1 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Semantic Categorization of Social Knowledge for Commonsense Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Mapping probability word problems to executable representations ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Contrastive Domain Adaptation for Question Answering using Limited Text Corpora ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Smoothing Dialogue States for Open Conversational Machine Reading ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.299/ Abstract: Conversational machine reading (CMR) requires machines to communicate with humans through multi-turn interactions between two salient dialogue states of decision making and question generation processes. In open CMR settings, as the more realistic scenario, the retrieved background knowledge would be noisy, which results in severe challenges in the information transmission. Existing studies commonly train independent or pipeline systems for the two subtasks. However, those methods are trivial by using hard-label decisions to activate question generation, which eventually hinders the model performance. In this work, we propose an effective gating strategy by smoothing the two dialogue states in only one decoder and bridge decision making and question generation to provide a richer dialogue state reference. Experiments on the OR-ShARC dataset show the effectiveness of our method, which achieves new state-of-the-art results. ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Question-Answering Systems
|
|
URL: https://dx.doi.org/10.48448/nf5h-wd78 https://underline.io/lecture/38046-smoothing-dialogue-states-for-open-conversational-machine-reading
|
|
BASE
|
|
Hide details
|
|
14 |
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Zero-Shot Dialogue State Tracking via Cross-Task Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Case-based Reasoning for Natural Language Queries over Knowledge Bases ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|