Paper Group NANR 111
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice. SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications. From Information Bottleneck To Activation Norm Penalty. Classifying Sluice Occurrences in Dialogue. Deterministic Policy Imitation Gradient Algorithm. Oral-Mot …
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice
Title | Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice |
Authors | Alan Kuhnle, J. David Smith, Victoria Crawford, My Thai |
Abstract | The optimization of submodular functions on the integer lattice has received much attention recently, but the objective functions of many applications are non-submodular. We provide two approximation algorithms for maximizing a non-submodular function on the integer lattice subject to a cardinality constraint; these are the first algorithms for this purpose that have polynomial query complexity. We propose a general framework for influence maximization on the integer lattice that generalizes prior works on this topic, and we demonstrate the efficiency of our algorithms in this context. |
Tasks | |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1912 |
http://proceedings.mlr.press/v80/kuhnle18a/kuhnle18a.pdf | |
PWC | https://paperswithcode.com/paper/fast-maximization-of-non-submodular-monotonic |
Repo | |
Framework | |
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Title | SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications |
Authors | Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang |
Abstract | Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications. These approaches typically train a sequence-to-sequence learning model using a syntax-based objective: maximum likelihood estimation (MLE). Such syntax-based approaches do not effectively address the goal of generating semantically correct programs, because these approaches fail to handle Program Aliasing, i.e., semantically equivalent programs may have many syntactically different forms. To address this issue, in this paper, we propose a semantics-based approach named SemRegex. SemRegex provides solutions for a subtask of the program-synthesis problem: generating regular expressions from natural language. Different from the existing syntax-based approaches, SemRegex trains the model by maximizing the expected semantic correctness of the generated regular expressions. The semantic correctness is measured using the DFA-equivalence oracle, random test cases, and distinguishing test cases. The experiments on three public datasets demonstrate the superiority of SemRegex over the existing state-of-the-art approaches. |
Tasks | Program Synthesis |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1189/ |
https://www.aclweb.org/anthology/D18-1189 | |
PWC | https://paperswithcode.com/paper/semregex-a-semantics-based-approach-for |
Repo | |
Framework | |
From Information Bottleneck To Activation Norm Penalty
Title | From Information Bottleneck To Activation Norm Penalty |
Authors | Allen Nie, Mihir Mongia, James Zou |
Abstract | Many regularization methods have been proposed to prevent overfitting in neural networks. Recently, a regularization method has been proposed to optimize the variational lower bound of the Information Bottleneck Lagrangian. However, this method cannot be generalized to regular neural network architectures. We present the activation norm penalty that is derived from the information bottleneck principle and is theoretically grounded in a variation dropout framework. Unlike in previous literature, it can be applied to any general neural network. We demonstrate that this penalty can give consistent improvements to different state of the art architectures both in language modeling and image classification. We present analyses on the properties of this penalty and compare it to other methods that also reduce mutual information. |
Tasks | Image Classification, Language Modelling |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=SySpa-Z0Z |
https://openreview.net/pdf?id=SySpa-Z0Z | |
PWC | https://paperswithcode.com/paper/from-information-bottleneck-to-activation |
Repo | |
Framework | |
Classifying Sluice Occurrences in Dialogue
Title | Classifying Sluice Occurrences in Dialogue |
Authors | Austin Baird, Anissa Hamza, Daniel Hardt |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1249/ |
https://www.aclweb.org/anthology/L18-1249 | |
PWC | https://paperswithcode.com/paper/classifying-sluice-occurrences-in-dialogue |
Repo | |
Framework | |
Deterministic Policy Imitation Gradient Algorithm
Title | Deterministic Policy Imitation Gradient Algorithm |
Authors | Fumihiro Sasaki, Atsuo Kawaguchi |
Abstract | The goal of imitation learning (IL) is to enable a learner to imitate an expert’s behavior given the expert’s demonstrations. Recently, generative adversarial imitation learning (GAIL) has successfully achieved it even on complex continuous control tasks. However, GAIL requires a huge number of interactions with environment during training. We believe that IL algorithm could be more applicable to the real-world environments if the number of interactions could be reduced. To this end, we propose a model free, off-policy IL algorithm for continuous control. The keys of our algorithm are two folds: 1) adopting deterministic policy that allows us to derive a novel type of policy gradient which we call deterministic policy imitation gradient (DPIG), 2) introducing a function which we call state screening function (SSF) to avoid noisy policy updates with states that are not typical of those appeared on the expert’s demonstrations. Experimental results show that our algorithm can achieve the goal of IL with at least tens of times less interactions than GAIL on a variety of continuous control tasks. |
Tasks | Continuous Control, Imitation Learning |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rJ3fy0k0Z |
https://openreview.net/pdf?id=rJ3fy0k0Z | |
PWC | https://paperswithcode.com/paper/deterministic-policy-imitation-gradient |
Repo | |
Framework | |
Oral-Motor and Lexical Diversity During Naturalistic Conversations in Adults with Autism Spectrum Disorder
Title | Oral-Motor and Lexical Diversity During Naturalistic Conversations in Adults with Autism Spectrum Disorder |
Authors | Julia Parish-Morris, Evangelos Sariyanidi, Casey Zampella, G. Keith Bartley, Emily Ferguson, Ashley A. Pallathra, Leila Bateman, Samantha Plate, Meredith Cola, P, Juhi ey, Edward S. Brodkin, Robert T. Schultz, Birkan Tun{\c{c}} |
Abstract | Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by impaired social communication and the presence of restricted, repetitive patterns of behaviors and interests. Prior research suggests that restricted patterns of behavior in ASD may be cross-domain phenomena that are evident in a variety of modalities. Computational studies of language in ASD provide support for the existence of an underlying dimension of restriction that emerges during a conversation. Similar evidence exists for restricted patterns of facial movement. Using tools from computational linguistics, computer vision, and information theory, this study tests whether cognitive-motor restriction can be detected across multiple behavioral domains in adults with ASD during a naturalistic conversation. Our methods identify restricted behavioral patterns, as measured by entropy in word use and mouth movement. Results suggest that adults with ASD produce significantly less diverse mouth movements and words than neurotypical adults, with an increased reliance on repeated patterns in both domains. The diversity values of the two domains are not significantly correlated, suggesting that they provide complementary information. |
Tasks | Decision Making |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0616/ |
https://www.aclweb.org/anthology/W18-0616 | |
PWC | https://paperswithcode.com/paper/oral-motor-and-lexical-diversity-during |
Repo | |
Framework | |
Dynamics of an idiostyle of a Russian suicidal blogger
Title | Dynamics of an idiostyle of a Russian suicidal blogger |
Authors | Tatiana Litvinova, Olga Litvinova, Pavel Seredin |
Abstract | Over 800000 people die of suicide each year. It is es-timated that by the year 2020, this figure will have in-creased to 1.5 million. It is considered to be one of the major causes of mortality during adolescence. Thus there is a growing need for methods of identifying su-icidal individuals. Language analysis is known to be a valuable psychodiagnostic tool, however the material for such an analysis is not easy to obtain. Currently as the Internet communications are developing, there is an opportunity to study texts of suicidal individuals. Such an analysis can provide a useful insight into the peculiarities of suicidal thinking, which can be used to further develop methods for diagnosing the risk of suicidal behavior. The paper analyzes the dynamics of a number of linguistic parameters of an idiostyle of a Russian-language blogger who died by suicide. For the first time such an analysis has been conducted using the material of Russian online texts. For text processing, the LIWC program is used. A correlation analysis was performed to identify the relationship between LIWC variables and number of days prior to suicide. Data visualization, as well as comparison with the results of related studies was performed. |
Tasks | Text Classification |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0617/ |
https://www.aclweb.org/anthology/W18-0617 | |
PWC | https://paperswithcode.com/paper/dynamics-of-an-idiostyle-of-a-russian |
Repo | |
Framework | |
Fine-Grained Discourse Structures in Continuation Semantics
Title | Fine-Grained Discourse Structures in Continuation Semantics |
Authors | Timoth{'e}e Bernard |
Abstract | In this work, we are interested in the computation of logical representations of discourse. We argue that all discourse connectives are anaphors obeying different sets of constraints and show how this view allows one to account for the semantically parenthetical use of attitude verbs and verbs of report (e.g., think, say) and for sequences of conjunctions (A CONJ{_}1 B CONJ{_}2 C). We implement this proposal in event semantics using de Groote (2006){'}s dynamic framework. |
Tasks | Machine Translation, Question Answering |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-5034/ |
https://www.aclweb.org/anthology/W18-5034 | |
PWC | https://paperswithcode.com/paper/fine-grained-discourse-structures-in |
Repo | |
Framework | |
Rating Distributions and Bayesian Inference: Enhancing Cognitive Models of Spatial Language Use
Title | Rating Distributions and Bayesian Inference: Enhancing Cognitive Models of Spatial Language Use |
Authors | Thomas Kluth, Holger Schultheis |
Abstract | We present two methods that improve the assessment of cognitive models. The first method is applicable to models computing average acceptability ratings. For these models, we propose an extension that simulates a full rating distribution (instead of average ratings) and allows generating individual ratings. Our second method enables Bayesian inference for models generating individual data. To this end, we propose to use the cross-match test (Rosenbaum, 2005) as a likelihood function. We exemplarily present both methods using cognitive models from the domain of spatial language use. For spatial language use, determining linguistic acceptability judgments of a spatial preposition for a depicted spatial relation is assumed to be a crucial process (Logan and Sadler, 1996). Existing models of this process compute an average acceptability rating. We extend the models and {–} based on existing data {–} show that the extended models allow extracting more information from the empirical data and yield more readily interpretable information about model successes and failures. Applying Bayesian inference, we find that model performance relies less on mechanisms of capturing geometrical aspects than on mapping the captured geometry to a rating interval. |
Tasks | Bayesian Inference, Linguistic Acceptability |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-2807/ |
https://www.aclweb.org/anthology/W18-2807 | |
PWC | https://paperswithcode.com/paper/rating-distributions-and-bayesian-inference |
Repo | |
Framework | |
Generating Topic-Oriented Summaries Using Neural Attention
Title | Generating Topic-Oriented Summaries Using Neural Attention |
Authors | Kundan Krishna, Balaji Vasan Srinivasan |
Abstract | Summarizing a document requires identifying the important parts of the document with an objective of providing a quick overview to a reader. However, a long article can span several topics and a single summary cannot do justice to all the topics. Further, the interests of readers can vary and the notion of importance can change across them. Existing summarization algorithms generate a single summary and are not capable of generating multiple summaries tuned to the interests of the readers. In this paper, we propose an attention based RNN framework to generate multiple summaries of a single document tuned to different topics of interest. Our method outperforms existing baselines and our results suggest that the attention of generative networks can be successfully biased to look at sentences relevant to a topic and effectively used to generate topic-tuned summaries. |
Tasks | Abstractive Text Summarization, Text Summarization |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-1153/ |
https://www.aclweb.org/anthology/N18-1153 | |
PWC | https://paperswithcode.com/paper/generating-topic-oriented-summaries-using |
Repo | |
Framework | |
Simple Nearest Neighbor Policy Method for Continuous Control Tasks
Title | Simple Nearest Neighbor Policy Method for Continuous Control Tasks |
Authors | Elman Mansimov, Kyunghyun Cho |
Abstract | We design a new policy, called a nearest neighbor policy, that does not require any optimization for simple, low-dimensional continuous control tasks. As this policy does not require any optimization, it allows us to investigate the underlying difficulty of a task without being distracted by optimization difficulty of a learning algorithm. We propose two variants, one that retrieves an entire trajectory based on a pair of initial and goal states, and the other retrieving a partial trajectory based on a pair of current and goal states. We test the proposed policies on five widely-used benchmark continuous control tasks with a sparse reward: Reacher, Half Cheetah, Double Pendulum, Cart Pole and Mountain Car. We observe that the majority (the first four) of these tasks, which have been considered difficult, are easily solved by the proposed policies with high success rates, indicating that reported difficulties of them may have likely been due to the optimization difficulty. Our work suggests that it is necessary to evaluate any sophisticated policy learning algorithm on more challenging problems in order to truly assess the advances from them. |
Tasks | Continuous Control |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=ByL48G-AW |
https://openreview.net/pdf?id=ByL48G-AW | |
PWC | https://paperswithcode.com/paper/simple-nearest-neighbor-policy-method-for |
Repo | |
Framework | |
Disambiguated skip-gram model
Title | Disambiguated skip-gram model |
Authors | Karol Grzegorczyk, Marcin Kurdziel |
Abstract | We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and a word sense disambiguation model. Unlike previous probabilistic models for learning multi-sense word embeddings, disambiguated skip-gram is end-to-end differentiable and can be interpreted as a simple feed-forward neural network. We also introduce an effective pruning strategy for the embeddings learned by disambiguated skip-gram. This allows us to control the granularity of representations learned by our model. In experimental evaluation disambiguated skip-gram improves state-of-the are results in several word sense induction benchmarks. |
Tasks | Image Captioning, Word Embeddings, Word Sense Disambiguation, Word Sense Induction |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1174/ |
https://www.aclweb.org/anthology/D18-1174 | |
PWC | https://paperswithcode.com/paper/disambiguated-skip-gram-model |
Repo | |
Framework | |
Feat2Vec: Dense Vector Representation for Data with Arbitrary Features
Title | Feat2Vec: Dense Vector Representation for Data with Arbitrary Features |
Authors | Luis Armona, José P. González-Brenes, Ralph Edezhath |
Abstract | Methods that calculate dense vector representations for features in unstructured data—such as words in a document—have proven to be very successful for knowledge representation. We study how to estimate dense representations when multiple feature types exist within a dataset for supervised learning where explicit labels are available, as well as for unsupervised learning where there are no labels. Feat2Vec calculates embeddings for data with multiple feature types enforcing that all different feature types exist in a common space. In the supervised case, we show that our method has advantages over recently proposed methods; such as enabling higher prediction accuracy, and providing a way to avoid the cold-start problem. In the unsupervised case, our experiments suggest that Feat2Vec significantly outperforms existing algorithms that do not leverage the structure of the data. We believe that we are the first to propose a method for learning unsuper vised embeddings that leverage the structure of multiple feature types. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rkZzY-lCb |
https://openreview.net/pdf?id=rkZzY-lCb | |
PWC | https://paperswithcode.com/paper/feat2vec-dense-vector-representation-for-data |
Repo | |
Framework | |
Topic-Based Question Generation
Title | Topic-Based Question Generation |
Authors | Wenpeng Hu, Bing Liu, Rui Yan, Dongyan Zhao, Jinwen Ma |
Abstract | Asking questions is an important ability for a chatbot. This paper focuses on question generation. Although there are existing works on question generation based on a piece of descriptive text, it remains to be a very challenging problem. In the paper, we propose a new question generation problem, which also requires the input of a target topic in addition to a piece of descriptive text. The key reason for proposing the new problem is that in practical applications, we found that useful questions need to be targeted toward some relevant topics. One almost never asks a random question in a conversation. Due to the fact that given a descriptive text, it is often possible to ask many types of questions, generating a question without knowing what it is about is of limited use. To solve the problem, we propose a novel neural network that is able to generate topic-specific questions. One major advantage of this model is that it can be trained directly using a question-answering corpus without requiring any additional annotations like annotating topics in the questions or answers. Experimental results show that our model outperforms the state-of-the-art baseline. |
Tasks | Chatbot, Question Answering, Question Generation |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rk3pnae0b |
https://openreview.net/pdf?id=rk3pnae0b | |
PWC | https://paperswithcode.com/paper/topic-based-question-generation |
Repo | |
Framework | |
Amrita_student at SemEval-2018 Task 1: Distributed Representation of Social Media Text for Affects in Tweets
Title | Amrita_student at SemEval-2018 Task 1: Distributed Representation of Social Media Text for Affects in Tweets |
Authors | Nidhin A Unnithan, Shalini K., Barathi Ganesh H. B., An Kumar M, , Soman K. P. |
Abstract | In this paper we did an analysis of {``}Affects in Tweets{''} which was one of the task conducted by semeval 2018. Task was to build a model which is able to do regression and classification of different emotions from the given tweets data set. We developed a base model for all the subtasks using distributed representation (Doc2Vec) and applied machine learning techniques for classification and regression. Distributed representation is an unsupervised algorithm which is capable of learning fixed length feature representation from variable length texts. Machine learning techniques used for regression is {'}Linear Regression{'} while {'}Random Forest Tree{'} is used for classification purpose. Empirical results obtained for all the subtasks by our model are shown in this paper. | |
Tasks | Emotion Classification, Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1047/ |
https://www.aclweb.org/anthology/S18-1047 | |
PWC | https://paperswithcode.com/paper/amrita_student-at-semeval-2018-task-1 |
Repo | |
Framework | |