Paper Group NANR 84
Proceedings of the IJCNLP 2017, Shared Tasks. Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues. Multi-Grained Chinese Word Segmentation. Neural Joint Model for Transition-based Chinese Syntactic Analysis. OPI-JSA at SemEval-2017 Task 1: Application of Ensemble learning for computing semantic textual similarity. Semantic W …
Proceedings of the IJCNLP 2017, Shared Tasks
| Title | Proceedings of the IJCNLP 2017, Shared Tasks |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4000/ |
| https://www.aclweb.org/anthology/I17-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-ijcnlp-2017-shared-tasks |
| Repo | |
| Framework | |
Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues
| Title | Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues |
| Authors | Xin Wang, Jianan Wang, Yuanchao Liu, Xiaolong Wang, Zhuoran Wang, Baoxun Wang |
| Abstract | User experience is essential for human-computer dialogue systems. However, it is impractical to ask users to provide explicit feedbacks when the agents{'} responses displease them. Therefore, in this paper, we explore to predict users{'} imminent dissatisfactions caused by intelligent agents by analysing the existing utterances in the dialogue sessions. To our knowledge, this is the first work focusing on this task. Several possible factors that trigger negative emotions are modelled. A relation sequence model (RSM) is proposed to encode the sequence of appropriateness of current response with respect to the earlier utterances. The experimental results show that the proposed structure is effective in modelling emotional risk (possibility of negative feedback) than existing conversation modelling approaches. Besides, strategies of obtaining distance supervision data for pre-training are also discussed in this work. Balanced sampling with respect to the last response in the distance supervision data are shown to be reliable for data augmentation. |
| Tasks | Data Augmentation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1072/ |
| https://www.aclweb.org/anthology/I17-1072 | |
| PWC | https://paperswithcode.com/paper/predicting-users-negative-feedbacks-in-multi |
| Repo | |
| Framework | |
Multi-Grained Chinese Word Segmentation
| Title | Multi-Grained Chinese Word Segmentation |
| Authors | Chen Gong, Zhenghua Li, Min Zhang, Xinzhou Jiang |
| Abstract | Traditionally, word segmentation (WS) adopts the single-grained formalism, where a sentence corresponds to a single word sequence. However, Sproat et al. (1997) show that the inter-native-speaker consistency ratio over Chinese word boundaries is only 76{%}, indicating single-grained WS (SWS) imposes unnecessary challenges on both manual annotation and statistical modeling. Moreover, WS results of different granularities can be complementary and beneficial for high-level applications. This work proposes and addresses multi-grained WS (MWS). We build a large-scale pseudo MWS dataset for model training and tuning by leveraging the annotation heterogeneity of three SWS datasets. Then we manually annotate 1,500 test sentences with true MWS annotations. Finally, we propose three benchmark approaches by casting MWS as constituent parsing and sequence labeling. Experiments and analysis lead to many interesting findings. |
| Tasks | Chinese Word Segmentation, Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1072/ |
| https://www.aclweb.org/anthology/D17-1072 | |
| PWC | https://paperswithcode.com/paper/multi-grained-chinese-word-segmentation |
| Repo | |
| Framework | |
Neural Joint Model for Transition-based Chinese Syntactic Analysis
| Title | Neural Joint Model for Transition-based Chinese Syntactic Analysis |
| Authors | Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing. Our models are the first neural approaches for fully joint Chinese analysis that is known to prevent the error propagation problem of pipeline models. Although word embeddings play a key role in dependency parsing, they cannot be applied directly to the joint task in the previous work. To address this problem, we propose embeddings of character strings, in addition to words. Experiments show that our models outperform existing systems in Chinese word segmentation and POS tagging, and perform preferable accuracies in dependency parsing. We also explore bi-LSTM models with fewer features. |
| Tasks | Chinese Word Segmentation, Dependency Parsing, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1111/ |
| https://www.aclweb.org/anthology/P17-1111 | |
| PWC | https://paperswithcode.com/paper/neural-joint-model-for-transition-based |
| Repo | |
| Framework | |
OPI-JSA at SemEval-2017 Task 1: Application of Ensemble learning for computing semantic textual similarity
| Title | OPI-JSA at SemEval-2017 Task 1: Application of Ensemble learning for computing semantic textual similarity |
| Authors | Martyna {'S}piewak, Piotr Sobecki, Daniel Kara{'s} |
| Abstract | Semantic Textual Similarity (STS) evaluation assesses the degree to which two parts of texts are similar, based on their semantic evaluation. In this paper, we describe three models submitted to STS SemEval 2017. Given two English parts of a text, each of proposed methods outputs the assessment of their semantic similarity. We propose an approach for computing monolingual semantic textual similarity based on an ensemble of three distinct methods. Our model consists of recursive neural network (RNN) text auto-encoders ensemble with supervised a model of vectorized sentences using reduced part of speech (PoS) weighted word embeddings as well as unsupervised a method based on word coverage (TakeLab). Additionally, we enrich our model with additional features that allow disambiguation of ensemble methods based on their efficiency. We have used Multi-Layer Perceptron as an ensemble classifier basing on estimations of trained Gradient Boosting Regressors. Results of our research proves that using such ensemble leads to a higher accuracy due to a fact that each member-algorithm tends to specialize in particular type of sentences. Simple model based on PoS weighted Word2Vec word embeddings seem to improve performance of more complex RNN based auto-encoders in the ensemble. In the monolingual English-English STS subtask our Ensemble based model achieved mean Pearson correlation of .785 compared with human annotators. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2018/ |
| https://www.aclweb.org/anthology/S17-2018 | |
| PWC | https://paperswithcode.com/paper/opi-jsa-at-semeval-2017-task-1-application-of |
| Repo | |
| Framework | |
Semantic Word Clusters Using Signed Spectral Clustering
| Title | Semantic Word Clusters Using Signed Spectral Clustering |
| Authors | Jo{~a}o Sedoc, Jean Gallier, Dean Foster, Lyle Ungar |
| Abstract | Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights. We present a new signed spectral normalized graph cut algorithm, \textit{signed clustering}, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships between word pairs are represented by negative weights. Our signed clustering algorithm produces clusters of words that simultaneously capture distributional and synonym relations. By using randomized spectral decomposition (Halko et al., 2011) and sparse matrices, our method is both fast and scalable. We validate our clusters using datasets containing human judgments of word pair similarities and show the benefit of using our word clusters for sentiment prediction. |
| Tasks | Graph Clustering, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1087/ |
| https://www.aclweb.org/anthology/P17-1087 | |
| PWC | https://paperswithcode.com/paper/semantic-word-clusters-using-signed-spectral |
| Repo | |
| Framework | |
Multimodal Machine Learning: Integrating Language, Vision and Speech
| Title | Multimodal Machine Learning: Integrating Language, Vision and Speech |
| Authors | Louis-Philippe Morency, Tadas Baltru{\v{s}}aitis |
| Abstract | Multimodal machine learning is a vibrant multi-disciplinary research field which addresses some of the original goals of artificial intelligence by integrating and modeling multiple communicative modalities, including linguistic, acoustic and visual messages. With the initial research on audio-visual speech recognition and more recently with image and video captioning projects, this research field brings some unique challenges for multimodal researchers given the heterogeneity of the data and the contingency often found between modalities.This tutorial builds upon a recent course taught at Carnegie Mellon University during the Spring 2016 semester (CMU course 11-777) and two tutorials presented at CVPR 2016 and ICMI 2016. The present tutorial will review fundamental concepts of machine learning and deep neural networks before describing the five main challenges in multimodal machine learning: (1) multimodal representation learning, (2) translation {&} mapping, (3) modality alignment, (4) multimodal fusion and (5) co-learning. The tutorial will also present state-of-the-art algorithms that were recently proposed to solve multimodal applications such as image captioning, video descriptions and visual question-answer. We will also discuss the current and upcoming challenges. |
| Tasks | Audio-Visual Speech Recognition, Image Captioning, Question Answering, Representation Learning, Speech Recognition, Video Captioning, Visual Question Answering, Visual Speech Recognition, Zero-Shot Learning |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-5002/ |
| https://www.aclweb.org/anthology/P17-5002 | |
| PWC | https://paperswithcode.com/paper/multimodal-machine-learning-integrating |
| Repo | |
| Framework | |
Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model
| Title | Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model |
| Authors | Kateryna Tymoshenko, Daniele Bonadiman, Aless Moschitti, ro |
| Abstract | Recent work has shown that Tree Kernels (TKs) and Convolutional Neural Networks (CNNs) obtain the state of the art in answer sentence reranking. Additionally, their combination used in Support Vector Machines (SVMs) is promising as it can exploit both the syntactic patterns captured by TKs and the embeddings learned by CNNs. However, the embeddings are constructed according to a classification function, which is not directly exploitable in the preference ranking algorithm of SVMs. In this work, we propose a new hybrid approach combining preference ranking applied to TKs and pointwise ranking applied to CNNs. We show that our approach produces better results on two well-known and rather different datasets: WikiQA for answer sentence selection and SemEval cQA for comment selection in Community Question Answering. |
| Tasks | Community Question Answering, Learning-To-Rank, Question Answering, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1093/ |
| https://www.aclweb.org/anthology/D17-1093 | |
| PWC | https://paperswithcode.com/paper/ranking-kernels-for-structures-and-embeddings |
| Repo | |
| Framework | |
ECNU at SemEval-2017 Task 8: Rumour Evaluation Using Effective Features and Supervised Ensemble Models
| Title | ECNU at SemEval-2017 Task 8: Rumour Evaluation Using Effective Features and Supervised Ensemble Models |
| Authors | Feixiang Wang, Man Lan, Yuanbin Wu |
| Abstract | This paper describes our submissions to task 8 in SemEval 2017, i.e., Determining rumour veracity and support for rumours. Given a rumoured tweet and a lot of reply tweets, the subtask A is to label whether these tweets are support, deny, query or comment, and the subtask B aims to predict the veracity (i.e., true, false, and unverified) with a confidence (in range of 0-1) of the given rumoured tweet. For both subtasks, we adopted supervised machine learning methods, incorporating rich features. Since training data is imbalanced, we specifically designed a two-step classifier to address subtask A . |
| Tasks | Rumour Detection, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2086/ |
| https://www.aclweb.org/anthology/S17-2086 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2017-task-8-rumour-evaluation |
| Repo | |
| Framework | |
Dependency Parsing with Partial Annotations: An Empirical Comparison
| Title | Dependency Parsing with Partial Annotations: An Empirical Comparison |
| Authors | Yue Zhang, Zhenghua Li, Jun Lang, Qingrong Xia, Min Zhang |
| Abstract | This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA). The first approach is based on a forest-based training objective for two CRF parsers, i.e., a biaffine neural network graph-based parser (Biaffine) and a traditional log-linear graph-based parser (LLGPar). The second approach is based on the idea of constrained decoding for three parsers, i.e., a traditional linear graph-based parser (LGPar), a globally normalized neural network transition-based parser (GN3Par) and a traditional linear transition-based parser (LTPar). For the test phase, constrained decoding is also used for completing partial trees. We conduct experiments on Penn Treebank under three different settings for simulating PA, i.e., random, most uncertain, and divergent outputs from the five parsers. The results show that LLGPar is most effective in directly learning from PA, and other parsers can achieve best performance when PAs are completed into full trees by LLGPar. |
| Tasks | Active Learning, Dependency Parsing |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1006/ |
| https://www.aclweb.org/anthology/I17-1006 | |
| PWC | https://paperswithcode.com/paper/dependency-parsing-with-partial-annotations |
| Repo | |
| Framework | |
Towards Lower Bounds on Number of Dimensions for Word Embeddings
| Title | Towards Lower Bounds on Number of Dimensions for Word Embeddings |
| Authors | Kevin Patel, Pushpak Bhattacharyya |
| Abstract | Word embeddings are a relatively new addition to the modern NLP researcher{'}s toolkit. However, unlike other tools, word embeddings are used in a black box manner. There are very few studies regarding various hyperparameters. One such hyperparameter is the dimension of word embeddings. They are rather decided based on a rule of thumb: in the range 50 to 300. In this paper, we show that the dimension should instead be chosen based on corpus statistics. More specifically, we show that the number of pairwise equidistant words of the corpus vocabulary (as defined by some distance/similarity metric) gives a lower bound on the the number of dimensions , and going below this bound results in degradation of quality of learned word embeddings. Through our evaluations on standard word embedding evaluation tasks, we show that for dimensions higher than or equal to the bound, we get better results as compared to the ones below it. |
| Tasks | Named Entity Recognition, Part-Of-Speech Tagging, Sarcasm Detection, Sentence Classification, Sentiment Analysis, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2006/ |
| https://www.aclweb.org/anthology/I17-2006 | |
| PWC | https://paperswithcode.com/paper/towards-lower-bounds-on-number-of-dimensions |
| Repo | |
| Framework | |
Learning to See Physics via Visual De-animation
| Title | Learning to See Physics via Visual De-animation |
| Authors | Jiajun Wu, Erika Lu, Pushmeet Kohli, Bill Freeman, Josh Tenenbaum |
| Abstract | We introduce a paradigm for understanding physical scenes without human annotations. At the core of our system is a physical world representation that is first recovered by a perception module and then utilized by physics and graphics engines. During training, the perception module and the generative models learn by visual de-animation — interpreting and reconstructing the visual information stream. During testing, the system first recovers the physical world state, and then uses the generative models for reasoning and future prediction. Even more so than forward simulation, inverting a physics or graphics engine is a computationally hard problem; we overcome this challenge by using a convolutional inversion network. Our system quickly recognizes the physical world state from appearance and motion cues, and has the flexibility to incorporate both differentiable and non-differentiable physics and graphics engines. We evaluate our system on both synthetic and real datasets involving multiple physical scenes, and demonstrate that our system performs well on both physical state estimation and reasoning problems. We further show that the knowledge learned on the synthetic dataset generalizes to constrained real images. |
| Tasks | Future prediction |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6620-learning-to-see-physics-via-visual-de-animation |
| http://papers.nips.cc/paper/6620-learning-to-see-physics-via-visual-de-animation.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-see-physics-via-visual-de |
| Repo | |
| Framework | |
Benben: A Chinese Intelligent Conversational Robot
| Title | Benben: A Chinese Intelligent Conversational Robot |
| Authors | Wei-Nan Zhang, Ting Liu, Bing Qin, Yu Zhang, Wanxiang Che, Yanyan Zhao, Xiao Ding |
| Abstract | |
| Tasks | Chinese Word Segmentation, Dependency Parsing, Information Retrieval, Intent Detection, Named Entity Recognition, Part-Of-Speech Tagging, Question Answering, Reading Comprehension, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4003/ |
| https://www.aclweb.org/anthology/P17-4003 | |
| PWC | https://paperswithcode.com/paper/benben-a-chinese-intelligent-conversational |
| Repo | |
| Framework | |
Textually Summarising Incomplete Data
| Title | Textually Summarising Incomplete Data |
| Authors | Stephanie Inglis, Ehud Reiter, Somayajulu Sripada |
| Abstract | Many data-to-text NLG systems work with data sets which are incomplete, ie some of the data is missing. We have worked with data journalists to understand how they describe incomplete data, and are building NLG algorithms based on these insights. A pilot evaluation showed mixed results, and highlighted several areas where we need to improve our system. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3535/ |
| https://www.aclweb.org/anthology/W17-3535 | |
| PWC | https://paperswithcode.com/paper/textually-summarising-incomplete-data |
| Repo | |
| Framework | |
Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG)
| Title | Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG) |
| Authors | Tomer Cagan, Stefan L. Frank, Reut Tsarfaty |
| Abstract | Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users{'} agendas, consisting of topics and sentiments, and based on wide-coverage automatically-acquired generative grammars. We compare three types of grammatical representations that we design for ONLG, which interleave different layers of linguistic information and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima{'}an, 2008) inspired grammar gets better language model scores than lexicalized grammars {`}a la Collins (2003), and that the latter gets better human-evaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content. | |
| Tasks | Language Modelling, Text Generation, Topic Models |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1122/ |
| https://www.aclweb.org/anthology/P17-1122 | |
| PWC | https://paperswithcode.com/paper/data-driven-broad-coverage-grammars-for |
| Repo | |
| Framework | |
