models with simple smoothing techniques based on a closed-world assumption. However, as a classification task, diacritic restoration is well suited for and will be more generalisable with machine learning. This paper, therefore, presents a more standard approach to dealing with the task which involves the application of machine learning algorithms. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1907/ |
| https://www.aclweb.org/anthology/W17-1907 | |
| PWC | https://paperswithcode.com/paper/lexical-disambiguation-of-igbo-using |
| Repo | |
| Framework | |
RTM at SemEval-2017 Task 1: Referential Translation Machines for Predicting Semantic Similarity
| Title | RTM at SemEval-2017 Task 1: Referential Translation Machines for Predicting Semantic Similarity |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | We use referential translation machines for predicting the semantic similarity of text in all STS tasks which contain Arabic, English, Spanish, and Turkish this year. RTMs pioneer a language independent approach to semantic similarity and remove the need to access any task or domain specific information or resource. RTMs become 6th out of 52 submissions in Spanish to English STS. We average prediction scores using weights based on the training performance to improve the overall performance. |
| Tasks | Feature Selection, Machine Translation, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2030/ |
| https://www.aclweb.org/anthology/S17-2030 | |
| PWC | https://paperswithcode.com/paper/rtm-at-semeval-2017-task-1-referential |
| Repo | |
| Framework | |
Ensemble Methods for Native Language Identification
| Title | Ensemble Methods for Native Language Identification |
| Authors | Sophia Chan, Maryam Honari Jahromi, Benjamin Benetti, Aazim Lakhani, Alona Fyshe |
| Abstract | Our team{—}Uvic-NLP{—}explored and evaluated a variety of lexical features for Native Language Identification (NLI) within the framework of ensemble methods. Using a subset of the highest performing features, we train Support Vector Machines (SVM) and Fully Connected Neural Networks (FCNN) as base classifiers, and test different methods for combining their outputs. Restricting our scope to the closed essay track in the NLI Shared Task 2017, we find that our best SVM ensemble achieves an F1 score of 0.8730 on the test set. |
| Tasks | Language Acquisition, Language Identification, Native Language Identification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5023/ |
| https://www.aclweb.org/anthology/W17-5023 | |
| PWC | https://paperswithcode.com/paper/ensemble-methods-for-native-language |
| Repo | |
| Framework | |
Coarticulatory propensity in Khalkha Mongolian
| Title | Coarticulatory propensity in Khalkha Mongolian |
| Authors | Ushashi Banerjee, Indranil Dutta, Irfan S |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7544/ |
| https://www.aclweb.org/anthology/W17-7544 | |
| PWC | https://paperswithcode.com/paper/coarticulatory-propensity-in-khalkha |
| Repo | |
| Framework | |
