Paper Group NANR 114
Results of the WMT16 Metrics Shared Task. Character-based Neural Machine Translation. BioDCA Identifier: A System for Automatic Identification of Discourse Connective and Arguments from Biomedical Text. SimpleNLG-IT: adapting SimpleNLG to Italian. Good Automatic Authentication Question Generation. Understanding Language Preference for Expression of …
Results of the WMT16 Metrics Shared Task
| Title | Results of the WMT16 Metrics Shared Task |
| Authors | Ond{\v{r}}ej Bojar, Yvette Graham, Amir Kamran, Milo{\v{s}} Stanojevi{'c} |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2302/ |
| https://www.aclweb.org/anthology/W16-2302 | |
| PWC | https://paperswithcode.com/paper/results-of-the-wmt16-metrics-shared-task |
| Repo | |
| Framework | |
Character-based Neural Machine Translation
| Title | Character-based Neural Machine Translation |
| Authors | Marta R. Costa-juss{`a}, Jos{'e} A. R. Fonollosa |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2058/ |
| https://www.aclweb.org/anthology/P16-2058 | |
| PWC | https://paperswithcode.com/paper/character-based-neural-machine-translation-2 |
| Repo | |
| Framework | |
BioDCA Identifier: A System for Automatic Identification of Discourse Connective and Arguments from Biomedical Text
| Title | BioDCA Identifier: A System for Automatic Identification of Discourse Connective and Arguments from Biomedical Text |
| Authors | Sindhuja Gopalan, Sobha Lalitha Devi |
| Abstract | This paper describes a Natural language processing system developed for automatic identification of explicit connectives, its sense and arguments. Prior work has shown that the difference in usage of connectives across corpora affects the cross domain connective identification task negatively. Hence the development of domain specific discourse parser has become indispensable. Here, we present a corpus annotated with discourse relations on Medline abstracts. Kappa score is calculated to check the annotation quality of our corpus. The previous works on discourse analysis in bio-medical data have concentrated only on the identification of connectives and hence we have developed an end-end parser for connective and argument identification using Conditional Random Fields algorithm. The type and sub-type of the connective sense is also identified. The results obtained are encouraging. |
| Tasks | Named Entity Recognition, Speech Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5110/ |
| https://www.aclweb.org/anthology/W16-5110 | |
| PWC | https://paperswithcode.com/paper/biodca-identifier-a-system-for-automatic |
| Repo | |
| Framework | |
SimpleNLG-IT: adapting SimpleNLG to Italian
| Title | SimpleNLG-IT: adapting SimpleNLG to Italian |
| Authors | Aless Mazzei, ro, Cristina Battaglino, Cristina Bosco |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6630/ |
| https://www.aclweb.org/anthology/W16-6630 | |
| PWC | https://paperswithcode.com/paper/simplenlg-it-adapting-simplenlg-to-italian |
| Repo | |
| Framework | |
Good Automatic Authentication Question Generation
| Title | Good Automatic Authentication Question Generation |
| Authors | Simon Woo, Zuyao Li, Jelena Mirkovic |
| Abstract | |
| Tasks | Common Sense Reasoning, Dependency Parsing, Question Generation, Semantic Role Labeling, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6632/ |
| https://www.aclweb.org/anthology/W16-6632 | |
| PWC | https://paperswithcode.com/paper/good-automatic-authentication-question |
| Repo | |
| Framework | |
Understanding Language Preference for Expression of Opinion and Sentiment: What do Hindi-English Speakers do on Twitter?
| Title | Understanding Language Preference for Expression of Opinion and Sentiment: What do Hindi-English Speakers do on Twitter? |
| Authors | Koustav Rudra, Shruti Rijhwani, Rafiya Begum, Kalika Bali, Monojit Choudhury, Niloy Ganguly |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1121/ |
| https://www.aclweb.org/anthology/D16-1121 | |
| PWC | https://paperswithcode.com/paper/understanding-language-preference-for |
| Repo | |
| Framework | |
Automatic Extraction of Implicit Interpretations from Modal Constructions
| Title | Automatic Extraction of Implicit Interpretations from Modal Constructions |
| Authors | S, Jordan ers, Eduardo Blanco |
| Abstract | |
| Tasks | Machine Translation, Natural Language Inference, Sentiment Analysis |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1118/ |
| https://www.aclweb.org/anthology/D16-1118 | |
| PWC | https://paperswithcode.com/paper/automatic-extraction-of-implicit |
| Repo | |
| Framework | |
Joint Inference for Mode Identification in Tutorial Dialogues
| Title | Joint Inference for Mode Identification in Tutorial Dialogues |
| Authors | Deepak Venugopal, Vasile Rus |
| Abstract | Identifying dialogue acts and dialogue modes during tutorial interactions is an extremely crucial sub-step in understanding patterns of effective tutor-tutee interactions. In this work, we develop a novel joint inference method that labels each utterance in a tutoring dialogue session with a dialogue act and a specific mode from a set of pre-defined dialogue acts and modes, respectively. Specifically, we develop our joint model using Markov Logic Networks (MLNs), a framework that combines first-order logic with probabilities, and is thus capable of representing complex, uncertain knowledge. We define first-order formulas in our MLN that encode the inter-dependencies between dialogue modes and more fine-grained dialogue actions. We then use a joint inference to jointly label the modes as well as the dialogue acts in an utterance. We compare our system against a pipeline system based on SVMs on a real-world dataset with tutoring sessions of over 500 students. Our results show that the joint inference system is far more effective than the pipeline system in mode detection, and improves over the performance of the pipeline system by about 6 points in F1 score. The joint inference system also performs much better than the pipeline system in the context of labeling modes that highlight important pedagogical steps in tutoring. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1188/ |
| https://www.aclweb.org/anthology/C16-1188 | |
| PWC | https://paperswithcode.com/paper/joint-inference-for-mode-identification-in |
| Repo | |
| Framework | |
CoRuSS - a New Prosodically Annotated Corpus of Russian Spontaneous Speech
| Title | CoRuSS - a New Prosodically Annotated Corpus of Russian Spontaneous Speech |
| Authors | Tatiana Kachkovskaia, Daniil Kocharov, Pavel Skrelin, Nina Volskaya |
| Abstract | This paper describes speech data recording, processing and annotation of a new speech corpus CoRuSS (Corpus of Russian Spontaneous Speech), which is based on connected communicative speech recorded from 60 native Russian male and female speakers of different age groups (from 16 to 77). Some Russian speech corpora available at the moment contain plain orthographic texts and provide some kind of limited annotation, but there are no corpora providing detailed prosodic annotation of spontaneous conversational speech. This corpus contains 30 hours of high quality recorded spontaneous Russian speech, half of it has been transcribed and prosodically labeled. The recordings consist of dialogues between two speakers, monologues (speakers{'} self-presentations) and reading of a short phonetically balanced text. Since the corpus is labeled for a wide range of linguistic - phonetic and prosodic - information, it provides basis for empirical studies of various spontaneous speech phenomena as well as for comparison with those we observe in prepared read speech. Since the corpus is designed as a open-access resource of speech data, it will also make possible to advance corpus-based analysis of spontaneous speech data across languages and speech technology development as well. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1309/ |
| https://www.aclweb.org/anthology/L16-1309 | |
| PWC | https://paperswithcode.com/paper/coruss-a-new-prosodically-annotated-corpus-of |
| Repo | |
| Framework | |
Defining Words with Words: Beyond the Distributional Hypothesis
| Title | Defining Words with Words: Beyond the Distributional Hypothesis |
| Authors | Iuliana-Elena Parasca, Andreas Lukas Rauter, Jack Roper, Aleks Rusinov, ar, Guillaume Bouchard, Sebastian Riedel, Pontus Stenetorp |
| Abstract | |
| Tasks | Representation Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2522/ |
| https://www.aclweb.org/anthology/W16-2522 | |
| PWC | https://paperswithcode.com/paper/defining-words-with-words-beyond-the |
| Repo | |
| Framework | |
Category-Driven Content Selection
| Title | Category-Driven Content Selection |
| Authors | Rania Mohammed, Laura Perez-Beltrachini, Claire Gardent |
| Abstract | |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6616/ |
| https://www.aclweb.org/anthology/W16-6616 | |
| PWC | https://paperswithcode.com/paper/category-driven-content-selection |
| Repo | |
| Framework | |
Dialogue System Characterisation by Back-channelling Patterns Extracted from Dialogue Corpus
| Title | Dialogue System Characterisation by Back-channelling Patterns Extracted from Dialogue Corpus |
| Authors | Masashi Inoue, Hiroshi Ueno |
| Abstract | In this study, we describe the use of back-channelling patterns extracted from a dialogue corpus as a mean to characterising text-based dialogue systems. Our goal was to provide system users with the feeling that they are interacting with distinct individuals rather than artificially created characters. An analysis of the corpus revealed that substantial difference exists among speakers regarding the usage patterns of back-channelling. The patterns consist of back-channelling frequency, types, and expressions. They were used for system characterisation. Implemented system characters were tested by asking users of the dialogue system to identify the source speakers in the corpus. Experimental results suggest that possibility of using back-channelling patterns alone to characterize the dialogue system in some cases even among the same age and gender groups. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1434/ |
| https://www.aclweb.org/anthology/L16-1434 | |
| PWC | https://paperswithcode.com/paper/dialogue-system-characterisation-by-back |
| Repo | |
| Framework | |
Deep Neural Networks with Massive Learned Knowledge
| Title | Deep Neural Networks with Massive Learned Knowledge |
| Authors | Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric Xing |
| Abstract | |
| Tasks | Representation Learning, Sentiment Analysis |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1173/ |
| https://www.aclweb.org/anthology/D16-1173 | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-with-massive-learned |
| Repo | |
| Framework | |
Frustratingly Easy Neural Domain Adaptation
| Title | Frustratingly Easy Neural Domain Adaptation |
| Authors | Young-Bum Kim, Karl Stratos, Ruhi Sarikaya |
| Abstract | Popular techniques for domain adaptation such as the feature augmentation method of Daum{'e} III (2009) have mostly been considered for sparse binary-valued features, but not for dense real-valued features such as those used in neural networks. In this paper, we describe simple neural extensions of these techniques. First, we propose a natural generalization of the feature augmentation method that uses K + 1 LSTMs where one model captures global patterns across all K domains and the remaining K models capture domain-specific information. Second, we propose a novel application of the framework for learning shared structures by Ando and Zhang (2005) to domain adaptation, and also provide a neural extension of their approach. In experiments on slot tagging over 17 domains, our methods give clear performance improvement over Daum{'e} III (2009) applied on feature-rich CRFs. |
| Tasks | Domain Adaptation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1038/ |
| https://www.aclweb.org/anthology/C16-1038 | |
| PWC | https://paperswithcode.com/paper/frustratingly-easy-neural-domain-adaptation |
| Repo | |
| Framework | |
The Effects of the Content of FOMC Communications on US Treasury Rates
| Title | The Effects of the Content of FOMC Communications on US Treasury Rates |
| Authors | Christopher Rohlfs, Sun Chakraborty, an, Lakshminarayanan Subramanian |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1226/ |
| https://www.aclweb.org/anthology/D16-1226 | |
| PWC | https://paperswithcode.com/paper/the-effects-of-the-content-of-fomc |
| Repo | |
| Framework | |
