Paper Group NANR 188
Semisupervied Data Driven Word Sense Disambiguation for Resource-poor Languages. Manual Identification of Arguments with Implicit Conclusions Using Semantic Rules for Argument Mining. Dimensions of Interpersonal Relationships: Corpus and Experiments. Comparing Character-level Neural Language Models Using a Lexical Decision Task. Using Reinforcement …
Semisupervied Data Driven Word Sense Disambiguation for Resource-poor Languages
| Title | Semisupervied Data Driven Word Sense Disambiguation for Resource-poor Languages |
| Authors | Pratibha Rani, Vikram Pudi, Dipti M. Sharma |
| Abstract | |
| Tasks | Word Sense Disambiguation |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7561/ |
| https://www.aclweb.org/anthology/W17-7561 | |
| PWC | https://paperswithcode.com/paper/semisupervied-data-driven-word-sense |
| Repo | |
| Framework | |
Manual Identification of Arguments with Implicit Conclusions Using Semantic Rules for Argument Mining
| Title | Manual Identification of Arguments with Implicit Conclusions Using Semantic Rules for Argument Mining |
| Authors | Nancy Green |
| Abstract | This paper describes a pilot study to evaluate human analysts{'} ability to identify the argumentation scheme and premises of an argument having an implicit conclusion. In preparation for the study, argumentation scheme definitions were crafted for genetics research articles. The schemes were defined in semantic terms, following a proposal to use semantic rules to mine arguments in that literature. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5109/ |
| https://www.aclweb.org/anthology/W17-5109 | |
| PWC | https://paperswithcode.com/paper/manual-identification-of-arguments-with |
| Repo | |
| Framework | |
Dimensions of Interpersonal Relationships: Corpus and Experiments
| Title | Dimensions of Interpersonal Relationships: Corpus and Experiments |
| Authors | Farzana Rashid, Eduardo Blanco |
| Abstract | This paper presents a corpus and experiments to determine dimensions of interpersonal relationships. We define a set of dimensions heavily inspired by work in social science. We create a corpus by retrieving pairs of people, and then annotating dimensions for their relationships. A corpus analysis shows that dimensions can be annotated reliably. Experimental results show that given a pair of people, values to dimensions can be assigned automatically. |
| Tasks | Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1244/ |
| https://www.aclweb.org/anthology/D17-1244 | |
| PWC | https://paperswithcode.com/paper/dimensions-of-interpersonal-relationships |
| Repo | |
| Framework | |
Comparing Character-level Neural Language Models Using a Lexical Decision Task
| Title | Comparing Character-level Neural Language Models Using a Lexical Decision Task |
| Authors | Ga{"e}l Le Godais, Tal Linzen, Emmanuel Dupoux |
| Abstract | What is the information captured by neural network models of language? We address this question in the case of character-level recurrent neural language models. These models do not have explicit word representations; do they acquire implicit ones? We assess the lexical capacity of a network using the lexical decision task common in psycholinguistics: the system is required to decide whether or not a string of characters forms a word. We explore how accuracy on this task is affected by the architecture of the network, focusing on cell type (LSTM vs. SRN), depth and width. We also compare these architectural properties to a simple count of the parameters of the network. The overall number of parameters in the network turns out to be the most important predictor of accuracy; in particular, there is little evidence that deeper networks are beneficial for this task. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2020/ |
| https://www.aclweb.org/anthology/E17-2020 | |
| PWC | https://paperswithcode.com/paper/comparing-character-level-neural-language |
| Repo | |
| Framework | |
Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game
| Title | Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game |
| Authors | Ramesh Manuvinakurike, David DeVault, Kallirroi Georgila |
| Abstract | We apply Reinforcement Learning (RL) to the problem of incremental dialogue policy learning in the context of a fast-paced dialogue game. We compare the policy learned by RL with a high-performance baseline policy which has been shown to perform very efficiently (nearly as well as humans) in this dialogue game. The RL policy outperforms the baseline policy in offline simulations (based on real user data). We provide a detailed comparison of the RL policy and the baseline policy, including information about how much effort and time it took to develop each one of them. We also highlight the cases where the RL policy performs better, and show that understanding the RL policy can provide valuable insights which can inform the creation of an even better rule-based policy. |
| Tasks | Spoken Dialogue Systems |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5539/ |
| https://www.aclweb.org/anthology/W17-5539 | |
| PWC | https://paperswithcode.com/paper/using-reinforcement-learning-to-model |
| Repo | |
| Framework | |
Patent NMT integrated with Large Vocabulary Phrase Translation by SMT at WAT 2017
| Title | Patent NMT integrated with Large Vocabulary Phrase Translation by SMT at WAT 2017 |
| Authors | Zi Long, Ryuichiro Kimura, Takehito Utsuro, Tomoharu Mitsuhashi, Mikio Yamamoto |
| Abstract | Neural machine translation (NMT) cannot handle a larger vocabulary because the training complexity and decoding complexity proportionally increase with the number of target words. This problem becomes even more serious when translating patent documents, which contain many technical terms that are observed infrequently. Long et al.(2017) proposed to select phrases that contain out-of-vocabulary words using the statistical approach of branching entropy. The selected phrases are then replaced with tokens during training and post-translated by the phrase translation table of SMT. In this paper, we apply the method proposed by Long et al. (2017) to the WAT 2017 Japanese-Chinese and Japanese-English patent datasets. Evaluation on Japanese-to-Chinese, Chinese-to-Japanese, Japanese-to-English and English-to-Japanese patent sentence translation proved the effectiveness of phrases selected with branching entropy, where the NMT model of Long et al.(2017) achieves a substantial improvement over a baseline NMT model without the technique proposed by Long et al.(2017). |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5709/ |
| https://www.aclweb.org/anthology/W17-5709 | |
| PWC | https://paperswithcode.com/paper/patent-nmt-integrated-with-large-vocabulary |
| Repo | |
| Framework | |
Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering
| Title | Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering |
| Authors | Lilian Wanzare, Aless Zarcone, ra, Stefan Thater, Manfred Pinkal |
| Abstract | We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our approach exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach. |
| Tasks | Question Answering, Semantic Role Labeling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0901/ |
| https://www.aclweb.org/anthology/W17-0901 | |
| PWC | https://paperswithcode.com/paper/inducing-script-structure-from-crowdsourced |
| Repo | |
| Framework | |
Mining Association Rules from Clinical Narratives
| Title | Mining Association Rules from Clinical Narratives |
| Authors | Svetla Boytcheva, Ivelina Nikolova, Galia Angelova |
| Abstract | Shallow text analysis (Text Mining) uses mainly Information Extraction techniques. The low resource languages do not allow application of such traditional techniques with sufficient accuracy and recall on big data. In contrast, Data Mining approaches provide an opportunity to make deep analysis and to discover new knowledge. Frequent pattern mining approaches are used mainly for structured information in databases and are a quite challenging task in text mining. Unfortunately, most frequent pattern mining approaches do not use contextual information for extracted patterns: general patterns are extracted regardless of the context. We propose a method that processes raw informal texts (from health discussion forums) and formal texts (outpatient records) in Bulgarian language. In addition we use some context information and small terminological lexicons to generalize extracted frequent patterns. This allows to map informal expression of medical terminology to the formal one and to generate automatically resources. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1019/ |
| https://doi.org/10.26615/978-954-452-049-6_019 | |
| PWC | https://paperswithcode.com/paper/mining-association-rules-from-clinical |
| Repo | |
| Framework | |
Approximation Bounds for Hierarchical Clustering: Average Linkage, Bisecting K-means, and Local Search
| Title | Approximation Bounds for Hierarchical Clustering: Average Linkage, Bisecting K-means, and Local Search |
| Authors | Benjamin Moseley, Joshua Wang |
| Abstract | Hierarchical clustering is a data analysis method that has been used for decades. Despite its widespread use, the method has an underdeveloped analytical foundation. Having a well understood foundation would both support the currently used methods and help guide future improvements. The goal of this paper is to give an analytic framework to better understand observations seen in practice. This paper considers the dual of a problem framework for hierarchical clustering introduced by Dasgupta. The main result is that one of the most popular algorithms used in practice, average linkage agglomerative clustering, has a small constant approximation ratio for this objective. Furthermore, this paper establishes that using bisecting k-means divisive clustering has a very poor lower bound on its approximation ratio for the same objective. However, we show that there are divisive algorithms that perform well with respect to this objective by giving two constant approximation algorithms. This paper is some of the first work to establish guarantees on widely used hierarchical algorithms for a natural objective function. This objective and analysis give insight into what these popular algorithms are optimizing and when they will perform well. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6902-approximation-bounds-for-hierarchical-clustering-average-linkage-bisecting-k-means-and-local-search |
| http://papers.nips.cc/paper/6902-approximation-bounds-for-hierarchical-clustering-average-linkage-bisecting-k-means-and-local-search.pdf | |
| PWC | https://paperswithcode.com/paper/approximation-bounds-for-hierarchical |
| Repo | |
| Framework | |
Real-Time Bidding with Side Information
| Title | Real-Time Bidding with Side Information |
| Authors | Arthur Flajolet, Patrick Jaillet |
| Abstract | We consider the problem of repeated bidding in online advertising auctions when some side information (e.g. browser cookies) is available ahead of submitting a bid in the form of a $d$-dimensional vector. The goal for the advertiser is to maximize the total utility (e.g. the total number of clicks) derived from displaying ads given that a limited budget $B$ is allocated for a given time horizon $T$. Optimizing the bids is modeled as a contextual Multi-Armed Bandit (MAB) problem with a knapsack constraint and a continuum of arms. We develop UCB-type algorithms that combine two streams of literature: the confidence-set approach to linear contextual MABs and the probabilistic bisection search method for stochastic root-finding. Under mild assumptions on the underlying unknown distribution, we establish distribution-independent regret bounds of order $\tilde{O}(d \cdot \sqrt{T})$ when either $B = \infty$ or when $B$ scales linearly with $T$. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7101-real-time-bidding-with-side-information |
| http://papers.nips.cc/paper/7101-real-time-bidding-with-side-information.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-bidding-with-side-information |
| Repo | |
| Framework | |
On Modeling Sense Relatedness in Multi-prototype Word Embedding
| Title | On Modeling Sense Relatedness in Multi-prototype Word Embedding |
| Authors | Yixin Cao, Jiaxin Shi, Juanzi Li, Zhiyuan Liu, Chengjiang Li |
| Abstract | To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness among word senses which actually plays an important role. In this paper, we propose a novel approach to capture word sense relatedness in multi-prototype word embedding model. Particularly, we differentiate the original sense and extended senses of a word by introducing their global occurrence information and model their relatedness through the local textual context information. Based on the idea of fuzzy clustering, we introduce a random process to integrate these two types of senses and design two non-parametric methods for word sense induction. To make our model more scalable and efficient, we use an online joint learning framework extended from the Skip-gram model. The experimental results demonstrate that our model outperforms both conventional single-prototype embedding models and other multi-prototype embedding models, and achieves more stable performance when trained on smaller data. |
| Tasks | Language Modelling, Named Entity Recognition, Representation Learning, Word Sense Induction |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1024/ |
| https://www.aclweb.org/anthology/I17-1024 | |
| PWC | https://paperswithcode.com/paper/on-modeling-sense-relatedness-in-multi |
| Repo | |
| Framework | |
Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)
| Title | Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1000/ |
| https://www.aclweb.org/anthology/S17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-6th-joint-conference-on |
| Repo | |
| Framework | |
Monocular 3D Human Pose Estimation by Predicting Depth on Joints
| Title | Monocular 3D Human Pose Estimation by Predicting Depth on Joints |
| Authors | Bruce Xiaohan Nie, Ping Wei, Song-Chun Zhu |
| Abstract | This paper aims at estimating full-body 3D human poses from monocular images of which the biggest challenge is the inherent ambiguity introduced by lifting the 2D pose into 3D space. We propose a novel framework focusing on reducing this ambiguity by predicting the depth of human joints based on 2D human joint locations and body part images. Our approach is built on a two-level hierarchy of Long Short-Term Memory (LSTM) Networks which can be trained end-to-end. The first level consists of two components: 1) a skeleton-LSTM which learns the depth information from global human skeleton features; 2) a patch-LSTM which utilizes the local image evidence around joint locations. The both networks have tree structure defined on the kinematic relation of human skeleton, thus the information at different joints is broadcast through the whole skeleton in a top-down fashion. The two networks are first pre-trained separately on different data sources and then aggregated in the second layer for final depth prediction. The empirical evaluation on Human3.6M and HHOI dataset demonstrates the advantage of combining global 2D skeleton and local image patches for depth prediction, and our superior quantitative and qualitative performance relative to state-of-the-art methods. |
| Tasks | 3D Human Pose Estimation, Depth Estimation, Pose Estimation |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Nie_Monocular_3D_Human_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Nie_Monocular_3D_Human_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-3d-human-pose-estimation-by |
| Repo | |
| Framework | |
An'alise de Medidas de Similaridade Sem^antica na Tarefa de Reconhecimento de Implica\cc~ao Textual (Analysis of Semantic Similarity Measures in the Recognition of Textual Entailment Task)[In Portuguese]
| Title | An'alise de Medidas de Similaridade Sem^antica na Tarefa de Reconhecimento de Implica\cc~ao Textual (Analysis of Semantic Similarity Measures in the Recognition of Textual Entailment Task)[In Portuguese] |
| Authors | David Feitosa, Vl{'a}dia Pinheiro |
| Abstract | |
| Tasks | Natural Language Inference, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6619/ |
| https://www.aclweb.org/anthology/W17-6619 | |
| PWC | https://paperswithcode.com/paper/analise-de-medidas-de-similaridade-semantica |
| Repo | |
| Framework | |
Linguistic Description of Complex Phenomena with the rLDCP R Package
| Title | Linguistic Description of Complex Phenomena with the rLDCP R Package |
| Authors | Jose Alonso, Patricia Conde-Clemente, Gracian Trivino |
| Abstract | Monitoring and analysis of complex phenomena attract the attention of both academy and industry. Dealing with data produced by complex phenomena requires the use of advance computational intelligence techniques. Namely, linguistic description of complex phenomena constitutes a mature research line. It is supported by the Computational Theory of Perceptions grounded on the Fuzzy Sets Theory. Its aim is the development of computational systems with the ability to generate vague descriptions of the world in a similar way how humans do. This is a human-centric and multi-disciplinary research work. Moreover, its success is a matter of careful design; thus, developers play a key role. The rLDCP R package was designed to facilitate the development of new applications. This demo introduces the use of rLDCP, for both beginners and advance developers, in practical use cases. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3538/ |
| https://www.aclweb.org/anthology/W17-3538 | |
| PWC | https://paperswithcode.com/paper/linguistic-description-of-complex-phenomena |
| Repo | |
| Framework | |
