Paper Group NANR 40
Predicting Success in Goal-Driven Human-Human Dialogues. Neural Optimizer Search using Reinforcement Learning. Counterfactual Data-Fusion for Online Reinforcement Learners. Designing an Ontology for the Study of Ritual in Ancient Greek Tragedy. Prosody, syntax, and pragmatics: insubordination in spoken Brazilian Portuguese. Deriving continous groun …
Predicting Success in Goal-Driven Human-Human Dialogues
| Title | Predicting Success in Goal-Driven Human-Human Dialogues |
| Authors | Michael Noseworthy, Jackie Chi Kit Cheung, Joelle Pineau |
| Abstract | In goal-driven dialogue systems, success is often defined based on a structured definition of the goal. This requires that the dialogue system be constrained to handle a specific class of goals and that there be a mechanism to measure success with respect to that goal. However, in many human-human dialogues the diversity of goals makes it infeasible to define success in such a way. To address this scenario, we consider the task of automatically predicting success in goal-driven human-human dialogues using only the information communicated between participants in the form of text. We build a dataset from stackoverflow.com which consists of exchanges between two users in the technical domain where ground-truth success labels are available. We then propose a turn-based hierarchical neural network model that can be used to predict success without requiring a structured goal definition. We show this model outperforms rule-based heuristics and other baselines as it is able to detect patterns over the course of a dialogue and capture notions such as gratitude. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5531/ |
| https://www.aclweb.org/anthology/W17-5531 | |
| PWC | https://paperswithcode.com/paper/predicting-success-in-goal-driven-human-human |
| Repo | |
| Framework | |
Neural Optimizer Search using Reinforcement Learning
| Title | Neural Optimizer Search using Reinforcement Learning |
| Authors | Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le |
| Abstract | We present an approach to automate the process of discovering optimization methods, with a focus on deep learning architectures. We train a Recurrent Neural Network controller to generate a string in a specific domain language that describes a mathematical update equation based on a list of primitive functions, such as the gradient, running average of the gradient, etc. The controller is trained with Reinforcement Learning to maximize the performance of a model after a few epochs. On CIFAR-10, our method discovers several update rules that are better than many commonly used optimizers, such as Adam, RMSProp, or SGD with and without Momentum on a ConvNet model. These optimizers can also be transferred to perform well on different neural network architectures, including Google’s neural machine translation system. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=842 |
| http://proceedings.mlr.press/v70/bello17a/bello17a.pdf | |
| PWC | https://paperswithcode.com/paper/neural-optimizer-search-using-reinforcement |
| Repo | |
| Framework | |
Counterfactual Data-Fusion for Online Reinforcement Learners
| Title | Counterfactual Data-Fusion for Online Reinforcement Learners |
| Authors | Andrew Forney, Judea Pearl, Elias Bareinboim |
| Abstract | The Multi-Armed Bandit problem with Unobserved Confounders (MABUC) considers decision-making settings where unmeasured variables can influence both the agent’s decisions and received rewards (Bareinboim et al., 2015). Recent findings showed that unobserved confounders (UCs) pose a unique challenge to algorithms based on standard randomization (i.e., experimental data); if UCs are naively averaged out, these algorithms behave sub-optimally, possibly incurring infinite regret. In this paper, we show how counterfactual-based decision-making circumvents these problems and leads to a coherent fusion of observational and experimental data. We then demonstrate this new strategy in an enhanced Thompson Sampling bandit player, and support our findings’ efficacy with extensive simulations. |
| Tasks | Decision Making |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=872 |
| http://proceedings.mlr.press/v70/forney17a/forney17a.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-data-fusion-for-online |
| Repo | |
| Framework | |
Designing an Ontology for the Study of Ritual in Ancient Greek Tragedy
| Title | Designing an Ontology for the Study of Ritual in Ancient Greek Tragedy |
| Authors | Gloria Mugelli, Bell, Andrea i, Federico Boschetti, Anas Fahad Khan |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7011/ |
| https://www.aclweb.org/anthology/W17-7011 | |
| PWC | https://paperswithcode.com/paper/designing-an-ontology-for-the-study-of-ritual |
| Repo | |
| Framework | |
Prosody, syntax, and pragmatics: insubordination in spoken Brazilian Portuguese
| Title | Prosody, syntax, and pragmatics: insubordination in spoken Brazilian Portuguese |
| Authors | Giulia Bossaglia, Heliana Mello, Tommaso Raso |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6630/ |
| https://www.aclweb.org/anthology/W17-6630 | |
| PWC | https://paperswithcode.com/paper/prosody-syntax-and-pragmatics-insubordination |
| Repo | |
| Framework | |
Deriving continous grounded meaning representations from referentially structured multimodal contexts
| Title | Deriving continous grounded meaning representations from referentially structured multimodal contexts |
| Authors | Sina Zarrie{\ss}, David Schlangen |
| Abstract | Corpora of referring expressions paired with their visual referents are a good source for learning word meanings directly grounded in visual representations. Here, we explore additional ways of extracting from them word representations linked to multi-modal context: through expressions that refer to the same object, and through expressions that refer to different objects in the same scene. We show that continuous meaning representations derived from these contexts capture complementary aspects of similarity, , even if not outperforming textual embeddings trained on very large amounts of raw text when tested on standard similarity benchmarks. We propose a new task for evaluating grounded meaning representations{—}detection of potentially co-referential phrases{—}and show that it requires precise denotational representations of attribute meanings, which our method provides. |
| Tasks | Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1100/ |
| https://www.aclweb.org/anthology/D17-1100 | |
| PWC | https://paperswithcode.com/paper/deriving-continous-grounded-meaning |
| Repo | |
| Framework | |
Towards developing a phonetically balanced code-mixed speech corpus for Hindi-English ASR
| Title | Towards developing a phonetically balanced code-mixed speech corpus for Hindi-English ASR |
| Authors | P, Ayushi ey, Brij Mohan Lal Srivastava, Suryakanth Gangashetty |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7512/ |
| https://www.aclweb.org/anthology/W17-7512 | |
| PWC | https://paperswithcode.com/paper/towards-developing-a-phonetically-balanced |
| Repo | |
| Framework | |
A semantically-based approach to the annotation of narrative style
| Title | A semantically-based approach to the annotation of narrative style |
| Authors | Rodolfo Delmonte, Giulia Marchesi |
| Abstract | |
| Tasks | Opinion Mining |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7402/ |
| https://www.aclweb.org/anthology/W17-7402 | |
| PWC | https://paperswithcode.com/paper/a-semantically-based-approach-to-the |
| Repo | |
| Framework | |
PACTE: A colloaborative platform for textual annotation
| Title | PACTE: A colloaborative platform for textual annotation |
| Authors | Pierre Andr{'e} M{'e}nard, Caroline Barri{`e}re |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7410/ |
| https://www.aclweb.org/anthology/W17-7410 | |
| PWC | https://paperswithcode.com/paper/pacte-a-colloaborative-platform-for-textual |
| Repo | |
| Framework | |
Adversarial evaluation for open-domain dialogue generation
| Title | Adversarial evaluation for open-domain dialogue generation |
| Authors | Elia Bruni, Raquel Fern{'a}ndez |
| Abstract | We investigate the potential of adversarial evaluation methods for open-domain dialogue generation systems, comparing the performance of a discriminative agent to that of humans on the same task. Our results show that the task is hard, both for automated models and humans, but that a discriminative agent can learn patterns that lead to above-chance performance. |
| Tasks | Chatbot, Dialogue Generation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5534/ |
| https://www.aclweb.org/anthology/W17-5534 | |
| PWC | https://paperswithcode.com/paper/adversarial-evaluation-for-open-domain |
| Repo | |
| Framework | |
Lessons in Dialogue System Deployment
| Title | Lessons in Dialogue System Deployment |
| Authors | Anton Leuski, Ron Artstein |
| Abstract | We analyze deployment of an interactive dialogue system in an environment where deep technical expertise might not be readily available. The initial version was created using a collection of research tools. We summarize a number of challenges with its deployment at two museums and describe a new system that simplifies the installation and user interface; reduces reliance on 3rd-party software; and provides a robust data collection mechanism. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5541/ |
| https://www.aclweb.org/anthology/W17-5541 | |
| PWC | https://paperswithcode.com/paper/lessons-in-dialogue-system-deployment |
| Repo | |
| Framework | |
Word Embedding and Topic Modeling Enhanced Multiple Features for Content Linking and Argument / Sentiment Labeling in Online Forums
| Title | Word Embedding and Topic Modeling Enhanced Multiple Features for Content Linking and Argument / Sentiment Labeling in Online Forums |
| Authors | Lei Li, Liyuan Mao, Moye Chen |
| Abstract | Multiple grammatical and semantic features are adopted in content linking and argument/sentiment labeling for online forums in this paper. There are mainly two different methods for content linking. First, we utilize the deep feature obtained from Word Embedding Model in deep learning and compute sentence similarity. Second, we use multiple traditional features to locate candidate linking sentences, and then adopt a voting method to obtain the final result. LDA topic modeling is used to mine latent semantic feature and K-means clustering is implemented for argument labeling, while features from sentiment dictionaries and rule-based sentiment analysis are integrated for sentiment labeling. Experimental results have shown that our methods are valid. |
| Tasks | Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1005/ |
| https://www.aclweb.org/anthology/W17-1005 | |
| PWC | https://paperswithcode.com/paper/word-embedding-and-topic-modeling-enhanced |
| Repo | |
| Framework | |
Literal readings of multiword expressions: as scarce as hen’s teeth
| Title | Literal readings of multiword expressions: as scarce as hen’s teeth |
| Authors | Agata Savary, Silvio Ricardo Cordeiro |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7610/ |
| https://www.aclweb.org/anthology/W17-7610 | |
| PWC | https://paperswithcode.com/paper/literal-readings-of-multiword-expressions-as |
| Repo | |
| Framework | |
Data point selection for genre-aware parsing
| Title | Data point selection for genre-aware parsing |
| Authors | Ines Rehbein, Felix Bildhauer |
| Abstract | |
| Tasks | Dependency Parsing, Domain Adaptation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7614/ |
| https://www.aclweb.org/anthology/W17-7614 | |
| PWC | https://paperswithcode.com/paper/data-point-selection-for-genre-aware-parsing |
| Repo | |
| Framework | |
Syntactic Semantic Correspondence in Dependency Grammar
| Title | Syntactic Semantic Correspondence in Dependency Grammar |
| Authors | C{\u{a}}t{\u{a}}lina M{\u{a}}r{\u{a}}nduc, C{\u{a}}t{\u{a}}lin Mititelu, Victoria Bobicev |
| Abstract | |
| Tasks | Question Answering |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7621/ |
| https://www.aclweb.org/anthology/W17-7621 | |
| PWC | https://paperswithcode.com/paper/syntactic-semantic-correspondence-in |
| Repo | |
| Framework | |
