Paper Group NANR 43
Legal NERC with ontologies, Wikipedia and curriculum learning. Framing QA as Building and Ranking Intersentence Answer Justifications. Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding. Learning A Structured Optimal Bipartite Graph for Co-Clustering. Improving Japanese-to-English Neural Machine Translation by Voice Pred …
Legal NERC with ontologies, Wikipedia and curriculum learning
| Title | Legal NERC with ontologies, Wikipedia and curriculum learning |
| Authors | Cristian Cardellino, Milagro Teruel, Laura Alonso Alemany, Serena Villata |
| Abstract | In this paper, we present a Wikipedia-based approach to develop resources for the legal domain. We establish a mapping between a legal domain ontology, LKIF (Hoekstra et al. 2007), and a Wikipedia-based ontology, YAGO (Suchanek et al. 2007), and through that we populate LKIF. Moreover, we use the mentions of those entities in Wikipedia text to train a specific Named Entity Recognizer and Classifier. We find that this classifier works well in the Wikipedia, but, as could be expected, performance decreases in a corpus of judgments of the European Court of Human Rights. However, this tool will be used as a preprocess for human annotation. We resort to a technique called {``}curriculum learning{''} aimed to overcome problems of overfitting by learning increasingly more complex concepts. However, we find that in this particular setting, the method works best by learning from most specific to most general concepts, not the other way round. | |
| Tasks | Dependency Parsing, Semantic Role Labeling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2041/ |
| https://www.aclweb.org/anthology/E17-2041 | |
| PWC | https://paperswithcode.com/paper/legal-nerc-with-ontologies-wikipedia-and |
| Repo | |
| Framework | |
Framing QA as Building and Ranking Intersentence Answer Justifications
| Title | Framing QA as Building and Ranking Intersentence Answer Justifications |
| Authors | Peter Jansen, Rebecca Sharp, Mihai Surdeanu, Peter Clark |
| Abstract | We propose a question answering (QA) approach for standardized science exams that both identifies correct answers and produces compelling human-readable justifications for why those answers are correct. Our method first identifies the actual information needed in a question using psycholinguistic concreteness norms, then uses this information need to construct answer justifications by aggregating multiple sentences from different knowledge bases using syntactic and lexical information. We then jointly rank answers and their justifications using a reranking perceptron that treats justification quality as a latent variable. We evaluate our method on 1,000 multiple-choice questions from elementary school science exams, and empirically demonstrate that it performs better than several strong baselines, including neural network approaches. Our best configuration answers 44{%} of the questions correctly, where the top justifications for 57{%} of these correct answers contain a compelling human-readable justification that explains the inference required to arrive at the correct answer. We include a detailed characterization of the justification quality for both our method and a strong baseline, and show that information aggregation is key to addressing the information need in complex questions. |
| Tasks | Question Answering |
| Published | 2017-06-01 |
| URL | https://www.aclweb.org/anthology/J17-2005/ |
| https://www.aclweb.org/anthology/J17-2005 | |
| PWC | https://paperswithcode.com/paper/framing-qa-as-building-and-ranking |
| Repo | |
| Framework | |
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
| Title | Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding |
| Authors | Yixin Cao, Lifu Huang, Heng Ji, Xu Chen, Juanzi Li |
| Abstract | Integrating text and knowledge into a unified semantic space has attracted significant research interests recently. However, the ambiguity in the common space remains a challenge, namely that the same mention phrase usually refers to various entities. In this paper, to deal with the ambiguity of entity mentions, we propose a novel Multi-Prototype Mention Embedding model, which learns multiple sense embeddings for each mention by jointly modeling words from textual contexts and entities derived from a knowledge base. In addition, we further design an efficient language model based approach to disambiguate each mention to a specific sense. In experiments, both qualitative and quantitative analysis demonstrate the high quality of the word, entity and multi-prototype mention embeddings. Using entity linking as a study case, we apply our disambiguation method as well as the multi-prototype mention embeddings on the benchmark dataset, and achieve state-of-the-art performance. |
| Tasks | Entity Linking, Knowledge Graph Completion, Language Modelling, Relation Extraction, Word Sense Disambiguation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1149/ |
| https://www.aclweb.org/anthology/P17-1149 | |
| PWC | https://paperswithcode.com/paper/bridge-text-and-knowledge-by-learning-multi |
| Repo | |
| Framework | |
Learning A Structured Optimal Bipartite Graph for Co-Clustering
| Title | Learning A Structured Optimal Bipartite Graph for Co-Clustering |
| Authors | Feiping Nie, Xiaoqian Wang, Cheng Deng, Heng Huang |
| Abstract | Co-clustering methods have been widely applied to document clustering and gene expression analysis. These methods make use of the duality between features and samples such that the co-occurring structure of sample and feature clusters can be extracted. In graph based co-clustering methods, a bipartite graph is constructed to depict the relation between features and samples. Most existing co-clustering methods conduct clustering on the graph achieved from the original data matrix, which doesn’t have explicit cluster structure, thus they require a post-processing step to obtain the clustering results. In this paper, we propose a novel co-clustering method to learn a bipartite graph with exactly k connected components, where k is the number of clusters. The new bipartite graph learned in our model approximates the original graph but maintains an explicit cluster structure, from which we can immediately get the clustering results without post-processing. Extensive empirical results are presented to verify the effectiveness and robustness of our model. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7001-learning-a-structured-optimal-bipartite-graph-for-co-clustering |
| http://papers.nips.cc/paper/7001-learning-a-structured-optimal-bipartite-graph-for-co-clustering.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-structured-optimal-bipartite-graph |
| Repo | |
| Framework | |
Improving Japanese-to-English Neural Machine Translation by Voice Prediction
| Title | Improving Japanese-to-English Neural Machine Translation by Voice Prediction |
| Authors | Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, Mamoru Komachi |
| Abstract | This study reports an attempt to predict the voice of reference using the information from the input sentences or previous input/output sentences. Our previous study presented a voice controlling method to generate sentences for neural machine translation, wherein it was demonstrated that the BLEU score improved when the voice of generated sentence was controlled relative to that of the reference. However, it is impractical to use the reference information because we cannot discern the voice of the correct translation in advance. Thus, this study presents a voice prediction method for generated sentences for neural machine translation. While evaluating on Japanese-to-English translation, we obtain a 0.70-improvement in the BLEU using the predicted voice. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2047/ |
| https://www.aclweb.org/anthology/I17-2047 | |
| PWC | https://paperswithcode.com/paper/improving-japanese-to-english-neural-machine-1 |
| Repo | |
| Framework | |
Gender Prediction for Chinese Social Media Data
| Title | Gender Prediction for Chinese Social Media Data |
| Authors | Wen Li, Markus Dickinson |
| Abstract | Social media provides users a platform to publish messages and socialize with others, and microblogs have gained more users than ever in recent years. With such usage, user profiling is a popular task in computational linguistics and text mining. Different approaches have been used to predict users{'} gender, age, and other information, but most of this work has been done on English and other Western languages. The goal of this project is to predict the gender of users based on their posts on Weibo, a Chinese micro-blogging platform. Given issues in Chinese word segmentation, we explore character and word n-grams as features for this task, as well as using character and word embeddings for classification. Given how the data is extracted, we approach the task on a per-post basis, and we show the difficulties of the task for both humans and computers. Nonetheless, we present encouraging results and point to future improvements. |
| Tasks | Chinese Word Segmentation, Gender Prediction, Sentiment Analysis, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1058/ |
| https://doi.org/10.26615/978-954-452-049-6_058 | |
| PWC | https://paperswithcode.com/paper/gender-prediction-for-chinese-social-media |
| Repo | |
| Framework | |
The HIT-SCIR System for End-to-End Parsing of Universal Dependencies
| Title | The HIT-SCIR System for End-to-End Parsing of Universal Dependencies |
| Authors | Wanxiang Che, Jiang Guo, Yuxuan Wang, Bo Zheng, Huaipeng Zhao, Yang Liu, Dechuan Teng, Ting Liu |
| Abstract | This paper describes our system (HIT-SCIR) for the CoNLL 2017 shared task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system includes three pipelined components: \textit{tokenization}, \textit{Part-of-Speech} (POS) \textit{tagging} and \textit{dependency parsing}. We use character-based bidirectional long short-term memory (LSTM) networks for both tokenization and POS tagging. Afterwards, we employ a list-based transition-based algorithm for general non-projective parsing and present an improved Stack-LSTM-based architecture for representing each transition state and making predictions. Furthermore, to parse low/zero-resource languages and cross-domain data, we use a model transfer approach to make effective use of existing resources. We demonstrate substantial gains against the UDPipe baseline, with an average improvement of 3.76{%} in LAS of all languages. And finally, we rank the 4th place on the official test sets. |
| Tasks | Dependency Parsing, Information Retrieval, Part-Of-Speech Tagging, Tokenization, Transfer Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3005/ |
| https://www.aclweb.org/anthology/K17-3005 | |
| PWC | https://paperswithcode.com/paper/the-hit-scir-system-for-end-to-end-parsing-of |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems
| Title | Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5400/ |
| https://www.aclweb.org/anthology/W17-5400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-building |
| Repo | |
| Framework | |
Lexicon for Natural Language Generation in Spanish Adapted to Alternative and Augmentative Communication
| Title | Lexicon for Natural Language Generation in Spanish Adapted to Alternative and Augmentative Communication |
| Authors | Silvia Garc{'\i}a-M{'e}ndez, Milagros Fern{'a}ndez-Gavilanes, Enrique Costa-Montenegro, Jonathan Juncal-Mart{'\i}nez, Francisco J. Gonz{'a}lez-Casta{~n}o |
| Abstract | |
| Tasks | Speech Recognition, Speech Synthesis, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3802/ |
| https://www.aclweb.org/anthology/W17-3802 | |
| PWC | https://paperswithcode.com/paper/lexicon-for-natural-language-generation-in |
| Repo | |
| Framework | |
Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers
| Title | Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers |
| Authors | Mark Hopkins, Cristian Petrescu-Prahova, Roie Levin, Ronan Le Bras, Alvaro Herrasti, Vidur Joshi |
| Abstract | We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions {–} the math portion of the Scholastic Aptitude Test (SAT). By using a tree transducer cascade as its basic architecture, our system propagates uncertainty from multiple sources (e.g. coreference resolution or verb interpretation) until it can be confidently resolved. Experiments show the first-ever results 43{%} recall and 91{%} precision) on SAT algebra word problems. We also apply our system to the public Dolphin algebra question set, and improve the state-of-the-art F1-score from 73.9{%} to 77.0{%}. |
| Tasks | Coreference Resolution, Question Answering, Semantic Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1083/ |
| https://www.aclweb.org/anthology/D17-1083 | |
| PWC | https://paperswithcode.com/paper/beyond-sentential-semantic-parsing-tackling |
| Repo | |
| Framework | |
GW_QA at SemEval-2017 Task 3: Question Answer Re-ranking on Arabic Fora
| Title | GW_QA at SemEval-2017 Task 3: Question Answer Re-ranking on Arabic Fora |
| Authors | Nada Almarwani, Mona Diab |
| Abstract | This paper describes our submission to SemEval-2017 Task 3 Subtask D, {``}Question Answer Ranking in Arabic Community Question Answering{''}. In this work, we applied a supervised machine learning approach to automatically re-rank a set of QA pairs according to their relevance to a given question. We employ features based on latent semantic models, namely WTMF, as well as a set of lexical features based on string lengths and surface level matching. The proposed system ranked first out of 3 submissions, with a MAP score of 61.16{%}. | |
| Tasks | Answer Selection, Community Question Answering, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2056/ |
| https://www.aclweb.org/anthology/S17-2056 | |
| PWC | https://paperswithcode.com/paper/gw_qa-at-semeval-2017-task-3-question-answer |
| Repo | |
| Framework | |
Adapting the TTL Romanian POS Tagger to the Biomedical Domain
| Title | Adapting the TTL Romanian POS Tagger to the Biomedical Domain |
| Authors | Maria Mitrofan, Radu Ion |
| Abstract | This paper presents the adaptation of the Hidden Markov Models-based TTL part-of-speech tagger to the biomedical domain. TTL is a text processing platform that performs sentence splitting, tokenization, POS tagging, chunking and Named Entity Recognition (NER) for a number of languages, including Romanian. The POS tagging accuracy obtained by the TTL POS tagger exceeds 97{%} when TTL{'}s baseline model is updated with training information from a Romanian biomedical corpus. This corpus is developed in the context of the CoRoLa (a reference corpus for the contemporary Romanian language) project. Informative description and statistics of the Romanian biomedical corpus are also provided. |
| Tasks | Chunking, Domain Adaptation, Lemmatization, Named Entity Recognition, Part-Of-Speech Tagging, Tokenization, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8002/ |
| https://doi.org/10.26615/978-954-452-044-1_002 | |
| PWC | https://paperswithcode.com/paper/adapting-the-ttl-romanian-pos-tagger-to-the |
| Repo | |
| Framework | |
Learning with Bandit Feedback in Potential Games
| Title | Learning with Bandit Feedback in Potential Games |
| Authors | Amélie Heliou, Johanne Cohen, Panayotis Mertikopoulos |
| Abstract | This paper examines the equilibrium convergence properties of no-regret learning with exponential weights in potential games. To establish convergence with minimal information requirements on the players’ side, we focus on two frameworks: the semi-bandit case (where players have access to a noisy estimate of their payoff vectors, including strategies they did not play), and the bandit case (where players are only able to observe their in-game, realized payoffs). In the semi-bandit case, we show that the induced sequence of play converges almost surely to a Nash equilibrium at a quasi-exponential rate. In the bandit case, the same result holds for approximate Nash equilibria if we introduce a constant exploration factor that guarantees that action choice probabilities never become arbitrarily small. In particular, if the algorithm is run with a suitably decreasing exploration factor, the sequence of play converges to a bona fide Nash equilibrium with probability 1. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7216-learning-with-bandit-feedback-in-potential-games |
| http://papers.nips.cc/paper/7216-learning-with-bandit-feedback-in-potential-games.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-bandit-feedback-in-potential |
| Repo | |
| Framework | |
Painless Relation Extraction with Kindred
| Title | Painless Relation Extraction with Kindred |
| Authors | Jake Lever, Steven Jones |
| Abstract | Relation extraction methods are essential for creating robust text mining tools to help researchers find useful knowledge in the vast published literature. Easy-to-use and generalizable methods are needed to encourage an ecosystem in which researchers can easily use shared resources and build upon each others{'} methods. We present the Kindred Python package for relation extraction. It builds upon methods from the most successful tools in the recent BioNLP Shared Task to predict high-quality predictions with low computational cost. It also integrates with PubAnnotation, PubTator, and BioNLP Shared Task data in order to allow easy development and application of relation extraction models. |
| Tasks | Named Entity Recognition, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2322/ |
| https://www.aclweb.org/anthology/W17-2322 | |
| PWC | https://paperswithcode.com/paper/painless-relation-extraction-with-kindred |
| Repo | |
| Framework | |
SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News
| Title | SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News |
| Authors | Keith Cortis, Andr{'e} Freitas, Tobias Daudert, Manuela Huerlimann, Manel Zarrouk, H, Siegfried schuh, Brian Davis |
| Abstract | This paper discusses the {}Fine-Grained Sentiment Analysis on Financial Microblogs and News{''} task as part of SemEval-2017, specifically under the {}Detecting sentiment, humour, and truth{''} theme. This task contains two tracks, where the first one concerns Microblog messages and the second one covers News Statements and Headlines. The main goal behind both tracks was to predict the sentiment score for each of the mentioned companies/stocks. The sentiment scores for each text instance adopted floating point values in the range of -1 (very negative/bearish) to 1 (very positive/bullish), with 0 designating neutral sentiment. This task attracted a total of 32 participants, with 25 participating in Track 1 and 29 in Track 2. |
| Tasks | Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2089/ |
| https://www.aclweb.org/anthology/S17-2089 | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-5-fine-grained-sentiment |
| Repo | |
| Framework | |
