Paper Group NANR 2
IIIT-H at IJCNLP-2017 Task 3: A Bidirectional-LSTM Approach for Review Opinion Diversification. Natural Language Informs the Interpretation of Iconic Gestures: A Computational Approach. Deep Learning for Semantic Composition. Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems. Para …
IIIT-H at IJCNLP-2017 Task 3: A Bidirectional-LSTM Approach for Review Opinion Diversification
| Title | IIIT-H at IJCNLP-2017 Task 3: A Bidirectional-LSTM Approach for Review Opinion Diversification |
| Authors | Pruthwik Mishra, D, Prathyusha a, Silpa Kanneganti, Soujanya Lanka |
| Abstract | The Review Opinion Diversification (Revopid-2017) shared task focuses on selecting top-k reviews from a set of reviews for a particular product based on a specific criteria. In this paper, we describe our approaches and results for modeling the ranking of reviews based on their usefulness score, this being the first of the three subtasks under this shared task. Instead of posing this as a regression problem, we modeled this as a classification task where we want to identify whether a review is useful or not. We employed a bi-directional LSTM to represent each review and is used with a softmax layer to predict the usefulness score. We chose the review with highest usefulness score, then find its cosine similarity score with rest of the reviews. This is done in order to ensure diversity in the selection of top-k reviews. On the top-5 list prediction, we finished 3rd while in top-10 list one, we are placed 2nd in the shared task. We have discussed the model and the results in detail in the paper. |
| Tasks | Decision Making |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4008/ |
| https://www.aclweb.org/anthology/I17-4008 | |
| PWC | https://paperswithcode.com/paper/iiit-h-at-ijcnlp-2017-task-3-a-bidirectional |
| Repo | |
| Framework | |
Natural Language Informs the Interpretation of Iconic Gestures: A Computational Approach
| Title | Natural Language Informs the Interpretation of Iconic Gestures: A Computational Approach |
| Authors | Ting Han, Julian Hough, David Schlangen |
| Abstract | When giving descriptions, speakers often signify object shape or size with hand gestures. Such so-called {`}iconic{'} gestures represent their meaning through their relevance to referents in the verbal content, rather than having a conventional form. The gesture form on its own is often ambiguous, and the aspect of the referent that it highlights is constrained by what the language makes salient. We show how the verbal content guides gesture interpretation through a computational model that frames the task as a multi-label classification task that maps multimodal utterances to semantic categories, using annotated human-human data. | |
| Tasks | Multi-Label Classification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2023/ |
| https://www.aclweb.org/anthology/I17-2023 | |
| PWC | https://paperswithcode.com/paper/natural-language-informs-the-interpretation |
| Repo | |
| Framework | |
Deep Learning for Semantic Composition
| Title | Deep Learning for Semantic Composition |
| Authors | Xiaodan Zhu, Edward Grefenstette |
| Abstract | Learning representation to model the meaning of text has been a core problem in NLP. The last several years have seen extensive interests on distributional approaches, in which text spans of different granularities are encoded as vectors of numerical values. If properly learned, such representation has showed to achieve the state-of-the-art performance on a wide range of NLP problems.In this tutorial, we will cover the fundamentals and the state-of-the-art research on neural network-based modeling for semantic composition, which aims to learn distributed representation for different granularities of text, e.g., phrases, sentences, or even documents, from their sub-component meaning representation, e.g., word embedding. |
| Tasks | Semantic Composition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-5003/ |
| https://www.aclweb.org/anthology/P17-5003 | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-semantic-composition |
| Repo | |
| Framework | |
Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems
| Title | Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems |
| Authors | Hiroki Asano, Tomoya Mizumoto, Kentaro Inui |
| Abstract | In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage. To address this problem, a reference-less approach has recently emerged; however, previous reference-less metrics that only consider the criterion of grammaticality, have not worked as well as reference-based metrics. This study explores the potential of extending a prior grammaticality-based method to establish a reference-less evaluation method for GEC systems. Further, we empirically show that a reference-less metric that combines fluency and meaning preservation with grammaticality provides a better estimate of manual scores than that of commonly used reference-based metrics. To our knowledge, this is the first study that provides empirical evidence that a reference-less metric can replace reference-based metrics in evaluating GEC systems. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2058/ |
| https://www.aclweb.org/anthology/I17-2058 | |
| PWC | https://paperswithcode.com/paper/reference-based-metrics-can-be-replaced-with |
| Repo | |
| Framework | |
Parameter Free Hierarchical Graph-Based Clustering for Analyzing Continuous Word Embeddings
| Title | Parameter Free Hierarchical Graph-Based Clustering for Analyzing Continuous Word Embeddings |
| Authors | Thomas Alex Trost, er, Dietrich Klakow |
| Abstract | Word embeddings are high-dimensional vector representations of words and are thus difficult to interpret. In order to deal with this, we introduce an unsupervised parameter free method for creating a hierarchical graphical clustering of the full ensemble of word vectors and show that this structure is a geometrically meaningful representation of the original relations between the words. This newly obtained representation can be used for better understanding and thus improving the embedding algorithm and exhibits semantic meaning, so it can also be utilized in a variety of language processing tasks like categorization or measuring similarity. |
| Tasks | Dimensionality Reduction, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2404/ |
| https://www.aclweb.org/anthology/W17-2404 | |
| PWC | https://paperswithcode.com/paper/parameter-free-hierarchical-graph-based |
| Repo | |
| Framework | |
Bandits Dueling on Partially Ordered Sets
| Title | Bandits Dueling on Partially Ordered Sets |
| Authors | Julien Audiffren, Liva Ralaivola |
| Abstract | We address the problem of dueling bandits defined on partially ordered sets, or posets. In this setting, arms may not be comparable, and there may be several (incomparable) optimal arms. We propose an algorithm, UnchainedBandits, that efficiently finds the set of optimal arms, or Pareto front, of any poset even when pairs of comparable arms cannot be a priori distinguished from pairs of incomparable arms, with a set of minimal assumptions. This means that UnchainedBandits does not require information about comparability and can be used with limited knowledge of the poset. To achieve this, the algorithm relies on the concept of decoys, which stems from social psychology. We also provide theoretical guarantees on both the regret incurred and the number of comparison required by UnchainedBandits, and we report compelling empirical results. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6808-bandits-dueling-on-partially-ordered-sets |
| http://papers.nips.cc/paper/6808-bandits-dueling-on-partially-ordered-sets.pdf | |
| PWC | https://paperswithcode.com/paper/bandits-dueling-on-partially-ordered-sets |
| Repo | |
| Framework | |
High Recall Open IE for Relation Discovery
| Title | High Recall Open IE for Relation Discovery |
| Authors | Hady Elsahar, Christophe Gravier, Frederique Laforest |
| Abstract | Relation Discovery discovers predicates (relation types) from a text corpus relying on the co-occurrence of two named entities in the same sentence. This is a very narrowing constraint: it represents only a small fraction of all relation mentions in practice. In this paper we propose a high recall approach for Open IE, which enables covering up to 16 times more sentences in a large corpus. Comparison against OpenIE systems shows that our proposed approach achieves 28{%} improvement over the highest recall OpenIE system and 6{%} improvement in precision than the same system. |
| Tasks | Open Information Extraction, Relation Extraction |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2039/ |
| https://www.aclweb.org/anthology/I17-2039 | |
| PWC | https://paperswithcode.com/paper/high-recall-open-ie-for-relation-discovery |
| Repo | |
| Framework | |
Evaluating text coherence based on semantic similarity graph
| Title | Evaluating text coherence based on semantic similarity graph |
| Authors | Jan Wira Gotama Putra, Takenobu Tokunaga |
| Abstract | Coherence is a crucial feature of text because it is indispensable for conveying its communication purpose and meaning to its readers. In this paper, we propose an unsupervised text coherence scoring based on graph construction in which edges are established between semantically similar sentences represented by vertices. The sentence similarity is calculated based on the cosine similarity of semantic vectors representing sentences. We provide three graph construction methods establishing an edge from a given vertex to a preceding adjacent vertex, to a single similar vertex, or to multiple similar vertices. We evaluated our methods in the document discrimination task and the insertion task by comparing our proposed methods to the supervised (Entity Grid) and unsupervised (Entity Graph) baselines. In the document discrimination task, our method outperformed the unsupervised baseline but could not do the supervised baseline, while in the insertion task, our method outperformed both baselines. |
| Tasks | graph construction, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2410/ |
| https://www.aclweb.org/anthology/W17-2410 | |
| PWC | https://paperswithcode.com/paper/evaluating-text-coherence-based-on-semantic |
| Repo | |
| Framework | |
MappSent at IJCNLP-2017 Task 5: A Textual Similarity Approach Applied to Multi-choice Question Answering in Examinations
| Title | MappSent at IJCNLP-2017 Task 5: A Textual Similarity Approach Applied to Multi-choice Question Answering in Examinations |
| Authors | Amir Hazem |
| Abstract | In this paper we present MappSent, a textual similarity approach that we applied to the multi-choice question answering in exams shared task. MappSent has initially been proposed for question-to-question similarity hazem2017. In this work, we present the results of two adaptations of MappSent for the question answering task on the English dataset. |
| Tasks | Information Retrieval, Question Answering, Question Similarity |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4034/ |
| https://www.aclweb.org/anthology/I17-4034 | |
| PWC | https://paperswithcode.com/paper/mappsent-at-ijcnlp-2017-task-5-a-textual |
| Repo | |
| Framework | |
Investigating the Effect of Conveying Understanding Results in Chat-Oriented Dialogue Systems
| Title | Investigating the Effect of Conveying Understanding Results in Chat-Oriented Dialogue Systems |
| Authors | Koh Mitsuda, Ryuichiro Higashinaka, Junji Tomita |
| Abstract | In dialogue systems, conveying understanding results of user utterances is important because it enables users to feel understood by the system. However, it is not clear what types of understanding results should be conveyed to users; some utterances may be offensive and some may be too commonsensical. In this paper, we explored the effect of conveying understanding results of user utterances in a chat-oriented dialogue system by an experiment using human subjects. As a result, we found that only certain types of understanding results, such as those related to a user{'}s permanent state, are effective to improve user satisfaction. This paper clarifies the types of understanding results that can be safely uttered by a system. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2066/ |
| https://www.aclweb.org/anthology/I17-2066 | |
| PWC | https://paperswithcode.com/paper/investigating-the-effect-of-conveying |
| Repo | |
| Framework | |
NNEMBs at SemEval-2017 Task 4: Neural Twitter Sentiment Classification: a Simple Ensemble Method with Different Embeddings
| Title | NNEMBs at SemEval-2017 Task 4: Neural Twitter Sentiment Classification: a Simple Ensemble Method with Different Embeddings |
| Authors | Yichun Yin, Yangqiu Song, Ming Zhang |
| Abstract | Recently, neural twitter sentiment classification has become one of state-of-thearts, which relies less feature engineering work compared with traditional methods. In this paper, we propose a simple and effective ensemble method to further boost the performances of neural models. We collect several word embedding sets which are publicly released (often are learned on different corpus) or constructed by running Skip-gram on released large-scale corpus. We make an assumption that different word embeddings cover different words and encode different semantic knowledge, thus using them together can improve the generalizations and performances of neural models. In the SemEval 2017, our method ranks 1st in Accuracy, 5th in AverageR. Meanwhile, the additional comparisons demonstrate the superiority of our model over these ones based on only one word embedding set. We release our code for the method duplicability. |
| Tasks | Feature Engineering, Learning Word Embeddings, Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2102/ |
| https://www.aclweb.org/anthology/S17-2102 | |
| PWC | https://paperswithcode.com/paper/nnembs-at-semeval-2017-task-4-neural-twitter |
| Repo | |
| Framework | |
Towards an integrated pipeline for aspect-based sentiment analysis in various domains
| Title | Towards an integrated pipeline for aspect-based sentiment analysis in various domains |
| Authors | Orph{'e}e De Clercq, Els Lefever, Gilles Jacobs, Tijl Carpels, V{'e}ronique Hoste |
| Abstract | This paper presents an integrated ABSA pipeline for Dutch that has been developed and tested on qualitative user feedback coming from three domains: retail, banking and human resources. The two latter domains provide service-oriented data, which has not been investigated before in ABSA. By performing in-domain and cross-domain experiments the validity of our approach was investigated. We show promising results for the three ABSA subtasks, aspect term extraction, aspect category classification and aspect polarity classification. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5218/ |
| https://www.aclweb.org/anthology/W17-5218 | |
| PWC | https://paperswithcode.com/paper/towards-an-integrated-pipeline-for-aspect |
| Repo | |
| Framework | |
Data-Driven News Generation for Automated Journalism
| Title | Data-Driven News Generation for Automated Journalism |
| Authors | Leo Lepp{"a}nen, Myriam Munezero, Mark Granroth-Wilding, Hannu Toivonen |
| Abstract | Despite increasing amounts of data and ever improving natural language generation techniques, work on automated journalism is still relatively scarce. In this paper, we explore the field and challenges associated with building a journalistic natural language generation system. We present a set of requirements that should guide system design, including transparency, accuracy, modifiability and transferability. Guided by the requirements, we present a data-driven architecture for automated journalism that is largely domain and language independent. We illustrate its practical application in the production of news articles about the 2017 Finnish municipal elections in three languages, demonstrating the successfulness of the data-driven, modular approach of the design. We then draw some lessons for future automated journalism. |
| Tasks | News Generation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3528/ |
| https://www.aclweb.org/anthology/W17-3528 | |
| PWC | https://paperswithcode.com/paper/data-driven-news-generation-for-automated |
| Repo | |
| Framework | |
SentiME++ at SemEval-2017 Task 4: Stacking State-of-the-Art Classifiers to Enhance Sentiment Classification
| Title | SentiME++ at SemEval-2017 Task 4: Stacking State-of-the-Art Classifiers to Enhance Sentiment Classification |
| Authors | Rapha{"e}l Troncy, Enrico Palumbo, Efstratios Sygkounas, Giuseppe Rizzo |
| Abstract | In this paper, we describe the participation of the SentiME++ system to the SemEval 2017 Task 4A {``}Sentiment Analysis in Twitter{''} that aims to classify whether English tweets are of positive, neutral or negative sentiment. SentiME++ is an ensemble approach to sentiment analysis that leverages stacked generalization to automatically combine the predictions of five state-of-the-art sentiment classifiers. SentiME++ achieved officially 61.30{%} F1-score, ranking 12th out of 38 participants. | |
| Tasks | Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2107/ |
| https://www.aclweb.org/anthology/S17-2107 | |
| PWC | https://paperswithcode.com/paper/sentime-at-semeval-2017-task-4-stacking-state |
| Repo | |
| Framework | |
TwiSe at SemEval-2017 Task 4: Five-point Twitter Sentiment Classification and Quantification
| Title | TwiSe at SemEval-2017 Task 4: Five-point Twitter Sentiment Classification and Quantification |
| Authors | Georgios Balikas |
| Abstract | The paper describes the participation of the team {}TwiSE{''} in the SemEval-2017 challenge. Specifically, I participated at Task 4 entitled {}Sentiment Analysis in Twitter{''} for which I implemented systems for five-point tweet classification (Subtask C) and five-point tweet quantification (Subtask E) for English tweets. In the feature extraction steps the systems rely on the vector space model, morpho-syntactic analysis of the tweets and several sentiment lexicons. The classification step of Subtask C uses a Logistic Regression trained with the one-versus-rest approach. Another instance of Logistic Regression combined with the classify-and-count approach is trained for the quantification task of Subtask E. In the official leaderboard the system is ranked \textit{5/15} in Subtask C and \textit{2/12} in Subtask E. |
| Tasks | Opinion Mining, Sentiment Analysis, Twitter Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2127/ |
| https://www.aclweb.org/anthology/S17-2127 | |
| PWC | https://paperswithcode.com/paper/twise-at-semeval-2017-task-4-five-point |
| Repo | |
| Framework | |
