Paper Group NANR 181
Deep Multi-Task Learning with Shared Memory for Text Classification. Event participant modelling with neural networks. Predicting human similarity judgments with distributional models: The value of word associations.. Creating a Novel Geolocation Corpus from Historical Texts. IHS-RD-Belarus at SemEval-2016 Task 1: Multistage Approach for Measuring …
Deep Multi-Task Learning with Shared Memory for Text Classification
| Title | Deep Multi-Task Learning with Shared Memory for Text Classification |
| Authors | Pengfei Liu, Xipeng Qiu, Xuanjing Huang |
| Abstract | |
| Tasks | Machine Translation, Multi-Task Learning, Text Classification |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1012/ |
| https://www.aclweb.org/anthology/D16-1012 | |
| PWC | https://paperswithcode.com/paper/deep-multi-task-learning-with-shared-memory-1 |
| Repo | |
| Framework | |
Event participant modelling with neural networks
| Title | Event participant modelling with neural networks |
| Authors | Ottokar Tilk, Vera Demberg, Asad Sayeed, Dietrich Klakow, Stefan Thater |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1017/ |
| https://www.aclweb.org/anthology/D16-1017 | |
| PWC | https://paperswithcode.com/paper/event-participant-modelling-with-neural |
| Repo | |
| Framework | |
Predicting human similarity judgments with distributional models: The value of word associations.
| Title | Predicting human similarity judgments with distributional models: The value of word associations. |
| Authors | Simon De Deyne, Amy Perfors, Daniel J Navarro |
| Abstract | Most distributional lexico-semantic models derive their representations based on external language resources such as text corpora. In this study, we propose that internal language models, that are more closely aligned to the mental representations of words could provide important insights into cognitive science, including linguistics. Doing so allows us to reflect upon theoretical questions regarding the structure of the mental lexicon, and also puts into perspective a number of assumptions underlying recently proposed distributional text-based models. In particular, we focus on word-embedding models which have been proposed to learn aspects of word meaning in a manner similar to humans. These are contrasted with internal language models derived from a new extensive data set of word associations. Using relatedness and similarity judgments we evaluate these models and find that the word-association-based internal language models consistently outperform current state-of-the art text-based external language models, often with a large margin. These results are not just a performance improvement; they also have implications for our understanding of how distributional knowledge is used by people. |
| Tasks | Language Modelling, Semantic Textual Similarity |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1175/ |
| https://www.aclweb.org/anthology/C16-1175 | |
| PWC | https://paperswithcode.com/paper/predicting-human-similarity-judgments-with |
| Repo | |
| Framework | |
Creating a Novel Geolocation Corpus from Historical Texts
| Title | Creating a Novel Geolocation Corpus from Historical Texts |
| Authors | Grant DeLozier, Ben Wing, Jason Baldridge, Scott Nesbit |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1721/ |
| https://www.aclweb.org/anthology/W16-1721 | |
| PWC | https://paperswithcode.com/paper/creating-a-novel-geolocation-corpus-from |
| Repo | |
| Framework | |
IHS-RD-Belarus at SemEval-2016 Task 1: Multistage Approach for Measuring Semantic Similarity
| Title | IHS-RD-Belarus at SemEval-2016 Task 1: Multistage Approach for Measuring Semantic Similarity |
| Authors | Maryna Beliuha, Maryna Chernyshevich |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Question Answering, Semantic Similarity, Semantic Textual Similarity, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1107/ |
| https://www.aclweb.org/anthology/S16-1107 | |
| PWC | https://paperswithcode.com/paper/ihs-rd-belarus-at-semeval-2016-task-1 |
| Repo | |
| Framework | |
Jointly Embedding Knowledge Graphs and Logical Rules
| Title | Jointly Embedding Knowledge Graphs and Logical Rules |
| Authors | Shu Guo, Quan Wang, Lihong Wang, Bin Wang, Li Guo |
| Abstract | |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction, Word Sense Disambiguation |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1019/ |
| https://www.aclweb.org/anthology/D16-1019 | |
| PWC | https://paperswithcode.com/paper/jointly-embedding-knowledge-graphs-and |
| Repo | |
| Framework | |
Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets
| Title | Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets |
| Authors | Lei Shu, Bing Liu, Hu Xu, Annice Kim |
| Abstract | |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1022/ |
| https://www.aclweb.org/anthology/D16-1022 | |
| PWC | https://paperswithcode.com/paper/lifelong-rl-lifelong-relaxation-labeling-for |
| Repo | |
| Framework | |
UWB at SemEval-2016 Task 2: Interpretable Semantic Textual Similarity with Distributional Semantics for Chunks
| Title | UWB at SemEval-2016 Task 2: Interpretable Semantic Textual Similarity with Distributional Semantics for Chunks |
| Authors | Miloslav Konop{'\i}k, Ond{\v{r}}ej Pra{\v{z}}{'a}k, David Steinberger, Tom{'a}{\v{s}} Brychc{'\i}n |
| Abstract | |
| Tasks | Semantic Textual Similarity, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1124/ |
| https://www.aclweb.org/anthology/S16-1124 | |
| PWC | https://paperswithcode.com/paper/uwb-at-semeval-2016-task-2-interpretable |
| Repo | |
| Framework | |
PMI-cool at SemEval-2016 Task 3: Experiments with PMI and Goodness Polarity Lexicons for Community Question Answering
| Title | PMI-cool at SemEval-2016 Task 3: Experiments with PMI and Goodness Polarity Lexicons for Community Question Answering |
| Authors | Daniel Balchev, Yasen Kiprov, Ivan Koychev, Preslav Nakov |
| Abstract | |
| Tasks | Community Question Answering, Question Answering, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1130/ |
| https://www.aclweb.org/anthology/S16-1130 | |
| PWC | https://paperswithcode.com/paper/pmi-cool-at-semeval-2016-task-3-experiments |
| Repo | |
| Framework | |
Context-Sensitive Inference Rule Discovery: A Graph-Based Method
| Title | Context-Sensitive Inference Rule Discovery: A Graph-Based Method |
| Authors | Xianpei Han, Le Sun |
| Abstract | Inference rule discovery aims to identify entailment relations between predicates, e.g., {}X acquire Y {--}{\textgreater} X purchase Y{'} and {}X is author of Y {–}{\textgreater} X write Y{'}. Traditional methods dis-cover inference rules by computing distributional similarities between predicates, with each predicate is represented as one or more feature vectors of its instantiations. These methods, however, have two main drawbacks. Firstly, these methods are mostly context-insensitive, cannot accurately measure the similarity between two predicates in a specific context. Secondly, traditional methods usually model predicates independently, ignore the rich inter-dependencies between predicates. To address the above two issues, this pa-per proposes a graph-based method, which can discover inference rules by effectively modelling and exploiting both the context and the inter-dependencies between predicates. Specifically, we propose a graph-based representation{—}Predicate Graph, which can capture the semantic relevance between predicates using both the predicate-feature co-occurrence statistics and the inter-dependencies between predicates. Based on the predicate graph, we propose a context-sensitive random walk algorithm, which can learn con-text-specific predicate representations by distinguishing context-relevant information from context-irrelevant information. Experimental results show that our method significantly outperforms traditional inference rule discovery methods. |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1273/ |
| https://www.aclweb.org/anthology/C16-1273 | |
| PWC | https://paperswithcode.com/paper/context-sensitive-inference-rule-discovery-a |
| Repo | |
| Framework | |
Multi-view Response Selection for Human-Computer Conversation
| Title | Multi-view Response Selection for Human-Computer Conversation |
| Authors | Xiangyang Zhou, Daxiang Dong, Hua Wu, Shiqi Zhao, Dianhai Yu, Hao Tian, Xuan Liu, Rui Yan |
| Abstract | |
| Tasks | Conversational Response Selection |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1036/ |
| https://www.aclweb.org/anthology/D16-1036 | |
| PWC | https://paperswithcode.com/paper/multi-view-response-selection-for-human |
| Repo | |
| Framework | |
Improved Semantic Representation for Domain-Specific Entities
| Title | Improved Semantic Representation for Domain-Specific Entities |
| Authors | Mohammad Taher Pilehvar, Nigel Collier |
| Abstract | |
| Tasks | Learning Semantic Representations, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2902/ |
| https://www.aclweb.org/anthology/W16-2902 | |
| PWC | https://paperswithcode.com/paper/improved-semantic-representation-for-domain |
| Repo | |
| Framework | |
Adaptive Averaging in Accelerated Descent Dynamics
| Title | Adaptive Averaging in Accelerated Descent Dynamics |
| Authors | Walid Krichene, Alexandre Bayen, Peter L. Bartlett |
| Abstract | We study accelerated descent dynamics for constrained convex optimization. This dynamics can be described naturally as a coupling of a dual variable accumulating gradients at a given rate $\eta(t)$, and a primal variable obtained as the weighted average of the mirrored dual trajectory, with weights $w(t)$. Using a Lyapunov argument, we give sufficient conditions on $\eta$ and $w$ to achieve a desired convergence rate. As an example, we show that the replicator dynamics (an example of mirror descent on the simplex) can be accelerated using a simple averaging scheme. We then propose an adaptive averaging heuristic which adaptively computes the weights to speed up the decrease of the Lyapunov function. We provide guarantees on adaptive averaging in continuous-time, prove that it preserves the quadratic convergence rate of accelerated first-order methods in discrete-time, and give numerical experiments to compare it with existing heuristics, such as adaptive restarting. The experiments indicate that adaptive averaging performs at least as well as adaptive restarting, with significant improvements in some cases. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6553-adaptive-averaging-in-accelerated-descent-dynamics |
| http://papers.nips.cc/paper/6553-adaptive-averaging-in-accelerated-descent-dynamics.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-averaging-in-accelerated-descent |
| Repo | |
| Framework | |
Edinburgh’s Statistical Machine Translation Systems for WMT16
| Title | Edinburgh’s Statistical Machine Translation Systems for WMT16 |
| Authors | Philip Williams, Rico Sennrich, Maria N{\u{a}}dejde, Matthias Huck, Barry Haddow, Ond{\v{r}}ej Bojar |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Tokenization, Word Alignment |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2327/ |
| https://www.aclweb.org/anthology/W16-2327 | |
| PWC | https://paperswithcode.com/paper/edinburghs-statistical-machine-translation |
| Repo | |
| Framework | |
Detecting Opinion Polarities using Kernel Methods
| Title | Detecting Opinion Polarities using Kernel Methods |
| Authors | Rasoul Kaljahi, Jennifer Foster |
| Abstract | We investigate the application of kernel methods to representing both structural and lexical knowledge for predicting polarity of opinions in consumer product review. We introduce any-gram kernels which model lexical information in a significantly faster way than the traditional n-gram features, while capturing all possible orders of n-grams n in a sequence without the need to explicitly present a pre-specified set of such orders. We also present an effective format to represent constituency and dependency structure together with aspect terms and sentiment polarity scores. Furthermore, we modify the traditional tree kernel function to compute the similarity based on word embedding vectors instead of exact string match and present experiments using the new models. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4307/ |
| https://www.aclweb.org/anthology/W16-4307 | |
| PWC | https://paperswithcode.com/paper/detecting-opinion-polarities-using-kernel |
| Repo | |
| Framework | |
