arXiv subjects

Yifan Gao

Publications and source records attributed to Yifan Gao.

117 records · Page 7Linked to original sources

arXiv2020

Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited in their decision making due to struggles in extracting question-related rules and reasoning about them. In this paper, we present a new framework of conversational machine reading that comprises a novel Explicit Memory Tracker (EMT) to track whether conditions listed in the rule text have already been satisfied to make a decision. Moreover, our framework generates clarification questions by adopting a coarse-to-fine reasoning strategy, utilizing sentence-level entailment scores to weight token-level distributions. On the ShARC benchmark (blind, held-out) testset, EMT achieves new state-of-the-art results of 74.6% micro-averaged decision accuracy and 49.5 BLEU4. We also show that EMT is more interpretable by visualizing the entailment-oriented reasoning process as the conversation flows. Code and models are released at https://github.com/Yifan-Gao/explicit_memory_tracker.

cs.CL↗

arXiv2019

Improving Question Generation With to the Point Context

Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence. A major challenge in QG is to identify answer-relevant context words to finish the declarative-to-interrogative sentence transformation. Existing sequence-to-sequence neural models achieve this goal by proximity-based answer position encoding under the intuition that neighboring words of answers are of high possibility to be answer-relevant. However, such intuition may not apply to all cases especially for sentences with complex answer-relevant relations. Consequently, the performance of these models drops sharply when the relative distance between the answer fragment and other non-stop sentence words that also appear in the ground truth question increases. To address this issue, we propose a method to jointly model the unstructured sentence and the structured answer-relevant relation (extracted from the sentence in advance) for question generation. Specifically, the structured answer-relevant relation acts as the to the point context and it thus naturally helps keep the generated question to the point, while the unstructured sentence provides the full information. Extensive experiments show that to the point context helps our question generation model achieve significant improvements on several automatic evaluation metrics. Furthermore, our model is capable of generating diverse questions for a sentence which conveys multiple relations of its answer fragment.

cs.CL↗

arXiv2019

Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling

We study the problem of generating interconnected questions in question-answering style conversations. Compared with previous works which generate questions based on a single sentence (or paragraph), this setting is different in two major aspects: (1) Questions are highly conversational. Almost half of them refer back to conversation history using coreferences. (2) In a coherent conversation, questions have smooth transitions between turns. We propose an end-to-end neural model with coreference alignment and conversation flow modeling. The coreference alignment modeling explicitly aligns coreferent mentions in conversation history with corresponding pronominal references in generated questions, which makes generated questions interconnected to conversation history. The conversation flow modeling builds a coherent conversation by starting questioning on the first few sentences in a text passage and smoothly shifting the focus to later parts. Extensive experiments show that our system outperforms several baselines and can generate highly conversational questions. The code implementation is released at https://github.com/Evan-Gao/conversational-QG.

cs.CL↗

arXiv2019

Difficulty Controllable Generation of Reading Comprehension Questions

We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG). Taking as input a sentence in the reading comprehension paragraph and some of its text fragments (i.e., answers) that we want to ask questions about, a DQG method needs to generate questions each of which has a given text fragment as its answer, and meanwhile the generation is under the control of specified difficulty labels---the output questions should satisfy the specified difficulty as much as possible. To solve this task, we propose an end-to-end framework to generate questions of designated difficulty levels by exploring a few important intuitions. For evaluation, we prepared the first dataset of reading comprehension questions with difficulty labels. The results show that the question generated by our framework not only have better quality under the metrics like BLEU, but also comply with the specified difficulty labels.

cs.CL↗

arXiv2019

Title-Guided Encoding for Keyphrase Generation

Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP). Most previous methods solve this problem in an extractive manner, while recently, several attempts are made under the generative setting using deep neural networks. However, the state-of-the-art generative methods simply treat the document title and the document main body equally, ignoring the leading role of the title to the overall document. To solve this problem, we introduce a new model called Title-Guided Network (TG-Net) for automatic keyphrase generation task based on the encoder-decoder architecture with two new features: (i) the title is additionally employed as a query-like input, and (ii) a title-guided encoder gathers the relevant information from the title to each word in the document. Experiments on a range of KG datasets demonstrate that our model outperforms the state-of-the-art models with a large margin, especially for documents with either very low or very high title length ratios.

cs.CL↗

arXiv2018

Generating Distractors for Reading Comprehension Questions from Real Examinations

We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations. In contrast to all previous works, we do not aim at preparing words or short phrases distractors, instead, we endeavor to generate longer and semantic-rich distractors which are closer to distractors in real reading comprehension from examinations. Taking a reading comprehension article, a pair of question and its correct option as input, our goal is to generate several distractors which are somehow related to the answer, consistent with the semantic context of the question and have some trace in the article. We propose a hierarchical encoder-decoder framework with static and dynamic attention mechanisms to tackle this task. Specifically, the dynamic attention can combine sentence-level and word-level attention varying at each recurrent time step to generate a more readable sequence. The static attention is to modulate the dynamic attention not to focus on question irrelevant sentences or sentences which contribute to the correct option. Our proposed framework outperforms several strong baselines on the first prepared distractor generation dataset of real reading comprehension questions. For human evaluation, compared with those distractors generated by baselines, our generated distractors are more functional to confuse the annotators.

cs.CL↗

arXiv2018

The Effectiveness of Traditional Tools and Computer-Aided Technologies for Health and Safety Training in the Construction Sector: A Systematic Review

For workers, the exposure to on-site hazards can result in fatalities and serious injuries. To improve safety outcomes, different approaches have been implemented for health and safety training in the construction sector, such as traditional tools and computer-aided technologies (e.g., serious games and virtual reality). However, the effectiveness of these approaches has been barely explored. In order to bridge this gap, a systematic review of existing studies was conducted. Unlike previous review studies in this field that focused on uncovering the technology characters and challenges, this study mainly evaluated the effectiveness of training using traditional tools and computer-aided technologies on the well-being of individuals. Measures of the effectiveness included knowledge acquisition, unsafe behaviour alteration, and injury rate reduction. Results indicated that: 1. the effectiveness of traditional tools is sufficiently supported by statistical evidence; and 2. the use of computer-aided technologies has evidence to support its effectiveness, but more solid evidence is required to support this statement. It was also found that the overall performance of computer-aided technologies is superior in several technical aspects compared to traditional tools, namely, representing actual workplace situations, providing text-free interfaces, having better user engagement, and being more cost-efficient. Finally, using the systematic review findings, a theoretical framework is proposed as a potential solution to help future research in this field systematically examine the effectiveness and usability of their approaches. This framework is theoretical in nature and requires further validation. A further study is therefore proposed to test and validate this framework.

cs.CY↗

arXiv2018

Multi-objective Non-cooperative Game Model for Cost-based Task Scheduling in Computational Grid

Task scheduling is an important and complex problem in computational grid. A computational grid often covers a range of different kinds of nodes, which offers a complex environment. There is a need to develop algorithms that can capture this complexity as while as can be easily implemented and used to solve a wide range of load-balancing scenarios. In this paper, we propose a game theory based algorithm to the grid load balancing problem on the principle of minimizing the cost of the grid. The grid load-balancing problem is treated as a non-cooperative game. The experiment results demonstrate that the game based algorithm has a desirable capability to reduce the cost of the grid.

cs.DC↗

arXiv2017

Learning Multi-level Features For Sensor-based Human Action Recognition

This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor. The framework consists of three phases, respectively designed to analyze signal-based (low-level), components (mid-level) and semantic (high-level) information. Low-level features capture the time and frequency domain property while mid-level representations learn the composition of the action. The Max-margin Latent Pattern Learning (MLPL) method is proposed to learn high-level semantic descriptions of latent action patterns as the output of our framework. The proposed method achieves the state-of-the-art performances, 88.7%, 98.8% and 72.6% (weighted F1 score) respectively, on Skoda, WISDM and OPP datasets.

cs.CV↗