Paper Group NANR 106
Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Proceedings of the Workshop on Structured Prediction for NLP. Annotating Named Entities in Consumer Health Questions. Catching heuristics are optimal control policies. A Study …
Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation
| Title | Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation |
| Authors | Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, Mamoru Komachi |
| Abstract | In machine translation, we must consider the difference in expression between languages. For example, the active/passive voice may change in Japanese-English translation. The same verb in Japanese may be translated into different voices at each translation because the voice of a generated sentence cannot be determined using only the information of the Japanese sentence. Machine translation systems should consider the information structure to improve the coherence of the output by using several topicalization techniques such as passivization. Therefore, this paper reports on our attempt to control the voice of the sentence generated by an encoder-decoder model. To control the voice of the generated sentence, we added the voice information of the target sentence to the source sentence during the training. We then generated sentences with a specified voice by appending the voice information to the source sentence. We observed experimentally whether the voice could be controlled. The results showed that, we could control the voice of the generated sentence with 85.0{%} accuracy on average. In the evaluation of Japanese-English translation, we obtained a 0.73-point improvement in BLEU score by using gold voice labels. |
| Tasks | Machine Translation, Text Summarization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4620/ |
| https://www.aclweb.org/anthology/W16-4620 | |
| PWC | https://paperswithcode.com/paper/controlling-the-voice-of-a-sentence-in |
| Repo | |
| Framework | |
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
| Title | Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1000/ |
| https://www.aclweb.org/anthology/D16-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2016-conference-on |
| Repo | |
| Framework | |
Proceedings of the Workshop on Structured Prediction for NLP
| Title | Proceedings of the Workshop on Structured Prediction for NLP |
| Authors | |
| Abstract | |
| Tasks | Structured Prediction |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5900/ |
| https://www.aclweb.org/anthology/W16-5900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-structured |
| Repo | |
| Framework | |
Annotating Named Entities in Consumer Health Questions
| Title | Annotating Named Entities in Consumer Health Questions |
| Authors | Halil Kilicoglu, Asma Ben Abacha, Yassine Mrabet, Kirk Roberts, Laritza Rodriguez, Sonya Shooshan, Dina Demner-Fushman |
| Abstract | We describe a corpus of consumer health questions annotated with named entities. The corpus consists of 1548 de-identified questions about diseases and drugs, written in English. We defined 15 broad categories of biomedical named entities for annotation. A pilot annotation phase in which a small portion of the corpus was double-annotated by four annotators was followed by a main phase in which double annotation was carried out by six annotators, and a reconciliation phase in which all annotations were reconciled by an expert. We conducted the annotation in two modes, manual and assisted, to assess the effect of automatic pre-annotation and calculated inter-annotator agreement. We obtained moderate inter-annotator agreement; assisted annotation yielded slightly better agreement and fewer missed annotations than manual annotation. Due to complex nature of biomedical entities, we paid particular attention to nested entities for which we obtained slightly lower inter-annotator agreement, confirming that annotating nested entities is somewhat more challenging. To our knowledge, the corpus is the first of its kind for consumer health text and is publicly available. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1530/ |
| https://www.aclweb.org/anthology/L16-1530 | |
| PWC | https://paperswithcode.com/paper/annotating-named-entities-in-consumer-health |
| Repo | |
| Framework | |
Catching heuristics are optimal control policies
| Title | Catching heuristics are optimal control policies |
| Authors | Boris Belousov, Gerhard Neumann, Constantin A. Rothkopf, Jan R. Peters |
| Abstract | Two seemingly contradictory theories attempt to explain how humans move to intercept an airborne ball. One theory posits that humans predict the ball trajectory to optimally plan future actions; the other claims that, instead of performing such complicated computations, humans employ heuristics to reactively choose appropriate actions based on immediate visual feedback. In this paper, we show that interception strategies appearing to be heuristics can be understood as computational solutions to the optimal control problem faced by a ball-catching agent acting under uncertainty. Modeling catching as a continuous partially observable Markov decision process and employing stochastic optimal control theory, we discover that the four main heuristics described in the literature are optimal solutions if the catcher has sufficient time to continuously visually track the ball. Specifically, by varying model parameters such as noise, time to ground contact, and perceptual latency, we show that different strategies arise under different circumstances. The catcher’s policy switches between generating reactive and predictive behavior based on the ratio of system to observation noise and the ratio between reaction time and task duration. Thus, we provide a rational account of human ball-catching behavior and a unifying explanation for seemingly contradictory theories of target interception on the basis of stochastic optimal control. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6548-catching-heuristics-are-optimal-control-policies |
| http://papers.nips.cc/paper/6548-catching-heuristics-are-optimal-control-policies.pdf | |
| PWC | https://paperswithcode.com/paper/catching-heuristics-are-optimal-control |
| Repo | |
| Framework | |
A Study on the Interplay Between the Corpus Size and Parameters of a Distributional Model for Term Classification
| Title | A Study on the Interplay Between the Corpus Size and Parameters of a Distributional Model for Term Classification |
| Authors | Behrang QasemiZadeh |
| Abstract | We propose and evaluate a method for identifying co-hyponym lexical units in a terminological resource. The principles of term recognition and distributional semantics are combined to extract terms from a similar category of concept. Given a set of candidate terms, random projections are employed to represent them as low-dimensional vectors. These vectors are derived automatically from the frequency of the co-occurrences of the candidate terms and words that appear within windows of text in their proximity (context-windows). In a $k$-nearest neighbours framework, these vectors are classified using a small set of manually annotated terms which exemplify concept categories. We then investigate the interplay between the size of the corpus that is used for collecting the co-occurrences and a number of factors that play roles in the performance of the proposed method: the configuration of context-windows for collecting co-occurrences, the selection of neighbourhood size ($k$), and the choice of similarity metric. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4708/ |
| https://www.aclweb.org/anthology/W16-4708 | |
| PWC | https://paperswithcode.com/paper/a-study-on-the-interplay-between-the-corpus |
| Repo | |
| Framework | |
Non-sentential Question Resolution using Sequence to Sequence Learning
| Title | Non-sentential Question Resolution using Sequence to Sequence Learning |
| Authors | Vineet Kumar, Sachindra Joshi |
| Abstract | An interactive Question Answering (QA) system frequently encounters non-sentential (incomplete) questions. These non-sentential questions may not make sense to the system when a user asks them without the context of conversation. The system thus needs to take into account the conversation context to process the question. In this work, we present a recurrent neural network (RNN) based encoder decoder network that can generate a complete (intended) question, given an incomplete question and conversation context. RNN encoder decoder networks have been show to work well when trained on a parallel corpus with millions of sentences, however it is extremely hard to obtain conversation data of this magnitude. We therefore propose to decompose the original problem into two separate simplified problems where each problem focuses on an abstraction. Specifically, we train a semantic sequence model to learn semantic patterns, and a syntactic sequence model to learn linguistic patterns. We further combine syntactic and semantic sequence models to generate an ensemble model. Our model achieves a BLEU score of 30.15 as compared to 18.54 using a standard RNN encoder decoder model. |
| Tasks | Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1190/ |
| https://www.aclweb.org/anthology/C16-1190 | |
| PWC | https://paperswithcode.com/paper/non-sentential-question-resolution-using |
| Repo | |
| Framework | |
Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology
| Title | Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0300/ |
| https://www.aclweb.org/anthology/W16-0300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-4 |
| Repo | |
| Framework | |
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
| Title | Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1000/ |
| https://www.aclweb.org/anthology/C16-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-coling-2016-the-26th-1 |
| Repo | |
| Framework | |
SV000gg at SemEval-2016 Task 11: Heavy Gauge Complex Word Identification with System Voting
| Title | SV000gg at SemEval-2016 Task 11: Heavy Gauge Complex Word Identification with System Voting |
| Authors | Gustavo Paetzold, Lucia Specia |
| Abstract | |
| Tasks | Complex Word Identification, Lexical Simplification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1149/ |
| https://www.aclweb.org/anthology/S16-1149 | |
| PWC | https://paperswithcode.com/paper/sv000gg-at-semeval-2016-task-11-heavy-gauge |
| Repo | |
| Framework | |
PLUJAGH at SemEval-2016 Task 11: Simple System for Complex Word Identification
| Title | PLUJAGH at SemEval-2016 Task 11: Simple System for Complex Word Identification |
| Authors | Krzysztof Wr{'o}bel |
| Abstract | |
| Tasks | Complex Word Identification, Lexical Simplification, Word Sense Disambiguation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1146/ |
| https://www.aclweb.org/anthology/S16-1146 | |
| PWC | https://paperswithcode.com/paper/plujagh-at-semeval-2016-task-11-simple-system |
| Repo | |
| Framework | |
Creating Annotated Dialogue Resources: Cross-domain Dialogue Act Classification
| Title | Creating Annotated Dialogue Resources: Cross-domain Dialogue Act Classification |
| Authors | Dilafruz Amanova, Volha Petukhova, Dietrich Klakow |
| Abstract | This paper describes a method to automatically create dialogue resources annotated with dialogue act information by reusing existing dialogue corpora. Numerous dialogue corpora are available for research purposes and many of them are annotated with dialogue act information that captures the intentions encoded in user utterances. Annotated dialogue resources, however, differ in various respects: data collection settings and modalities used, dialogue task domains and scenarios (if any) underlying the collection, number and roles of dialogue participants involved and dialogue act annotation schemes applied. The presented study encompasses three phases of data-driven investigation. We, first, assess the importance of various types of features and their combinations for effective cross-domain dialogue act classification. Second, we establish the best predictive model comparing various cross-corpora training settings. Finally, we specify models adaptation procedures and explore late fusion approaches to optimize the overall classification decision taking process. The proposed methodology accounts for empirically motivated and technically sound classification procedures that may reduce annotation and training costs significantly. |
| Tasks | Dialogue Act Classification |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1017/ |
| https://www.aclweb.org/anthology/L16-1017 | |
| PWC | https://paperswithcode.com/paper/creating-annotated-dialogue-resources-cross |
| Repo | |
| Framework | |
DiegoLab16 at SemEval-2016 Task 4: Sentiment Analysis in Twitter using Centroids, Clusters, and Sentiment Lexicons
| Title | DiegoLab16 at SemEval-2016 Task 4: Sentiment Analysis in Twitter using Centroids, Clusters, and Sentiment Lexicons |
| Authors | Abeed Sarker, Graciela Gonzalez |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1031/ |
| https://www.aclweb.org/anthology/S16-1031 | |
| PWC | https://paperswithcode.com/paper/diegolab16-at-semeval-2016-task-4-sentiment |
| Repo | |
| Framework | |
UniPI at SemEval-2016 Task 4: Convolutional Neural Networks for Sentiment Classification
| Title | UniPI at SemEval-2016 Task 4: Convolutional Neural Networks for Sentiment Classification |
| Authors | Giuseppe Attardi, Daniele Sartiano |
| Abstract | |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1033/ |
| https://www.aclweb.org/anthology/S16-1033 | |
| PWC | https://paperswithcode.com/paper/unipi-at-semeval-2016-task-4-convolutional |
| Repo | |
| Framework | |
Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction
| Title | Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction |
| Authors | Stefan Falk, Andi Rexha, Roman Kern |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1042/ |
| https://www.aclweb.org/anthology/S16-1042 | |
| PWC | https://paperswithcode.com/paper/know-center-at-semeval-2016-task-5-using-word |
| Repo | |
| Framework | |
