Proceedings of the 2019 Conference of the North
Enabling Real-time Neural IME with Incremental Vocabulary Selection (N19-2)
Copied to clipboard
| Challenge: | Input method editor (IME) converts sequential alphabet key inputs to words in a target language. |
| Approach: | They propose a neural-based language model that incrementally builds a subset vocabulary from the word lattice. |
| Outcome: | The proposed approach achieves 50x speedup on Japanese IME benchmark without losing conversion accuracy. |
Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding (N19-2)
Copied to clipboard
| Challenge: | Existing approaches to leveraging data across locales to improve domain classification accuracy are ineffective. |
| Approach: | They propose a locale-agnostic universal domain classification model that leverages available data across locales sharing the same language to improve domain classification accuracy. |
| Outcome: | The proposed model outperforms baseline models especially when classifying locale-specific domains and low-resourced domains. |
Practical Semantic Parsing for Spoken Language Understanding (N19-2)
Copied to clipboard
| Challenge: | Existing systems that can handle a user's utterance are unable to handle Q&A or SLU. |
| Approach: | They build a transfer learning framework for executable semantic parsing . they show it is effective for Q&A and for spoken language understanding . |
| Outcome: | The proposed framework is effective for Q&A and Spoken Language Understanding . it can be learned by exploiting data on other domains, the authors show . |
Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring (N19-2)
Copied to clipboard
Zhengyuan Liu, Hazel Lim, Nur Farah Ain Suhaimi, Shao Chuen Tong, Sharon Ong, Angela Ng, Sheldon Lee, Michael R. Macdonald, Savitha Ramasamy, Pavitra Krishnaswamy, Wai Leng Chow, Nancy F. Chen
| Challenge: | a limited amount of data exists for human-human spoken dialogues for research and development . a dialogue comprehension system that extracts clinical information from spoken conversations is clinically useful . |
| Approach: | They propose a framework inspired by nurse-initiated clinical symptom monitoring conversations to construct a simulated human-human dialogue dataset. |
| Outcome: | The proposed system achieves more than 80% F1 on held-out test set from nurse-to-patient conversations. |
Graph Convolution for Multimodal Information Extraction from Visually Rich Documents (N19-2)
Copied to clipboard
| Challenge: | Visually rich documents (VRDs) present information in the form of both text and vision. |
| Approach: | They propose a graph convolution based model to combine textual and visual information presented in VRDs. |
| Outcome: | The proposed model outperforms existing models on two real-world datasets. |
Diversifying Reply Suggestions Using a Matching-Conditional Variational Autoencoder (N19-2)
Copied to clipboard
| Challenge: | Automated reply suggestions (SR) are becoming common in many popular applications such as Gmail (2016) . |
| Approach: | They propose a constrained-sampling approach to make the variational inference efficient for a commercial instant-messaging system. |
| Outcome: | The proposed model increases diversity without losing relevance in offline experiments. |
Goal-Oriented End-to-End Conversational Models with Profile Features in a Real-World Setting (N19-2)
Copied to clipboard
| Challenge: | a recent study has focused on how algorithmic improvements help model performance on fabricated datasets. |
| Approach: | They propose two approaches to train conversational neural models for goal-oriented conversational systems . they train models on historical chat transcripts and test on live contacts . |
| Outcome: | The proposed model is able to generate top-four responses on live contacts . the model is also able for customer profile features to assess their impact on performance . |
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)
Copied to clipboard
Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin
| Challenge: | e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features. |
| Approach: | They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent. |
| Outcome: | The proposed model outperforms baseline models and provides better recall and triage for specialized agents. |
Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce (N19-2)
Copied to clipboard
| Challenge: | Existing methods for short product title generation only consider textual information from long titles . MM-GAN incorporates image information and attribute tags from product, as well as textual info from original long titles. |
| Approach: | They propose a multi-modal generative adversarial network for short product title generation in E-commerce . they incorporate image information and attribute tags from product, as well as textual information from original long titles . |
| Outcome: | The proposed model outperforms state-of-the-art methods on a large-scale E-commerce dataset. |
A Case Study on Neural Headline Generation for Editing Support (N19-2)
Copied to clipboard
Kazuma Murao, Ken Kobayashi, Hayato Kobayashi, Taichi Yatsuka, Takeshi Masuyama, Tatsuru Higurashi, Yoshimune Tabuchi
| Challenge: | a news-aggregator is a website or mobile application that aggregates web content . dozens of professional editors manually create their headlines, which are much shorter than the original headlines. |
| Approach: | They propose a neural headline generation model that automatically generates short headlines from news articles. |
| Outcome: | The proposed model is deployed to an editing support tool and compares editors' behavior before and after the release. |
Neural Lexicons for Slot Tagging in Spoken Language Understanding (N19-2)
Copied to clipboard
| Challenge: | lexicons or gazettes are used to improve slot tagging in spoken language understanding systems. |
| Approach: | They develop models that encode lexicon information as neural features for use in a long-short term memory neural network. |
| Outcome: | The proposed models improve slot tagging with lexicons and gazettes . the results could be used to improve other natural language applications . |
Active Learning for New Domains in Natural Language Understanding (N19-2)
Copied to clipboard
| Challenge: | Existing approaches to improve the accuracy of new domains are lacking annotated live utterances. |
| Approach: | They propose an algorithm called Majority-CRF that uses an ensemble of classification models to guide the selection of relevant utterances and a sequence labeling model to prioritize informative examples. |
| Outcome: | The proposed algorithm achieves 6.6%-9% error rate reduction and statistically significant improvements on six new domains. |
Scaling Multi-Domain Dialogue State Tracking via Query Reformulation (N19-2)
Copied to clipboard
| Challenge: | Using a pointer-generator network, we model the reference resolution task as a dialogue context-aware user query reformulation task. |
| Approach: | They propose a pointer-generator network and a novel multi-task learning setup to model dialogue state tracking and referring expression resolution tasks using a dialogue context-aware user query reformulation task. |
| Outcome: | The proposed model improves absolute F1 on internal and public benchmarks. |
Are the Tools up to the Task? an Evaluation of Commercial Dialog Tools in Developing Conversational Enterprise-grade Dialog Systems (N19-2)
Copied to clipboard
| Challenge: | Existing toolsets are incomplete in meeting the goal of building effective dialog systems, authors say . |
| Approach: | They compare dialog tools available from a number of companies to determine their strengths and weaknesses . they provide quantitative and qualitative results in three main areas: natural language understanding, dialog, and text generation . |
| Outcome: | The toolsets are incomplete, but they are compared to other tools to determine their strengths and weaknesses. |
Development and Deployment of a Large-Scale Dialog-based Intelligent Tutoring System (N19-2)
Copied to clipboard
Shazia Afzal, Tejas Dhamecha, Nirmal Mukhi, Renuka Sindhgatta, Smit Marvaniya, Matthew Ventura, Jessica Yarbro
| Challenge: | Dialog-based intelligent tutoring systems capture the effectiveness of expert human teacher-learner interactions by using natural language dialogue. |
| Approach: | They propose to use dialog-based tutoring systems to help students learn through a sequence of dialogue moves in natural language to steer them through varying levels of content granularity. |
| Outcome: | The proposed system is being used by hundreds of college level students for practice and self-regulated study in diverse subjects like Sociology, Communications, and American Government. |
Learning When Not to Answer: a Ternary Reward Structure for Reinforcement Learning Based Question Answering (N19-2)
Copied to clipboard
| Challenge: | Existing methods for question answering over knowledge graphs use reinforcement learning to reason over a knowledge graph. |
| Approach: | They propose a new performance metric for question-answering agents that extends the binary reward structure to a ternary reward structure which rewards an agent for not answering a question rather than giving an incorrect answer. |
| Outcome: | The proposed method significantly improves the precision of answered questions while only not answering a limited number of correctly answered questions. |
Extraction of Message Sequence Charts from Software Use-Case Descriptions (N19-2)
Copied to clipboard
Girish Palshikar, Nitin Ramrakhiyani, Sangameshwar Patil, Sachin Pawar, Swapnil Hingmire, Vasudeva Varma, Pushpak Bhattacharyya
| Challenge: | Software Requirement Specification documents provide natural language descriptions of the core functional requirements as a set of use-cases. |
| Approach: | They propose a linguistic knowledge-based approach to extract software requirements from use-cases using a textual representation of the core functional requirements. |
| Outcome: | The proposed method performs better than existing techniques and improves performance. |
Improving Knowledge Base Construction from Robust Infobox Extraction (N19-2)
Copied to clipboard
| Challenge: | Existing knowledge bases are incomplete, resulting in poor answers and incompleteness. |
| Approach: | They propose a method to extract Wikipedia infobox tables to populate an existing KB. |
| Outcome: | The proposed method improves accuracy and completeness of the final KB significantly compared to DBpedia's baseline method. |
A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling (N19-2)
Copied to clipboard
| Challenge: | Existing methods for complex dialog management require limited training data. |
| Approach: | They propose a method for intent recognition for complex dialog management in low resource situations . they use windowed word n-grams, POS tag n grams and pre-trained word embeddings as features . |
| Outcome: | The proposed method performs better with less than 1% of the data size than existing methods but requires considerably more data. |
Train One Get One Free: Partially Supervised Neural Network for Bug Report Duplicate Detection and Clustering (N19-2)
Copied to clipboard
| Challenge: | Existing methods for duplicate classification require manual review and assigning bugs to the correct teams. |
| Approach: | They propose a loss function that can detect duplicate bug reports and aggregate them into latent topics without supervision. |
| Outcome: | The proposed model outperforms state-of-the-art methods for duplicate classification on both cases and can learn meaningful latent clusters without supervision. |
Robust Semantic Parsing with Adversarial Learning for Domain Generalization (N19-2)
Copied to clipboard
| Challenge: | Using adversarial learning to train models on a higher level of abstraction to increase their robustness to lexical and stylistic variations is crucial for the integration of Semantic Parsing technologies in real applications. |
| Approach: | They propose to perform Semantic Parsing with a domain classification adversarial task and an unsupervised domain discovery approach that yields equivalent improvements. |
| Outcome: | The proposed approach improves on a French corpus of encyclopedic documents annotated with FrameNet and an unsupervised domain discovery approach yields equivalent improvements. |
TOI-CNN: a Solution of Information Extraction on Chinese Insurance Policy (N19-2)
Copied to clipboard
| Challenge: | Existing methods for Element Tagging on insurance policies can be used to streamline manual review of hundreds of contracts. |
| Approach: | They propose a text-of-interest convolutional neural network (TOI-CNN) to replace traditional pooling layer for processing nested phrasal or clausal elements in insurance policies. |
| Outcome: | The proposed method can automatically convert a massive amount of insurance policies into structural archives for management and comparison. |
Cross-lingual Transfer Learning for Japanese Named Entity Recognition (N19-2)
Copied to clipboard
| Challenge: | a recent study focuses on bootstrapping named entity models from English to Japanese . TL is a technique that overcomes linguistic differences between the target and source languages . |
| Approach: | They propose to use a deep neural network model to transfer weights between languages . they also propose a novel approach that romanizes a portion of the Japanese input . |
| Outcome: | The proposed approach overcomes linguistic differences by romanizing a portion of the Japanese input. |
Neural Text Normalization with Subword Units (N19-2)
Copied to clipboard
| Challenge: | Text normalization (TN) is an important step in conversational systems. |
| Approach: | They frame text normalization as a machine translation task and tackle it with sequence-to-sequence models. |
| Outcome: | The proposed model normalizes written text to its spoken form to facilitate speech recognition and text-to-speech synthesis. |
Audio De-identification - a New Entity Recognition Task (N19-2)
Copied to clipboard
Ido Cohn, Itay Laish, Genady Beryozkin, Gang Li, Izhak Shafran, Idan Szpektor, Tzvika Hartman, Avinatan Hassidim, Yossi Matias
| Challenge: | Named Entity Recognition (NER) is an important step in de-identification (de-ID) of medical records, many of which are recorded conversations between a patient and a doctor. |
| Approach: | They propose to use Named Entity Recognition (NER) to detect audio spans with entity mentions in medical records and then use it to evaluate the results. |
| Outcome: | The proposed pipeline is based on a large labeled segment of the Switchboard and Fisher audio datasets and compares it with a benchmark. |
In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data (N19-2)
Copied to clipboard
Nishant Prateek, Mateusz Łajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, Trevor Wood
| Challenge: | Recent advances in text-to-speech synthesis have enabled researchers to generate high-quality speech with a wide range of prosodic variations. |
| Approach: | They propose a model that can synthesise newscaster-style speech with a few hours of data . they propose to factor in contextual word embeddings and evaluate it against neutral synthesis . |
| Outcome: | The proposed model can synthesise newscaster-style speech with just a few hours of data. |
Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems (N19-2)
Copied to clipboard
| Challenge: | Existing datasets for grammatical error correction don’t capture the distribution of errors that data-driven generators are likely to make. |
| Approach: | They propose a framework that allows candidates to be filtered and ranked to select the best response. |
| Outcome: | The proposed framework can be scaled with relatively low effort and achieve high precision with reasonable recall on a weather domain dataset. |
Content-based Dwell Time Engagement Prediction Model for News Articles (N19-2)
Copied to clipboard
| Challenge: | Existing studies on article dwell time prediction are noisy and may not show the actual user engagement or satisfaction. |
| Approach: | They propose a deep neural network architecture to extract emotion, event and entity features from an article and learn interactions among them. |
| Outcome: | The proposed model outperforms state-of-the-art models on a real newspaper dataset. |