Paper Group NANR 171
Obituary: In Memoriam: Susan Armstrong. Optimal Tagging with Markov Chain Optimization. Annotation of causal and aspectual structure of events in RED: a preliminary report. Individual Differences in Strategic Deception. Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories. Alternations: From Lexicon to Grammar And …
Obituary: In Memoriam: Susan Armstrong
| Title | Obituary: In Memoriam: Susan Armstrong |
| Authors | Pierrette Bouillon, Paola Merlo, Gertjan van Noord, Mike Rosner |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/J16-2007/ |
| https://www.aclweb.org/anthology/J16-2007 | |
| PWC | https://paperswithcode.com/paper/obituary-in-memoriam-susan-armstrong |
| Repo | |
| Framework | |
Optimal Tagging with Markov Chain Optimization
| Title | Optimal Tagging with Markov Chain Optimization |
| Authors | Nir Rosenfeld, Amir Globerson |
| Abstract | Many information systems use tags and keywords to describe and annotate content. These allow for efficient organization and categorization of items, as well as facilitate relevant search queries. As such, the selected set of tags for an item can have a considerable effect on the volume of traffic that eventually reaches an item. In tagging systems where tags are exclusively chosen by an item’s owner, who in turn is interested in maximizing traffic, a principled approach for assigning tags can prove valuable. In this paper we introduce the problem of optimal tagging, where the task is to choose a subset of tags for a new item such that the probability of browsing users reaching that item is maximized. We formulate the problem by modeling traffic using a Markov chain, and asking how transitions in this chain should be modified to maximize traffic into a certain state of interest. The resulting optimization problem involves maximizing a certain function over subsets, under a cardinality constraint. We show that the optimization problem is NP-hard, but has a (1-1/e)-approximation via a simple greedy algorithm due to monotonicity and submodularity. Furthermore, the structure of the problem allows for an efficient computation of the greedy step. To demonstrate the effectiveness of our method, we perform experiments on three tagging datasets, and show that the greedy algorithm outperforms other baselines. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6041-optimal-tagging-with-markov-chain-optimization |
| http://papers.nips.cc/paper/6041-optimal-tagging-with-markov-chain-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-tagging-with-markov-chain |
| Repo | |
| Framework | |
Annotation of causal and aspectual structure of events in RED: a preliminary report
| Title | Annotation of causal and aspectual structure of events in RED: a preliminary report |
| Authors | William Croft, Pavlina Pe{\v{s}}kov{'a}, Michael Regan |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1002/ |
| https://www.aclweb.org/anthology/W16-1002 | |
| PWC | https://paperswithcode.com/paper/annotation-of-causal-and-aspectual-structure |
| Repo | |
| Framework | |
Individual Differences in Strategic Deception
| Title | Individual Differences in Strategic Deception |
| Authors | Scott Appling, Erica Briscoe |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0807/ |
| https://www.aclweb.org/anthology/W16-0807 | |
| PWC | https://paperswithcode.com/paper/individual-differences-in-strategic-deception |
| Repo | |
| Framework | |
Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories
| Title | Parallel Global Voices: a Collection of Multilingual Corpora with Citizen Media Stories |
| Authors | Prokopis Prokopidis, Vassilis Papavassiliou, Stelios Piperidis |
| Abstract | We present a new collection of multilingual corpora automatically created from the content available in the Global Voices websites, where volunteers have been posting and translating citizen media stories since 2004. We describe how we crawled and processed this content to generate parallel resources comprising 302.6K document pairs and 8.36M segment alignments in 756 language pairs. For some language pairs, the segment alignments in this resource are the first open examples of their kind. In an initial use of this resource, we discuss how a set of document pair detection algorithms performs on the Greek-English corpus. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1144/ |
| https://www.aclweb.org/anthology/L16-1144 | |
| PWC | https://paperswithcode.com/paper/parallel-global-voices-a-collection-of |
| Repo | |
| Framework | |
Alternations: From Lexicon to Grammar And Back Again
| Title | Alternations: From Lexicon to Grammar And Back Again |
| Authors | Mark{'e}ta Lopatkov{'a}, V{'a}clava Kettnerov{'a} |
| Abstract | An excellent example of a phenomenon bridging a lexicon and a grammar is provided by grammaticalized alternations (e.g., passivization, reflexivity, and reciprocity): these alternations represent productive grammatical processes which are, however, lexically determined. While grammaticalized alternations keep lexical meaning of verbs unchanged, they are usually characterized by various changes in their morphosyntactic structure. In this contribution, we demonstrate on the example of reciprocity and its representation in the valency lexicon of Czech verbs, VALLEX how a linguistic description of complex (and still systemic) changes characteristic of grammaticalized alternations can benefit from an integration of grammatical rules into a valency lexicon. In contrast to other types of grammaticalized alternations, reciprocity in Czech has received relatively little attention although it closely interacts with various linguistic phenomena (e.g., with light verbs, diatheses, and reflexivity). |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3804/ |
| https://www.aclweb.org/anthology/W16-3804 | |
| PWC | https://paperswithcode.com/paper/alternations-from-lexicon-to-grammar-and-back |
| Repo | |
| Framework | |
Efficient state-space modularization for planning: theory, behavioral and neural signatures
| Title | Efficient state-space modularization for planning: theory, behavioral and neural signatures |
| Authors | Daniel Mcnamee, Daniel M. Wolpert, Mate Lengyel |
| Abstract | Even in state-spaces of modest size, planning is plagued by the “curse of dimensionality”. This problem is particularly acute in human and animal cognition given the limited capacity of working memory, and the time pressures under which planning often occurs in the natural environment. Hierarchically organized modular representations have long been suggested to underlie the capacity of biological systems to efficiently and flexibly plan in complex environments. However, the principles underlying efficient modularization remain obscure, making it difficult to identify its behavioral and neural signatures. Here, we develop a normative theory of efficient state-space representations which partitions an environment into distinct modules by minimizing the average (information theoretic) description length of planning within the environment, thereby optimally trading off the complexity of planning across and within modules. We show that such optimal representations provide a unifying account for a diverse range of hitherto unrelated phenomena at multiple levels of behavior and neural representation. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6320-efficient-state-space-modularization-for-planning-theory-behavioral-and-neural-signatures |
| http://papers.nips.cc/paper/6320-efficient-state-space-modularization-for-planning-theory-behavioral-and-neural-signatures.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-state-space-modularization-for |
| Repo | |
| Framework | |
Bayesian optimization for automated model selection
| Title | Bayesian optimization for automated model selection |
| Authors | Gustavo Malkomes, Charles Schaff, Roman Garnett |
| Abstract | Despite the success of kernel-based nonparametric methods, kernel selection still requires considerable expertise, and is often described as a “black art.” We present a sophisticated method for automatically searching for an appropriate kernel from an infinite space of potential choices. Previous efforts in this direction have focused on traversing a kernel grammar, only examining the data via computation of marginal likelihood. Our proposed search method is based on Bayesian optimization in model space, where we reason about model evidence as a function to be maximized. We explicitly reason about the data distribution and how it induces similarity between potential model choices in terms of the explanations they can offer for observed data. In this light, we construct a novel kernel between models to explain a given dataset. Our method is capable of finding a model that explains a given dataset well without any human assistance, often with fewer computations of model evidence than previous approaches, a claim we demonstrate empirically. |
| Tasks | Model Selection |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6466-bayesian-optimization-for-automated-model-selection |
| http://papers.nips.cc/paper/6466-bayesian-optimization-for-automated-model-selection.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-for-automated-model |
| Repo | |
| Framework | |
Ranking Responses Oriented to Conversational Relevance in Chat-bots
| Title | Ranking Responses Oriented to Conversational Relevance in Chat-bots |
| Authors | Bowen Wu, Baoxun Wang, Hui Xue |
| Abstract | For automatic chatting systems, it is indeed a great challenge to reply the given query considering the conversation history, rather than based on the query only. This paper proposes a deep neural network to address the context-aware response ranking problem by end-to-end learning, so as to help to select conversationally relevant candidate. By combining the multi-column convolutional layer and the recurrent layer, our model is able to model the semantics of the utterance sequence by grasping the semantic clue within the conversation, on the basis of the effective representation for each sentence. Especially, the network utilizes attention pooling to further emphasis the importance of essential words in conversations, thus the representations of contexts tend to be more meaningful and the performance of candidate ranking is notably improved. Meanwhile, due to the adoption of attention pooling, it is possible to visualize the semantic clues. The experimental results on the large amount of conversation data from social media have shown that our approach is promising for quantifying the conversational relevance of responses, and indicated its good potential for building practical IR based chat-bots. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1063/ |
| https://www.aclweb.org/anthology/C16-1063 | |
| PWC | https://paperswithcode.com/paper/ranking-responses-oriented-to-conversational |
| Repo | |
| Framework | |
Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
| Title | Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2000/ |
| https://www.aclweb.org/anthology/W16-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-14th-sigmorphon-workshop |
| Repo | |
| Framework | |
Detection of Alzheimer’s disease based on automatic analysis of common objects descriptions
| Title | Detection of Alzheimer’s disease based on automatic analysis of common objects descriptions |
| Authors | Laura Hern{'a}ndez-Dom{'\i}nguez, Edgar Garc{'\i}a-Cano, Sylvie Ratt{'e}, Gerardo Sierra-Mart{'\i}nez |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1902/ |
| https://www.aclweb.org/anthology/W16-1902 | |
| PWC | https://paperswithcode.com/paper/detection-of-alzheimers-disease-based-on |
| Repo | |
| Framework | |
Breaking the Closed World Assumption in Text Classification
| Title | Breaking the Closed World Assumption in Text Classification |
| Authors | Geli Fei, Bing Liu |
| Abstract | |
| Tasks | Text Classification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1061/ |
| https://www.aclweb.org/anthology/N16-1061 | |
| PWC | https://paperswithcode.com/paper/breaking-the-closed-world-assumption-in-text |
| Repo | |
| Framework | |
Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution
| Title | Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution |
| Authors | Christopher Lynn, Daniel D. Lee |
| Abstract | Influence maximization in social networks has typically been studied in the context of contagion models and irreversible processes. In this paper, we consider an alternate model that treats individual opinions as spins in an Ising system at dynamic equilibrium. We formalize the \textit{Ising influence maximization} problem, which has a natural physical interpretation as maximizing the magnetization given a budget of external magnetic field. Under the mean-field (MF) approximation, we present a gradient ascent algorithm that uses the susceptibility to efficiently calculate local maxima of the magnetization, and we develop a number of sufficient conditions for when the MF magnetization is concave and our algorithm converges to a global optimum. We apply our algorithm on random and real-world networks, demonstrating, remarkably, that the MF optimal external fields (i.e., the external fields which maximize the MF magnetization) exhibit a phase transition from focusing on high-degree individuals at high temperatures to focusing on low-degree individuals at low temperatures. We also establish a number of novel results about the structure of steady-states in the ferromagnetic MF Ising model on general graphs, which are of independent interest. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6119-maximizing-influence-in-an-ising-network-a-mean-field-optimal-solution |
| http://papers.nips.cc/paper/6119-maximizing-influence-in-an-ising-network-a-mean-field-optimal-solution.pdf | |
| PWC | https://paperswithcode.com/paper/maximizing-influence-in-an-ising-network-a |
| Repo | |
| Framework | |
A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance
| Title | A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance |
| Authors | Felix Burkhardt, Uwe D. Reichel |
| Abstract | Current state-of-the-art speech synthesizers for domain-independent systems still struggle with the challenge of generating understandable and natural-sounding speech. This is mainly because the pronunciation of words of foreign origin, inflections and compound words often cannot be handled by rules. Furthermore there are too many of these for inclusion in exception dictionaries. We describe an approach to evaluating text-to-speech synthesizers with a subjective listening experiment. The focus is to differentiate between known problem classes for speech synthesizers. The target language is German but we believe that many of the described phenomena are not language specific. We distinguish the following problem categories: Normalization, Foreign linguistics, Natural writing, Language specific and General. Each of them is divided into five to three problem classes. Word lists for each of the above mentioned categories were compiled and synthesized by both a commercial and an open source synthesizer, both being based on the non-uniform unit-selection approach. The synthesized speech was evaluated by human judges using the Speechalyzer toolkit and the results are discussed. It shows that, as expected, the commercial synthesizer performs much better than the open-source one, and especially words of foreign origin were pronounced badly by both systems. |
| Tasks | Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1118/ |
| https://www.aclweb.org/anthology/L16-1118 | |
| PWC | https://paperswithcode.com/paper/a-taxonomy-of-specific-problem-classes-in |
| Repo | |
| Framework | |
Extraction and Recognition of Polish Multiword Expressions using Wikipedia and Finite-State Automata
| Title | Extraction and Recognition of Polish Multiword Expressions using Wikipedia and Finite-State Automata |
| Authors | Pawe{\l} Chrz{\k{a}}szcz |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1815/ |
| https://www.aclweb.org/anthology/W16-1815 | |
| PWC | https://paperswithcode.com/paper/extraction-and-recognition-of-polish |
| Repo | |
| Framework | |
