paper-with-me

홈 › Papers

A Multi-answer Multi-task Framework for Real-world Machine Reading Comprehension

2018-10-01 · EMNLP 2018 10 · Jiahua Liu, Wan Wei, Maosong Sun, Hao Chen, Yantao Du, Dekang Lin

The task of machine reading comprehension (MRC) has evolved from answering simple questions from well-edited text to answering real questions from users out of web data. In the real-world setting, full-body text from multiple relevant documents in the top search results are provided as context for questions from user queries, including not only questions with a single, short, and factual answer, but also questions about reasons, procedures, and opinions. In this case, multiple answers could be equally valid for a single question and each answer may occur multiple times in the context, which should be taken into consideration when we build MRC system. We propose a multi-answer multi-task framework, in which different loss functions are used for multiple reference answers. Minimum Risk Training is applied to solve the multi-occurrence problem of a single answer. Combined with a simple heuristic passage extraction strategy for overlong documents, our model increases the ROUGE-L score on the DuReader dataset from 44.18, the previous state-of-the-art, to 51.09.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalMachine Reading ComprehensionQuestion AnsweringReading Comprehensionvalid

Similar Papers 제목 키워드 기반

VOGUE: Answer Verbalization through Multi-Task Learning

2021-06-24 · Endri Kacupaj, Shyamnath Premnadh, Kuldeep Singh, Jens Lehmann 외

In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not …

Answer GenerationKnowledge GraphsMulti-Task LearningQuestion Answering

A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

2014-10-01 · NeurIPS 2014 12 · Mateusz Malinowski, Mario Fritz

We propose a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision. We combine discrete reasoning with uncertain predictions b…

Question Answering

Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering

2023-01-01 · CVPR 2023 1 · Chuanqi Zang, Hanqing Wang, Mingtao Pei, Wei Liang

Video Question Answering (VideoQA) is challenging as it requires capturing accurate correlations between modalities from redundant information. Recent methods focus on the explicit challenges of the task, e.g. multim…

Question AnsweringVideo Question Answering

CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers

2022-10-01 · COLING 2022 10 · Yiming Ju, Weikang Wang, Yuanzhe Zhang, Suncong Zheng 외

Forcing the answer of the Question Answering (QA) task to be a single text span might be restrictive since the answer can be multiple spans in the context. Moreover, we found that multi-span answers often appear with two…

Question Answering

SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding

2026-04-14 · Tanzila Rahman, Renjie Liao, Leonid Sigal arxiv

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and …

Video Object SegmentationSynthetic Data GenerationVisual Question AnsweringVisual Grounding