http://www.semanlink.net/tag/bruxelles Documents tagged with Bruxelles http://www.semanlink.net/doc/2025/11/le_marmiton_restaurant_belge_ 2025-11-02T13:28:32Z https://github.com/thunlp/OpenKE [paper at EMNLP 2018](https://www.aclweb.org/anthology/papers/D/D18/D18-2024/) 2019-04-23T20:10:11Z https://aclanthology.info/papers/D18-1360/d18-1360 Attempting to answer questions such as: "What is the task described in this paper?", "what method was used in solving the task?", "what dataset did the paper use?". The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. 2019-02-09T11:28:06Z http://ruder.io/10-exciting-ideas-of-2018-in-nlp/ 2018-12-19T21:48:10Z https://medium.com/@chriszhu12/highlights-of-emnlp-2018-55892fba4247 2018-11-25T17:24:27Z https://medium.com/@madrugado/interesting-stuff-at-emnlp-part-ii-ce92ac928f16 2018-11-25T15:55:26Z https://medium.com/@madrugado/interesting-stuff-in-emnlp-part-i-4a79b5007eb1 2018-11-25T15:53:56Z https://ai.googleblog.com/2018/10/google-at-emnlp-2018.html 2018-11-25T15:14:25Z https://aclanthology.coli.uni-saarland.de/papers/D18-1011/d18-1011 learning multimodal word representations by integrating textual, visual and auditory inputs. 2018-11-15T01:27:25Z https://supernlp.github.io/2018/11/10/emnlp-2018/ 2018-11-13T00:22:21Z http://u.cs.biu.ac.il/~yogo/blackbox2018.pdf 2018-11-11T23:29:46Z https://aclanthology.coli.uni-saarland.de/papers/D18-1482/d18-1482 unsupervised embeddings of sentences of variable length from pre-trained word embeddings (better on short length text). (Builds on the word mover's distance, but using ideas borrowed from kernel methods approximation, gets a representation of sentences, instead of just a distance between them) 2018-11-10T15:38:38Z http://ruder.io/emnlp-2018-highlights/ 2018-11-08T23:49:49Z https://twitter.com/feiliu_nlp/status/1058985012945735680 2018-11-06T23:11:24Z http://ruiyan.me/pubs/tutorial-emnlp18.pdf by Dr Wei Wu (Microsoft Xiaolce - chatbot with 200 millions users in China) and Dr Rui Yan (Peking Univ) - Chit-chat (casual, non goal oriented) open-domain. Must be relevant to the context and diverse (informative) to be engaging. - why creating a chat? to prove an AI can speak like a human, commercial reasons, link to services. Task oriented vs non task oriented: this tutorial is about the second one. Retrieval based vs generation based. Basic knowledge of DL for chatbots: - word embeddings - sentence embeddings (CNN, RNN) - dialogue modeling: seq-to-seq with attention Response selection for retrieval based chatbots: - single turn response selection (slides 37-57) - framework 1: matching with seq embeddings - framework 2: matching with message-response interaction (46) - extension of 1: KnowledgeMatching with External Knowledge (53) - extension of 2: RepresentationsMatching with Multiple Levels of Representations (54) - insights from comparison between 1 and 2 (57) - multi turn response selection (62) - context is now: mess + history - again, 2 frameworks Emerging directions (79): - matching with better representations - Self-Attention (82) - fusing multiple types of repr. But how to fuse matters (83) - pre-training Learning a matching model for response selection (84) Generation based models for chatbots: - single turn generarion (89) - Basic generation model - seq2seq - Attention - Bi-directional modeling - multi turn generation - Contexts are important - Context sensitive models - Hierarchical context modeling - Latent variable modeling - Hierarchical memory networks Diversity in conversations (99) Content introducing (106) Additional elements (113) - Topics in cnversation - Emotions Persona in chat: - Persona - ... - Knowledge - Common sense RL and Adversarial learning in conversations (125) Evaluation (132) Future trends: - Reasoning in dialogues - X-grounded dialogues 2018-11-06T14:37:53Z https://frcchang.github.io/tutorial/EMNLP2018_joint_models.pdf **Joint models: solve 2 tasks at once.** Related tasks: POS tagging, NER, chuncking. Pipeline tasks Motivations: - reduce error propagation - information exchange between tasks Challenges: - Joint learning - Search History: statistical models. 2 kinds: - Graph-Based Methods - Traditional solution: - Score each candidate, select the highest-scored output - Search-space typically exponential - Transition-Based Methods - Transition-Based systems: Automata - State: partial result during decoding, Action: operations that can be applied for state transition - Output constructed incrementally - Deep learning based model - Neural transition based models - Neural graph-based models - Cross task - Seminal work: Collobert, Ronan, et al. "Natural language processing (almost) from scratch." - Not all tasks are mutually beneficial - Ramachandran, et al. “Unsupervised pretraining for sequence to sequence learning.” - Peters, Matthew E., et al. "Deep contextualized word representations." (ELMo) - "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding." - ULMFIT - Correlation between multi-task learning and pretraining - Cross lingual - Cross domain - Cross standard 2018-11-06T11:22:04Z https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-2018-emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp 2018-11-06T10:06:41Z https://blackboxnlp.github.io/ 2018-11-06T09:58:57Z https://medium.com/@hadyelsahar/writing-code-for-natural-language-processing-research-emnlp2018-nlproc-a87367cc5146 2018-11-05T18:48:58Z https://drive.google.com/file/d/1kmNAwrSlFYo0cN_DcURMOArBwe9FxWxR/view 2018-11-05T13:50:50Z https://aclanthology.coli.uni-saarland.de/papers/D18-1360/d18-1360 > A multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. > The framework supports **construction of a scientific knowledge graph** [http://nlp.cs.washington.edu/sciIE/](http://nlp.cs.washington.edu/sciIE/) 2018-11-04T09:31:50Z http://emnlp2018.org/schedule 2018-11-04T00:49:44Z https://aclanthology.coli.uni-saarland.de/papers/D18-1092/d18-1092 [same paper](https://aclweb.org/anthology/papers/D/D18/D18-1092/) 2018-11-02T23:20:31Z https://aclanthology.coli.uni-saarland.de/events/emnlp-2018 2018-11-02T23:16:49Z http://nlp.seas.harvard.edu/latent-nlp-tutorial.html [arxiv](https://arxiv.org/abs/1812.06834.pdf) 2018-11-01T22:28:15Z https://research.fb.com/facebook-research-at-emnlp/ 2018-11-01T17:12:02Z https://twitter.com/yuvalpi/status/1057909000551964673 2018-11-01T16:58:32Z https://docs.google.com/presentation/d/17NoJY2SnC2UMbVegaRCWA7Oca7UCZ3vHnMqBV4SUayc/edit#slide=id.p 2018-10-31T18:11:21Z http://emnlp2018.org/program/tutorials/ 2018-10-31T15:56:28Z https://arxiv.org/abs/1809.00782 QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. > In practice, some questions are best answered using text, while others are best answered using KBs. A natural question, then, is how to effectively combine both types of information. Surprisingly little prior work has looked at this problem. 2018-09-06T01:38:28Z https://arxiv.org/abs/1601.03764 > Here it is shown that multiple word senses reside in linear superposition within the word embedding and simple sparse coding can recover vectors that approximately capture the senses > Each extracted word sense is accompanied by one of about 2000 “discourse atoms” that gives a succinct description of which other words co-occur with that word sense. > The success of the approach is mathematically explained using a variant of the random walk on discourses model ("random walk": a generative model for language). Under the assumptions of this model, there exists a linear relationship between the vector of a word w and the vectors of the words in its contexts (It is not the average of the words in w's context, but in a given corpus the matrix of the linear relationship does not depend on w. It can be estimated, and so we can compute the embedding of a word from the contexts it belongs to) [Related blog post](/doc/?uri=https%3A%2F%2Fwww.offconvex.org%2F2016%2F07%2F10%2Fembeddingspolysemy%2F) 2018-08-28T11:00:08Z http://emnlp2018.org/ 2018-08-23T22:37:54Z https://www.tensorflow.org/hub/modules/google/universal-sentence-encoder-large/1 [Paper presented at EMNLP 2018](https://aclanthology.coli.uni-saarland.de/papers/D18-2029/d18-2029) 2018-05-23T16:35:31Z