Paper Group NANR 71
Tokyo Metropolitan University Neural Machine Translation System for WAT 2017. Discourse-Wide Extraction of Assay Frames from the Biological Literature. ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization. Interactive Learning of Grounded Verb Semantics towards Human-Robot Communication. A Hierarchical Neural Mo …
Tokyo Metropolitan University Neural Machine Translation System for WAT 2017
| Title | Tokyo Metropolitan University Neural Machine Translation System for WAT 2017 |
| Authors | Yukio Matsumura, Mamoru Komachi |
| Abstract | In this paper, we describe our neural machine translation (NMT) system, which is based on the attention-based NMT and uses long short-term memories (LSTM) as RNN. We implemented beam search and ensemble decoding in the NMT system. The system was tested on the 4th Workshop on Asian Translation (WAT 2017) shared tasks. In our experiments, we participated in the scientific paper subtasks and attempted Japanese-English, English-Japanese, and Japanese-Chinese translation tasks. The experimental results showed that implementation of beam search and ensemble decoding can effectively improve the translation quality. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5716/ |
| https://www.aclweb.org/anthology/W17-5716 | |
| PWC | https://paperswithcode.com/paper/tokyo-metropolitan-university-neural-machine |
| Repo | |
| Framework | |
Discourse-Wide Extraction of Assay Frames from the Biological Literature
| Title | Discourse-Wide Extraction of Assay Frames from the Biological Literature |
| Authors | Dayne Freitag, Paul Kalmar, Eric Yeh |
| Abstract | We consider the problem of populating multi-part knowledge frames from textual information distributed over multiple sentences in a document. We present a corpus constructed by aligning papers from the cellular signaling literature to a collection of approximately 50,000 reference frames curated by hand as part of a decade-long project. We present and evaluate two approaches to the challenging problem of reconstructing these frames, which formalize biological assays described in the literature. One approach is based on classifying candidate records nominated by sentence-local entity co-occurrence. In the second approach, we introduce a novel virtual register machine traverses an article and generates frames, trained on our reference data. Our evaluations show that success in the task ultimately hinges on an integration of evidence spread across the discourse. |
| Tasks | Reading Comprehension, Relation Extraction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8003/ |
| https://doi.org/10.26615/978-954-452-044-1_003 | |
| PWC | https://paperswithcode.com/paper/discourse-wide-extraction-of-assay-frames |
| Repo | |
| Framework | |
ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization
| Title | ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization |
| Authors | Yi Xu, Mingrui Liu, Qihang Lin, Tianbao Yang |
| Abstract | Alternating direction method of multipliers (ADMM) has received tremendous interest for solving numerous problems in machine learning, statistics and signal processing. However, it is known that the performance of ADMM and many of its variants is very sensitive to the penalty parameter of a quadratic penalty applied to the equality constraints. Although several approaches have been proposed for dynamically changing this parameter during the course of optimization, they do not yield theoretical improvement in the convergence rate and are not directly applicable to stochastic ADMM. In this paper, we develop a new ADMM and its linearized variant with a new adaptive scheme to update the penalty parameter. Our methods can be applied under both deterministic and stochastic optimization settings for structured non-smooth objective function. The novelty of the proposed scheme lies at that it is adaptive to a local sharpness property of the objective function, which marks the key difference from previous adaptive scheme that adjusts the penalty parameter per-iteration based on certain conditions on iterates. On theoretical side, given the local sharpness characterized by an exponent $\theta\in(0, 1]$, we show that the proposed ADMM enjoys an improved iteration complexity of $\widetilde O(1/\epsilon^{1-\theta})$\footnote{$\widetilde O()$ suppresses a logarithmic factor.} in the deterministic setting and an iteration complexity of $\widetilde O(1/\epsilon^{2(1-\theta)})$ in the stochastic setting without smoothness and strong convexity assumptions. The complexity in either setting improves that of the standard ADMM which only uses a fixed penalty parameter. On the practical side, we demonstrate that the proposed algorithms converge comparably to, if not much faster than, ADMM with a fine-tuned fixed penalty parameter. |
| Tasks | Stochastic Optimization |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6726-admm-without-a-fixed-penalty-parameter-faster-convergence-with-new-adaptive-penalization |
| http://papers.nips.cc/paper/6726-admm-without-a-fixed-penalty-parameter-faster-convergence-with-new-adaptive-penalization.pdf | |
| PWC | https://paperswithcode.com/paper/admm-without-a-fixed-penalty-parameter-faster |
| Repo | |
| Framework | |
Interactive Learning of Grounded Verb Semantics towards Human-Robot Communication
| Title | Interactive Learning of Grounded Verb Semantics towards Human-Robot Communication |
| Authors | Lanbo She, Joyce Chai |
| Abstract | To enable human-robot communication and collaboration, previous works represent grounded verb semantics as the potential change of state to the physical world caused by these verbs. Grounded verb semantics are acquired mainly based on the parallel data of the use of a verb phrase and its corresponding sequences of primitive actions demonstrated by humans. The rich interaction between teachers and students that is considered important in learning new skills has not yet been explored. To address this limitation, this paper presents a new interactive learning approach that allows robots to proactively engage in interaction with human partners by asking good questions to learn models for grounded verb semantics. The proposed approach uses reinforcement learning to allow the robot to acquire an optimal policy for its question-asking behaviors by maximizing the long-term reward. Our empirical results have shown that the interactive learning approach leads to more reliable models for grounded verb semantics, especially in the noisy environment which is full of uncertainties. Compared to previous work, the models acquired from interactive learning result in a 48{%} to 145{%} performance gain when applied in new situations. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1150/ |
| https://www.aclweb.org/anthology/P17-1150 | |
| PWC | https://paperswithcode.com/paper/interactive-learning-of-grounded-verb |
| Repo | |
| Framework | |
A Hierarchical Neural Model for Learning Sequences of Dialogue Acts
| Title | A Hierarchical Neural Model for Learning Sequences of Dialogue Acts |
| Authors | Quan Hung Tran, Ingrid Zukerman, Gholamreza Haffari |
| Abstract | We propose a novel hierarchical Recurrent Neural Network (RNN) for learning sequences of Dialogue Acts (DAs). The input in this task is a sequence of utterances (i.e., conversational contributions) comprising a sequence of tokens, and the output is a sequence of DA labels (one label per utterance). Our model leverages the hierarchical nature of dialogue data by using two nested RNNs that capture long-range dependencies at the dialogue level and the utterance level. This model is combined with an attention mechanism that focuses on salient tokens in utterances. Our experimental results show that our model outperforms strong baselines on two popular datasets, Switchboard and MapTask; and our detailed empirical analysis highlights the impact of each aspect of our model. |
| Tasks | Machine Translation, Part-Of-Speech Tagging, Speech Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1041/ |
| https://www.aclweb.org/anthology/E17-1041 | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-neural-model-for-learning |
| Repo | |
| Framework | |
Combining the output of two coreference resolution systems for two source languages to improve annotation projection
| Title | Combining the output of two coreference resolution systems for two source languages to improve annotation projection |
| Authors | Yulia Grishina |
| Abstract | Although parallel coreference corpora can to a high degree support the development of SMT systems, there are no large-scale parallel datasets available due to the complexity of the annotation task and the variability in annotation schemes. In this study, we exploit an annotation projection method to combine the output of two coreference resolution systems for two different source languages (English, German) in order to create an annotated corpus for a third language (Russian). We show that our technique is superior to projecting annotations from a single source language, and we provide an in-depth analysis of the projected annotations in order to assess the perspectives of our approach. |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4809/ |
| https://www.aclweb.org/anthology/W17-4809 | |
| PWC | https://paperswithcode.com/paper/combining-the-output-of-two-coreference |
| Repo | |
| Framework | |
UCCAApp: Web-application for Syntactic and Semantic Phrase-based Annotation
| Title | UCCAApp: Web-application for Syntactic and Semantic Phrase-based Annotation |
| Authors | Omri Abend, Shai Yerushalmi, Ari Rappoport |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4019/ |
| https://www.aclweb.org/anthology/P17-4019 | |
| PWC | https://paperswithcode.com/paper/uccaapp-web-application-for-syntactic-and |
| Repo | |
| Framework | |
VecShare: A Framework for Sharing Word Representation Vectors
| Title | VecShare: A Framework for Sharing Word Representation Vectors |
| Authors | Fern, Jared ez, Zhaocheng Yu, Doug Downey |
| Abstract | Many Natural Language Processing (NLP) models rely on distributed vector representations of words. Because the process of training word vectors can require large amounts of data and computation, NLP researchers and practitioners often utilize pre-trained embeddings downloaded from the Web. However, finding the best embeddings for a given task is difficult, and can be computationally prohibitive. We present a framework, called VecShare, that makes it easy to share and retrieve word embeddings on the Web. The framework leverages a public data-sharing infrastructure to host embedding sets, and provides automated mechanisms for retrieving the embeddings most similar to a given corpus. We perform an experimental evaluation of VecShare{'}s similarity strategies, and show that they are effective at efficiently retrieving embeddings that boost accuracy in a document classification task. Finally, we provide an open-source Python library for using the VecShare framework. |
| Tasks | Document Classification, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1032/ |
| https://www.aclweb.org/anthology/D17-1032 | |
| PWC | https://paperswithcode.com/paper/vecshare-a-framework-for-sharing-word |
| Repo | |
| Framework | |
Reflexives and Reciprocals in Synchronous Tree Adjoining Grammar
| Title | Reflexives and Reciprocals in Synchronous Tree Adjoining Grammar |
| Authors | Cristina Aggazzotti, Stuart M. Shieber |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6204/ |
| https://www.aclweb.org/anthology/W17-6204 | |
| PWC | https://paperswithcode.com/paper/reflexives-and-reciprocals-in-synchronous |
| Repo | |
| Framework | |
Human Centered NLP with User-Factor Adaptation
| Title | Human Centered NLP with User-Factor Adaptation |
| Authors | Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian, H. Andrew Schwartz |
| Abstract | We pose the general task of user-factor adaptation {–} adapting supervised learning models to real-valued user factors inferred from a background of their language, reflecting the idea that a piece of text should be understood within the context of the user that wrote it. We introduce a continuous adaptation technique, suited for real-valued user factors that are common in social science and bringing us closer to personalized NLP, adapting to each user uniquely. We apply this technique with known user factors including age, gender, and personality traits, as well as latent factors, evaluating over five tasks: POS tagging, PP-attachment, sentiment analysis, sarcasm detection, and stance detection. Adaptation provides statistically significant benefits for 3 of the 5 tasks: up to +1.2 points for PP-attachment, +3.4 points for sarcasm, and +3.0 points for stance. |
| Tasks | Document Classification, Domain Adaptation, Sarcasm Detection, Sentiment Analysis, Stance Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1119/ |
| https://www.aclweb.org/anthology/D17-1119 | |
| PWC | https://paperswithcode.com/paper/human-centered-nlp-with-user-factor |
| Repo | |
| Framework | |
GRASP: Rich Patterns for Argumentation Mining
| Title | GRASP: Rich Patterns for Argumentation Mining |
| Authors | Eyal Shnarch, Ran Levy, Vikas Raykar, Noam Slonim |
| Abstract | GRASP (GReedy Augmented Sequential Patterns) is an algorithm for automatically extracting patterns that characterize subtle linguistic phenomena. To that end, GRASP augments each term of input text with multiple layers of linguistic information. These different facets of the text terms are systematically combined to reveal rich patterns. We report highly promising experimental results in several challenging text analysis tasks within the field of Argumentation Mining. We believe that GRASP is general enough to be useful for other domains too. For example, each of the following sentences includes a claim for a [topic]: 1. Opponents often argue that the open primary is unconstitutional. [Open Primaries] 2. Prof. Smith suggested that affirmative action devalues the accomplishments of the chosen. [Affirmative Action] 3. The majority stated that the First Amendment does not guarantee the right to offend others. [Freedom of Speech] These sentences share almost no words in common, however, they are similar at a more abstract level. A human observer may notice the following underlying common structure, or pattern: [someone][argue/suggest/state][that][topic term][sentiment term]. GRASP aims to automatically capture such underlying structures of the given data. For the above examples it finds the pattern [noun][express][that][noun,topic][sentiment], where [express] stands for all its (in)direct hyponyms, and [noun,topic] means a noun which is also related to the topic. |
| Tasks | Document Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1140/ |
| https://www.aclweb.org/anthology/D17-1140 | |
| PWC | https://paperswithcode.com/paper/grasp-rich-patterns-for-argumentation-mining |
| Repo | |
| Framework | |
Authorship Attribution with Convolutional Neural Networks and POS-Eliding
| Title | Authorship Attribution with Convolutional Neural Networks and POS-Eliding |
| Authors | Julian Hitschler, Esther van den Berg, Ines Rehbein |
| Abstract | We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications. In order to investigate the effect of domain biases, we obscure words below a certain frequency threshold, retaining only their POS-tags. This procedure improves test performance due to better generalization on unseen data. Using our method, we are able to predict the authors of scientific publications in the same discipline at levels well above chance. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4907/ |
| https://www.aclweb.org/anthology/W17-4907 | |
| PWC | https://paperswithcode.com/paper/authorship-attribution-with-convolutional |
| Repo | |
| Framework | |
Dynamic-Depth Context Tree Weighting
| Title | Dynamic-Depth Context Tree Weighting |
| Authors | Joao V. Messias, Shimon Whiteson |
| Abstract | Reinforcement learning (RL) in partially observable settings is challenging because the agent’s observations are not Markov. Recently proposed methods can learn variable-order Markov models of the underlying process but have steep memory requirements and are sensitive to aliasing between observation histories due to sensor noise. This paper proposes dynamic-depth context tree weighting (D2-CTW), a model-learning method that addresses these limitations. D2-CTW dynamically expands a suffix tree while ensuring that the size of the model, but not its depth, remains bounded. We show that D2-CTW approximately matches the performance of state-of-the-art alternatives at stochastic time-series prediction while using at least an order of magnitude less memory. We also apply D2-CTW to model-based RL, showing that, on tasks that require memory of past observations, D2-CTW can learn without prior knowledge of a good state representation, or even the length of history upon which such a representation should depend. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6925-dynamic-depth-context-tree-weighting |
| http://papers.nips.cc/paper/6925-dynamic-depth-context-tree-weighting.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-depth-context-tree-weighting |
| Repo | |
| Framework | |
Improving Neural Knowledge Base Completion with Cross-Lingual Projections
| Title | Improving Neural Knowledge Base Completion with Cross-Lingual Projections |
| Authors | Patrick Klein, Simone Paolo Ponzetto, Goran Glava{\v{s}} |
| Abstract | In this paper we present a cross-lingual extension of a neural tensor network model for knowledge base completion. We exploit multilingual synsets from BabelNet to translate English triples to other languages and then augment the reference knowledge base with cross-lingual triples. We project monolingual embeddings of different languages to a shared multilingual space and use them for network initialization (i.e., as initial concept embeddings). We then train the network with triples from the cross-lingually augmented knowledge base. Results on WordNet link prediction show that leveraging cross-lingual information yields significant gains over exploiting only monolingual triples. |
| Tasks | Knowledge Base Completion, Link Prediction, Reading Comprehension, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2083/ |
| https://www.aclweb.org/anthology/E17-2083 | |
| PWC | https://paperswithcode.com/paper/improving-neural-knowledge-base-completion |
| Repo | |
| Framework | |
Twitter Topic Modeling by Tweet Aggregation
| Title | Twitter Topic Modeling by Tweet Aggregation |
| Authors | Asbj{\o}rn Steinskog, Jonas Therkelsen, Bj{"o}rn Gamb{"a}ck |
| Abstract | |
| Tasks | Opinion Mining |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0210/ |
| https://www.aclweb.org/anthology/W17-0210 | |
| PWC | https://paperswithcode.com/paper/twitter-topic-modeling-by-tweet-aggregation |
| Repo | |
| Framework | |
